From c93126a46247768c0623c4c9b7ae58155b571ced Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" <41898282+github-actions[bot]@users.noreply.github.com> Date: Thu, 12 Nov 2026 12:38:53 +0000 Subject: [PATCH] Update LiteLLM model snapshot --- models/data/litellm_snapshot.json | 63721 +++++++++++++++++++--------- 1 file changed, 42611 insertions(+), 21110 deletions(-) diff --git a/models/data/litellm_snapshot.json b/models/data/litellm_snapshot.json index 99471d48..5a7e4e95 100644 --- a/models/data/litellm_snapshot.json +++ b/models/data/litellm_snapshot.json @@ -1,4 +1,172 @@ { + "azure/gpt-realtime-2.1-2026-07-07": { + "cache_creation_input_audio_token_cost": 4e-07, + "cache_read_input_audio_token_cost": 4e-07, + "cache_read_input_token_cost": 4e-07, + "deprecation_date": "2027-06-25", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_audio_token": 3.2e-05, + "input_cost_per_image_token": 5e-06, + "input_cost_per_token": 4e-06, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "mode": "realtime", + "provider_specific_entry": { + "realtime_ga_only": 1 + }, + "output_cost_per_audio_token": 6.4e-05, + "output_cost_per_token": 2.4e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "cache_read_input_image_token_cost": 5e-07, + "supports_prompt_caching": true, + "supports_reasoning": true + }, + "azure/gpt-realtime-2.1-mini-2026-07-07": { + "cache_creation_input_audio_token_cost": 3e-07, + "cache_read_input_audio_token_cost": 3e-07, + "cache_read_input_token_cost": 6e-08, + "deprecation_date": "2027-06-25", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_audio_token": 1e-05, + "input_cost_per_image_token": 8e-07, + "input_cost_per_token": 6e-07, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "mode": "realtime", + "provider_specific_entry": { + "realtime_ga_only": 1 + }, + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 2.4e-06, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "cache_read_input_image_token_cost": 8e-08, + "supports_prompt_caching": true, + "supports_reasoning": true + }, + "azure/gpt-realtime-translate-2026-05-06": { + "input_cost_per_second": 0.0005666666666666667, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "mode": "realtime", + "provider_specific_entry": { + "realtime_ga_only": 1 + }, + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/a-new-chapter-for-realtime-ai-reasoning-translation-and-real-time-transcription/4517124", + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "audio", + "text" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_native_streaming": true + }, + "azure/gpt-realtime-translate-2026-05-07": { + "input_cost_per_second": 0.0005666666666666667, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "mode": "realtime", + "provider_specific_entry": { + "realtime_ga_only": 1 + }, + "source": "https://ai.azure.com/catalog/models/gpt-realtime-translate", + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "audio", + "text" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_native_streaming": true + }, + "azure/gpt-realtime-whisper-2026-05-06": { + "input_cost_per_second": 0.0002833333333333333, + "litellm_provider": "azure", + "mode": "audio_transcription", + "provider_specific_entry": { + "realtime_ga_only": 1 + }, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/gpt-realtime-whisper", + "supported_endpoints": [ + "/v1/realtime", + "/v1/realtime/transcription_sessions" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "max_input_tokens": 32000, + "max_output_tokens": 4096 + }, + "azure/gpt-realtime-whisper-2026-05-07": { + "input_cost_per_second": 0.0002833333333333333, + "litellm_provider": "azure", + "mode": "audio_transcription", + "provider_specific_entry": { + "realtime_ga_only": 1 + }, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/gpt-realtime-whisper", + "supported_endpoints": [ + "/v1/realtime", + "/v1/realtime/transcription_sessions" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "max_input_tokens": 32000, + "max_output_tokens": 4096 + }, "sample_spec": { "code_interpreter_cost_per_session": 0.0, "computer_use_input_cost_per_1k_tokens": 0.0, @@ -9,9 +177,8 @@ "input_cost_per_audio_token": 0.0, "input_cost_per_token": 0.0, "litellm_provider": "one of https://docs.litellm.ai/docs/providers", - "max_input_tokens": "max input tokens, if the provider specifies it. if not default to max_tokens", - "max_output_tokens": "max output tokens, if the provider specifies it. if not default to max_tokens", - "max_tokens": "LEGACY parameter. set to max_output_tokens if provider specifies it. IF not set to max_input_tokens, if provider specifies it.", + "max_input_tokens": "max input tokens, if the provider specifies it", + "max_output_tokens": "max output tokens, if the provider specifies it", "mode": "one of: chat, embedding, completion, image_generation, audio_transcription, audio_speech, image_generation, moderation, rerank, search", "output_cost_per_reasoning_token": 0.0, "output_cost_per_token": 0.0, @@ -41,6 +208,7 @@ }, "1024-x-1024/50-steps/bedrock/amazon.nova-canvas-v1:0": { "deprecation_date": "2026-09-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "litellm_provider": "bedrock", "max_input_tokens": 2600, "mode": "image_generation", @@ -49,37 +217,132 @@ "1024-x-1024/50-steps/stability.stable-diffusion-xl-v1": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.04 }, "1024-x-1024/max-steps/stability.stable-diffusion-xl-v1": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.08 }, "512-x-512/50-steps/stability.stable-diffusion-xl-v0": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.018 }, "512-x-512/max-steps/stability.stable-diffusion-xl-v0": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.036 }, + "abliteration/abliterated-model": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "abliteration", + "max_input_tokens": 262144, + "max_output_tokens": 262134, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://abliteration.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "reasoning_effort_levels": [ + "none", + "minimal", + "low", + "medium", + "high", + "xhigh", + "max" + ] + }, + "abliteration/abliterated-model-large": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "abliteration", + "max_input_tokens": 1000000, + "max_output_tokens": 999990, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://abliteration.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "reasoning_effort_levels": [ + "none", + "minimal", + "low", + "medium", + "high", + "xhigh", + "max" + ] + }, + "abliteration/abliterated-model-large-v2": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "abliteration", + "max_input_tokens": 1000000, + "max_output_tokens": 999990, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://abliteration.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_none_reasoning_effort": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "reasoning_effort_levels": [ + "minimal", + "low", + "medium", + "high", + "xhigh", + "max" + ] + }, + "abliteration/abliterated-model-large-flash": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "abliteration", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://abliteration.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "reasoning_effort_levels": [ + "none", + "minimal", + "low", + "medium", + "high", + "xhigh", + "max" + ] + }, "ai21.j2-mid-v1": { "input_cost_per_token": 1.25e-05, "litellm_provider": "bedrock", "max_input_tokens": 8191, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 1.25e-05, "source": "https://aws.amazon.com/bedrock/pricing/" @@ -89,39 +352,37 @@ "litellm_provider": "bedrock", "max_input_tokens": 8191, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 1.88e-05, "source": "https://aws.amazon.com/bedrock/pricing/" }, "ai21.jamba-1-5-large-v1:0": { "deprecation_date": "2026-11-26", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-ai21-labs-jamba-1-5-large.md", "input_cost_per_token": 2e-06, "litellm_provider": "bedrock", "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 8e-06, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-ai21-labs-jamba-1-5-large.md" }, "ai21.jamba-1-5-mini-v1:0": { "deprecation_date": "2026-11-26", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-ai21-labs-jamba-1-5-mini.md", "input_cost_per_token": 2e-07, "litellm_provider": "bedrock", "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 4e-07, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-ai21-labs-jamba-1-5-mini.md" }, "ai21.jamba-instruct-v1:0": { "input_cost_per_token": 5e-07, "litellm_provider": "bedrock", "max_input_tokens": 70000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7e-07, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -278,6 +539,7 @@ }, "amazon.nova-canvas-v1:0": { "deprecation_date": "2026-09-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "litellm_provider": "bedrock", "max_input_tokens": 2600, "mode": "image_generation", @@ -286,6 +548,7 @@ }, "us.amazon.nova-canvas-v1:0": { "deprecation_date": "2026-09-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "litellm_provider": "bedrock", "max_input_tokens": 2600, "mode": "image_generation", @@ -293,73 +556,84 @@ "supports_nova_canvas_image_edit": true }, "us.writer.palmyra-x4-v1:0": { + "deprecation_date": "2027-03-09", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x4.md", "input_cost_per_token": 2.5e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-05, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x4.md", "supports_function_calling": true, "supports_pdf_input": true }, "us.writer.palmyra-x5-v1:0": { + "deprecation_date": "2027-03-21", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x5.md", "input_cost_per_token": 6e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x5.md", "supports_function_calling": true, "supports_pdf_input": true }, "writer.palmyra-x4-v1:0": { + "deprecation_date": "2027-03-09", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x4.md", "input_cost_per_token": 2.5e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-05, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x4.md", "supports_function_calling": true, "supports_pdf_input": true }, "writer.palmyra-x5-v1:0": { + "deprecation_date": "2027-03-21", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x5.md", "input_cost_per_token": 6e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x5.md", "supports_function_calling": true, "supports_pdf_input": true }, "writer.palmyra-vision-7b": { "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "input_cost_per_token_flex": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_flex": 3e-07, + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_vision": true }, "amazon.nova-lite-v1:0": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 6e-08, + "input_cost_per_token_batches": 3e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 2.4e-07, + "output_cost_per_token_batches": 1.2e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -369,13 +643,18 @@ }, "amazon.nova-2-lite-v1:0": { "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_priority": 1.3125e-07, "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_priority": 4.375e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -386,16 +665,20 @@ "supports_vision": true }, "amazon.nova-2-pro-preview-20251202-v1:0": { - "cache_read_input_token_cost": 5.46875e-07, - "input_cost_per_token": 2.1875e-06, - "input_cost_per_image_token": 2.1875e-06, - "input_cost_per_audio_token": 2.1875e-06, + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_image_token": 1.25e-06, + "input_cost_per_audio_token": 1.25e-06, + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_priority": 2.1875e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 1.75e-05, + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_priority": 1.75e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -406,14 +689,13 @@ "supports_vision": true }, "apac.amazon.nova-2-lite-v1:0": { - "cache_read_input_token_cost": 8.25e-08, - "input_cost_per_token": 3.3e-07, + "cache_read_input_token_cost": 9.9e-08, + "input_cost_per_token": 3.96e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 2.75e-06, + "output_cost_per_token": 3.311e-06, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -424,16 +706,16 @@ "supports_vision": true }, "apac.amazon.nova-2-pro-preview-20251202-v1:0": { - "cache_read_input_token_cost": 5.46875e-07, - "input_cost_per_token": 2.1875e-06, - "input_cost_per_image_token": 2.1875e-06, - "input_cost_per_audio_token": 2.1875e-06, + "cache_read_input_token_cost": 3.4375e-07, + "input_cost_per_token": 1.375e-06, + "input_cost_per_image_token": 1.375e-06, + "input_cost_per_audio_token": 1.375e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 1.75e-05, + "output_cost_per_token": 1.1e-05, + "source": "https://aws.amazon.com/nova/pricing/", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -444,14 +726,13 @@ "supports_vision": true }, "eu.amazon.nova-2-lite-v1:0": { - "cache_read_input_token_cost": 8.25e-08, - "input_cost_per_token": 3.3e-07, + "cache_read_input_token_cost": 1.0725e-07, + "input_cost_per_token": 4.29e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 2.75e-06, + "output_cost_per_token": 3.597e-06, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -462,16 +743,16 @@ "supports_vision": true }, "eu.amazon.nova-2-pro-preview-20251202-v1:0": { - "cache_read_input_token_cost": 5.46875e-07, - "input_cost_per_token": 2.1875e-06, - "input_cost_per_image_token": 2.1875e-06, - "input_cost_per_audio_token": 2.1875e-06, + "cache_read_input_token_cost": 3.4375e-07, + "input_cost_per_token": 1.375e-06, + "input_cost_per_image_token": 1.375e-06, + "input_cost_per_audio_token": 1.375e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 1.75e-05, + "output_cost_per_token": 1.1e-05, + "source": "https://aws.amazon.com/nova/pricing/", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -483,13 +764,21 @@ }, "us.amazon.nova-2-lite-v1:0": { "cache_read_input_token_cost": 8.25e-08, + "cache_read_input_token_cost_flex": 4.125e-08, + "cache_read_input_token_cost_priority": 1.44375e-07, "input_cost_per_token": 3.3e-07, + "input_cost_per_token_batches": 1.65e-07, + "input_cost_per_token_flex": 1.65e-07, + "input_cost_per_token_priority": 5.775e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.75e-06, + "output_cost_per_token_batches": 1.375e-06, + "output_cost_per_token_flex": 1.375e-06, + "output_cost_per_token_priority": 4.8125e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -500,16 +789,20 @@ "supports_vision": true }, "us.amazon.nova-2-pro-preview-20251202-v1:0": { - "cache_read_input_token_cost": 5.46875e-07, - "input_cost_per_token": 2.1875e-06, - "input_cost_per_image_token": 2.1875e-06, - "input_cost_per_audio_token": 2.1875e-06, + "cache_read_input_token_cost": 3.4375e-07, + "input_cost_per_token": 1.375e-06, + "input_cost_per_image_token": 1.375e-06, + "input_cost_per_audio_token": 1.375e-06, + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.40625e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 1.75e-05, + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 1.925e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -522,7 +815,6 @@ "amazon.nova-2-multimodal-embeddings-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 8172, - "max_tokens": 8172, "mode": "embedding", "input_cost_per_token": 1.35e-07, "input_cost_per_image": 6e-05, @@ -539,26 +831,57 @@ "amazon.nova-micro-v1:0": { "cache_read_input_token_cost": 8.75e-09, "input_cost_per_token": 3.5e-08, + "input_cost_per_token_batches": 1.75e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.4e-07, + "output_cost_per_token_batches": 7e-08, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, + "amazon.nova-premier-v1:0": { + "cache_read_input_token_cost": 6.25e-07, + "cache_read_input_token_cost_priority": 1.09375e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "input_cost_per_token_priority": 4.375e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 1.25e-05, + "output_cost_per_token_batches": 6.25e-06, + "output_cost_per_token_priority": 2.1875e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "amazon.nova-pro-v1:0": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_flex": 1e-07, + "cache_read_input_token_cost_priority": 3.5e-07, "input_cost_per_token": 8e-07, + "input_cost_per_token_batches": 4e-07, + "input_cost_per_token_flex": 4e-07, + "input_cost_per_token_priority": 1.4e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.2e-06, + "output_cost_per_token_batches": 1.6e-06, + "output_cost_per_token_flex": 1.6e-06, + "output_cost_per_token_priority": 5.6e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -570,9 +893,12 @@ "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 3.3e-07, "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2.75e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-2-sonic.md", "supports_audio_input": true, "supports_audio_output": true }, @@ -582,7 +908,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "rerank", "output_cost_per_token": 0.0 }, @@ -591,7 +916,6 @@ "input_cost_per_token": 8e-07, "litellm_provider": "bedrock", "max_input_tokens": 128, - "max_tokens": 128, "metadata": { "notes": "'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead." }, @@ -606,7 +930,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536 @@ -615,7 +938,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536 @@ -624,7 +946,6 @@ "input_cost_per_token": 2e-08, "litellm_provider": "bedrock", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -639,26 +960,30 @@ "mode": "image_generation" }, "amazon.titan-image-generator-v2": { + "deprecation_date": "2026-06-30", "input_cost_per_image": 0.0, "output_cost_per_image": 0.008, "litellm_provider": "bedrock", - "mode": "image_generation" + "mode": "image_generation", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-titan-image-generator-g1-v2.html" }, "amazon.titan-image-generator-v2:0": { + "deprecation_date": "2026-06-30", "input_cost_per_image": 0.0, "output_cost_per_image": 0.008, "litellm_provider": "bedrock", - "mode": "image_generation" + "mode": "image_generation", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-titan-image-generator-g1-v2.html" }, "twelvelabs.marengo-embed-2-7-v1:0": { "deprecation_date": "2026-11-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_query": 7e-05, "input_cost_per_video_per_second": 0.0007, "input_cost_per_audio_per_second": 0.00014, "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -667,13 +992,13 @@ }, "us.twelvelabs.marengo-embed-2-7-v1:0": { "deprecation_date": "2026-11-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_query": 7e-05, "input_cost_per_video_per_second": 0.0007, "input_cost_per_audio_per_second": 0.00014, "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -682,13 +1007,13 @@ }, "eu.twelvelabs.marengo-embed-2-7-v1:0": { "deprecation_date": "2026-11-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_query": 7e-05, "input_cost_per_video_per_second": 0.0007, "input_cost_per_audio_per_second": 0.00014, "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -702,7 +1027,6 @@ "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 500, - "max_tokens": 500, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 512, @@ -716,7 +1040,6 @@ "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 500, - "max_tokens": 500, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 512, @@ -730,7 +1053,6 @@ "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 500, - "max_tokens": 500, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 512, @@ -738,58 +1060,66 @@ "supports_image_input": true }, "twelvelabs.pegasus-1-2-v1:0": { + "deprecation_date": "2027-03-22", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md", "input_cost_per_video_per_second": 0.00049, "output_cost_per_token": 7.5e-06, "litellm_provider": "bedrock", "mode": "chat", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md", "supports_video_input": true }, "us.twelvelabs.pegasus-1-2-v1:0": { + "deprecation_date": "2027-03-22", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md", "input_cost_per_video_per_second": 0.00049, "output_cost_per_token": 7.5e-06, "litellm_provider": "bedrock", "mode": "chat", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md", "supports_video_input": true }, "eu.twelvelabs.pegasus-1-2-v1:0": { + "deprecation_date": "2027-03-22", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md", "input_cost_per_video_per_second": 0.00049, "output_cost_per_token": 7.5e-06, "litellm_provider": "bedrock", "mode": "chat", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md", "supports_video_input": true }, "global.twelvelabs.pegasus-1-2-v1:0": { + "deprecation_date": "2027-03-22", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md", "input_cost_per_video_per_second": 0.00049, "output_cost_per_token": 7.5e-06, "litellm_provider": "bedrock", "mode": "chat", "supports_video_input": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md" }, "amazon.titan-text-express-v1": { - "input_cost_per_token": 1.3e-06, + "input_cost_per_token": 2e-07, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", - "output_cost_per_token": 1.7e-06 + "output_cost_per_token": 6e-07 }, "amazon.titan-text-lite-v1": { - "input_cost_per_token": 3e-07, + "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", - "output_cost_per_token": 4e-07 + "output_cost_per_token": 2e-07 }, "amazon.titan-text-premier-v1:0": { "input_cost_per_token": 5e-07, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-06 }, @@ -800,7 +1130,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-06, "supports_assistant_prefill": true, @@ -820,7 +1149,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", @@ -837,7 +1165,11 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5e-07, - "output_cost_per_token_batches": 2.5e-06 + "output_cost_per_token_batches": 2.5e-06, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "anthropic.claude-haiku-4-5@20251001": { "cache_creation_input_token_cost": 1.25e-06, @@ -848,7 +1180,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", @@ -864,14 +1195,14 @@ "supports_native_streaming": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "token_count_model": {"model":"anthropic.claude-haiku-4-5-20251001-v1:0","litellm_provider":"bedrock"} }, "anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -879,10 +1210,6 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 3e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07 }, @@ -891,9 +1218,8 @@ "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -903,11 +1229,7 @@ "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 3e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07 + "supports_vision": true }, "anthropic.claude-3-7-sonnet-20240620-v1:0": { "cache_creation_input_token_cost": 4.5e-06, @@ -916,7 +1238,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -936,7 +1257,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -954,7 +1274,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_function_calling": true, @@ -969,7 +1288,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-06, "supports_tool_choice": true @@ -978,11 +1296,11 @@ "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, "deprecation_date": "2027-01-08", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 1.5e-05, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { @@ -999,7 +1317,11 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "token_count_model": { + "model": "anthropic.claude-opus-4-1-20250805-v1:0", + "litellm_provider": "bedrock" + } }, "anthropic.claude-opus-4-20250514-v1:0": { "cache_creation_input_token_cost": 1.875e-05, @@ -1008,7 +1330,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { @@ -1036,7 +1357,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -1058,7 +1378,11 @@ "bedrock_output_config_effort_ceiling": "high", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-4-5-20251101-v1:0", + "litellm_provider": "bedrock" + } }, "anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, @@ -1071,7 +1395,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -1094,7 +1417,11 @@ "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-4-6-v1", + "litellm_provider": "bedrock" + } }, "global.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, @@ -1107,7 +1434,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -1130,7 +1456,11 @@ "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-6-v1", + "litellm_provider": "bedrock" + } }, "us.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, @@ -1143,7 +1473,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -1166,7 +1495,11 @@ "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-6-v1", + "litellm_provider": "bedrock" + } }, "eu.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, @@ -1179,7 +1512,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -1202,7 +1534,11 @@ "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-6-v1", + "litellm_provider": "bedrock" + } }, "au.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, @@ -1215,7 +1551,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -1238,7 +1573,11 @@ "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-6-v1", + "litellm_provider": "bedrock" + } }, "anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1251,7 +1590,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -1276,7 +1614,12 @@ "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-4-7", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "anthropic.claude-mythos-preview": { "cache_creation_input_token_cost": 3.4375e-05, @@ -1287,7 +1630,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "thinking_always_on": true, "supports_function_calling": true, @@ -1309,7 +1651,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -1334,7 +1675,12 @@ "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "global.anthropic.claude-opus-4-7", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "us.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1347,7 +1693,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -1372,7 +1717,12 @@ "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-7", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "eu.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1385,7 +1735,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -1410,7 +1759,12 @@ "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-7", + "litellm_provider": "bedrock_mantle", + "region": "eu-west-1" + } }, "au.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1423,7 +1777,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -1448,7 +1801,12 @@ "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-7", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + } }, "anthropic.claude-fable-5": { "cache_creation_input_token_cost": 1.25e-05, @@ -1458,7 +1816,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "search_context_cost_per_query": { @@ -1480,13 +1837,18 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-fable-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.25e-05, @@ -1496,7 +1858,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "search_context_cost_per_query": { @@ -1535,7 +1896,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "search_context_cost_per_query": { @@ -1557,13 +1917,18 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "global.anthropic.claude-fable-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "global.anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.25e-05, @@ -1573,7 +1938,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "search_context_cost_per_query": { @@ -1597,6 +1961,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -1604,6 +1969,9 @@ "prompt_cache_min_tokens": 512, "source": "https://aws.amazon.com/bedrock/pricing/" }, + "bedrock/claude-fable-latest": { + "alias_of": "global.anthropic.claude-fable-5-2" + }, "us.anthropic.claude-fable-5": { "cache_creation_input_token_cost": 1.375e-05, "cache_creation_input_token_cost_above_1hr": 2.2e-05, @@ -1612,7 +1980,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-05, "search_context_cost_per_query": { @@ -1634,13 +2001,18 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-fable-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "us.anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.375e-05, @@ -1650,7 +2022,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-05, "search_context_cost_per_query": { @@ -1674,6 +2045,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -1689,7 +2061,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-05, "search_context_cost_per_query": { @@ -1711,7 +2082,7 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -1727,7 +2098,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-05, "search_context_cost_per_query": { @@ -1751,6 +2121,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -1760,6 +2131,7 @@ "anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, @@ -1769,7 +2141,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -1793,7 +2164,14 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-east-1/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + }, + "input_cost_per_token_batches": 2.5e-06, + "output_cost_per_token_batches": 1.25e-05 }, "anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -1807,7 +2185,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "search_context_cost_per_query": { @@ -1833,11 +2210,17 @@ "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "thinking_always_on": true, - "supports_forced_tool_use": false + "supports_forced_tool_use": false, + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "global.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, @@ -1847,7 +2230,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -1867,11 +2249,19 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-east-1/index.json", + "token_count_model": { + "model": "global.anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + }, + "input_cost_per_token_batches": 2.5e-06, + "output_cost_per_token_batches": 1.25e-05 }, "global.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -1885,7 +2275,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "search_context_cost_per_query": { @@ -1905,17 +2294,27 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "source": "https://aws.amazon.com/bedrock/pricing/", "thinking_always_on": true, - "supports_forced_tool_use": false + "supports_forced_tool_use": false, + "token_count_model": { + "model": "global.anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } + }, + "bedrock/claude-opus-latest": { + "alias_of": "global.anthropic.claude-opus-5-5" }, "us.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 6.875e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, @@ -1925,7 +2324,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -1945,11 +2343,19 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-east-1/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + }, + "input_cost_per_token_batches": 2.75e-06, + "output_cost_per_token_batches": 1.375e-05 }, "us.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -1963,7 +2369,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "search_context_cost_per_query": { @@ -1983,17 +2388,24 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "source": "https://aws.amazon.com/bedrock/pricing/", "thinking_always_on": true, - "supports_forced_tool_use": false + "supports_forced_tool_use": false, + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "eu.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 6.875e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, @@ -2003,7 +2415,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2023,11 +2434,19 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/eu-west-1/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "eu-west-1" + }, + "input_cost_per_token_batches": 2.75e-06, + "output_cost_per_token_batches": 1.375e-05 }, "eu.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -2041,7 +2460,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "search_context_cost_per_query": { @@ -2061,6 +2479,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, @@ -2072,6 +2491,7 @@ "au.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 6.875e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, @@ -2081,7 +2501,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2101,11 +2520,19 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/ap-southeast-2/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + }, + "input_cost_per_token_batches": 2.75e-06, + "output_cost_per_token_batches": 1.375e-05 }, "au.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -2119,7 +2546,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "search_context_cost_per_query": { @@ -2139,17 +2565,24 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "thinking_always_on": true, "supports_forced_tool_use": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + } }, "jp.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 6.875e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, @@ -2159,7 +2592,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2179,11 +2611,14 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/ap-northeast-1/index.json", + "input_cost_per_token_batches": 2.75e-06, + "output_cost_per_token_batches": 1.375e-05 }, "jp.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -2197,7 +2632,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "search_context_cost_per_query": { @@ -2217,6 +2651,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, @@ -2237,7 +2672,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -2257,12 +2691,18 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "global.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -2276,7 +2716,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -2296,12 +2735,19 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "global.anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "us.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -2315,7 +2761,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2335,12 +2780,19 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "eu.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -2354,7 +2806,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2374,12 +2825,19 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "eu-west-1" + } }, "au.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -2393,7 +2851,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2413,12 +2870,19 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + } }, "jp.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -2432,7 +2896,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2452,12 +2915,19 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "ap-northeast-1" + } }, "jp.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -2469,7 +2939,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2494,7 +2963,12 @@ "supports_minimal_reasoning_effort": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-7", + "litellm_provider": "bedrock_mantle", + "region": "ap-northeast-1" + } }, "anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -2506,7 +2980,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "search_context_cost_per_query": { @@ -2515,6 +2988,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -2528,12 +3002,18 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "global.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -2545,7 +3025,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "search_context_cost_per_query": { @@ -2554,6 +3033,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -2567,12 +3047,19 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "global.anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "us.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -2584,7 +3071,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "search_context_cost_per_query": { @@ -2593,6 +3079,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -2606,12 +3093,19 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "eu.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -2623,7 +3117,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "search_context_cost_per_query": { @@ -2632,6 +3125,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -2645,12 +3139,19 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "eu-west-1" + } }, "au.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -2662,7 +3163,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "search_context_cost_per_query": { @@ -2671,6 +3171,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -2684,12 +3185,19 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + } }, "jp.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -2701,7 +3209,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "search_context_cost_per_query": { @@ -2710,6 +3217,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -2723,6 +3231,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -2741,7 +3251,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -2749,7 +3258,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -2763,7 +3272,11 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-6", + "litellm_provider": "bedrock" + } }, "global.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -2776,7 +3289,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -2784,7 +3296,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -2798,7 +3310,11 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-6", + "litellm_provider": "bedrock" + } }, "us.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -2811,7 +3327,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -2819,7 +3334,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -2833,7 +3348,11 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-6", + "litellm_provider": "bedrock" + } }, "eu.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -2846,7 +3365,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -2854,7 +3372,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -2868,7 +3386,11 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-6", + "litellm_provider": "bedrock" + } }, "au.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -2881,7 +3403,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -2889,7 +3410,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -2903,7 +3424,11 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-6", + "litellm_provider": "bedrock" + } }, "jp.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -2916,7 +3441,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -2924,7 +3448,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -2938,21 +3462,26 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-6", + "litellm_provider": "bedrock" + } }, "anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2026-10-14", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "anthropic.claude-sonnet-5", "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -2971,23 +3500,29 @@ "supports_vision": true, "bedrock_converse_supports_strict_tools": false, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-20250514-v1:0", + "litellm_provider": "bedrock" + } }, "anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "deprecation_date": "2027-04-08", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "anthropic.claude-sonnet-5-5", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -3009,14 +3544,17 @@ "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.5e-06, "output_cost_per_token_batches": 7.5e-06, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "anthropic.claude-v1": { "input_cost_per_token": 8e-06, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05 }, @@ -3025,7 +3563,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true @@ -3035,7 +3572,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-07 }, @@ -3044,7 +3580,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-06 }, @@ -3053,7 +3588,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-06, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/codellama-CodeLlama-70b-Instruct-hf" @@ -3063,7 +3597,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/google-gemma-7b-it" @@ -3073,7 +3606,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.5e-07 }, @@ -3082,7 +3614,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-06 }, @@ -3091,7 +3622,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-07 }, @@ -3100,7 +3630,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-06, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-70B-Instruct" @@ -3110,7 +3639,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-8B-Instruct" @@ -3120,7 +3648,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mistral-7B-Instruct-v0.1", @@ -3131,7 +3658,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 65536, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x22B-Instruct-v0.1", @@ -3142,7 +3668,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x7B-Instruct-v0.1", @@ -3154,7 +3679,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 2.52e-07, "supports_function_calling": true, @@ -3170,7 +3694,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.48e-07, "supports_function_calling": true, @@ -3180,13 +3703,15 @@ }, "apac.amazon.nova-pro-v1:0": { "cache_read_input_token_cost": 2.1e-07, + "cache_read_input_token_cost_flex": 1.05e-07, "input_cost_per_token": 8.4e-07, + "input_cost_per_token_flex": 4.2e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.36e-06, + "output_cost_per_token_flex": 1.68e-06, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -3202,7 +3727,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", @@ -3219,21 +3743,26 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5.5e-07, - "output_cost_per_token_batches": 2.75e-06 + "output_cost_per_token_batches": 2.75e-06, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "apac.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2026-10-14", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "apac.anthropic.claude-sonnet-5", "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -3252,7 +3781,11 @@ "supports_vision": true, "bedrock_converse_supports_strict_tools": false, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-20250514-v1:0", + "litellm_provider": "bedrock" + } }, "assemblyai/best": { "input_cost_per_second": 3.333e-05, @@ -3276,11 +3809,13 @@ "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05, "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, + "deprecation_date": "2027-04-08", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "au.anthropic.claude-sonnet-5-5", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -3302,26 +3837,30 @@ "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.65e-06, "output_cost_per_token_batches": 8.25e-06, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "azure/ada": { "deprecation_date": "2028-02-09", - "input_cost_per_token": 1e-07, + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_token": 1.1e-07, "litellm_provider": "azure", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule" + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/codex-mini": { "cache_read_input_token_cost": 3.75e-07, "deprecation_date": "2026-11-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.5e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 6e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -3345,20 +3884,10 @@ "supports_tool_choice": true, "supports_vision": true }, - "azure/command-r-plus": { - "deprecation_date": "2025-06-30", - "input_cost_per_token": 3e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", - "supports_function_calling": true - }, "azure_ai/claude-haiku-4-5": { - "deprecation_date": "2026-10-19", + "deprecation_date": "2026-11-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/claude-haiku-5-5", "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, "cache_read_input_token_cost": 1e-07, @@ -3366,7 +3895,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "supports_assistant_prefill": true, @@ -3378,10 +3906,13 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule" }, "azure_ai/claude-opus-4-5": { - "deprecation_date": "2026-10-19", + "deprecation_date": "2026-11-24", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/claude-opus-5-5", "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, @@ -3389,8 +3920,12 @@ "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "output_cost_per_token": 2.5e-05, "supports_assistant_prefill": true, "supports_computer_use": true, @@ -3402,10 +3937,13 @@ "supports_tool_choice": true, "supports_vision": true, "supports_output_config": true, - "prompt_cache_min_tokens": 4096 + "supports_web_search": true, + "prompt_cache_min_tokens": 4096, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule" }, "azure_ai/claude-opus-4-6": { "deprecation_date": "2027-02-02", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "input_cost_per_token": 5e-06, @@ -3413,7 +3951,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -3434,17 +3971,18 @@ "supports_vision": true, "supports_output_config": true, "supports_max_reasoning_effort": true, + "supports_web_search": true, "prompt_cache_min_tokens": 4096 }, "azure_ai/claude-opus-4-7": { "deprecation_date": "2027-04-06", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "supports_adaptive_thinking": true, "input_cost_per_token": 5e-06, "output_cost_per_token": 2.5e-05, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -3466,17 +4004,18 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, + "supports_web_search": true, "prompt_cache_min_tokens": 2048 }, "azure_ai/claude-fable-5": { "deprecation_date": "2027-12-05", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "supports_mid_conversation_system": true, "input_cost_per_token": 1e-05, "output_cost_per_token": 5e-05, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -3499,7 +4038,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_max_reasoning_effort": true, + "supports_max_reasoning_effort": false, + "supports_web_search": true, "prompt_cache_min_tokens": 512 }, "azure_ai/claude-fable-5-1": { @@ -3509,7 +4049,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -3534,20 +4073,64 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_max_reasoning_effort": true, + "supports_max_reasoning_effort": false, + "supports_web_search": true, + "prompt_cache_min_tokens": 512, + "deprecation_date": "2027-12-05", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement" + }, + "azure_ai/claude-fable-latest": { + "alias_of": "azure_ai/claude-fable-5-2" + }, + "azure_ai/claude-mythos-5-1": { + "input_cost_per_token": 1e-05, + "output_cost_per_token": 5e-05, + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_read_input_token_cost": 2.5e-07, + "deprecation_date": "2027-09-01", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": false, + "supports_web_search": true, "prompt_cache_min_tokens": 512, - "deprecation_date": "2027-12-05" + "source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement" }, "azure_ai/claude-opus-5": { "deprecation_date": "2027-07-08", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "supports_mid_conversation_system": true, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "input_cost_per_token": 5e-06, "output_cost_per_token": 2.5e-05, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -3569,6 +4152,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, + "supports_web_search": true, "prompt_cache_min_tokens": 512 }, "azure_ai/claude-opus-5-5": { @@ -3578,7 +4162,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -3588,6 +4171,7 @@ "cache_creation_input_token_cost": 5e-06, "cache_creation_input_token_cost_above_1hr": 8e-06, "cache_read_input_token_cost": 2e-07, + "deprecation_date": "2027-09-18", "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_assistant_prefill": false, @@ -3604,10 +4188,16 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 512 + "supports_web_search": true, + "prompt_cache_min_tokens": 512, + "source": "https://management.azure.com/subscriptions/c873328e-b572-4770-8dff-aaeb6f1f0e79/providers/Microsoft.CognitiveServices/locations/eastus2/models?api-version=2024-10-01" + }, + "azure_ai/claude-opus-latest": { + "alias_of": "azure_ai/claude-opus-5-5" }, "azure_ai/claude-opus-4-8": { "deprecation_date": "2027-09-01", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "supports_mid_conversation_system": true, "supports_adaptive_thinking": true, "input_cost_per_token": 5e-06, @@ -3615,7 +4205,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -3637,10 +4226,13 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, + "supports_web_search": true, "prompt_cache_min_tokens": 1024 }, "azure_ai/claude-sonnet-4-5": { - "deprecation_date": "2026-10-19", + "deprecation_date": "2026-11-30", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/claude-sonnet-5-5", "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, @@ -3648,8 +4240,12 @@ "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, "supports_computer_use": true, @@ -3660,10 +4256,13 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 1024 + "supports_web_search": true, + "prompt_cache_min_tokens": 1024, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule" }, "azure_ai/claude-sonnet-5": { "deprecation_date": "2027-06-30", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_1hr": 4e-06, @@ -3672,7 +4271,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "search_context_cost_per_query": { @@ -3681,6 +4279,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -3693,10 +4292,12 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, + "supports_web_search": true, "prompt_cache_min_tokens": 1024 }, "azure_ai/claude-sonnet-4-6": { "deprecation_date": "2027-02-10", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost": 3.75e-06, @@ -3706,10 +4307,14 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "output_cost_per_token": 1.5e-05, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -3720,6 +4325,7 @@ "supports_tool_choice": true, "supports_vision": true, "supports_output_config": true, + "supports_web_search": true, "prompt_cache_min_tokens": 1024, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/claude-models" }, @@ -3728,7 +4334,6 @@ "litellm_provider": "azure", "max_input_tokens": 8192, "max_output_tokens": 1024, - "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 1.2e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -3752,21 +4357,24 @@ "supports_vision": true }, "azure/container": { - "code_interpreter_cost_per_session": 0.03, + "code_interpreter_cost_per_session": 0.033, "litellm_provider": "azure", - "mode": "chat" + "mode": "chat", + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/" }, "azure_ai/gpt-oss-120b": { + "deprecation_date": "2027-09-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_pdf_input": false, "supports_response_schema": true, "supports_tool_choice": true }, @@ -3780,7 +4388,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_above_272k_tokens": 7.5e-05, @@ -3806,7 +4413,7 @@ "supports_max_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, @@ -3819,6 +4426,9 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "azure_ai/gpt-astra-latest": { + "alias_of": "azure_ai/gpt-6-astra" + }, "azure_ai/gpt-6-luna": { "cache_creation_input_token_cost": 1.25e-07, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, @@ -3829,7 +4439,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_above_272k_tokens": 7.5e-07, @@ -3868,6 +4477,9 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "azure_ai/gpt-luna-latest": { + "alias_of": "azure_ai/gpt-6-luna" + }, "azure_ai/gpt-6-sol": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, @@ -3878,7 +4490,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, @@ -3927,7 +4538,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, @@ -3953,7 +4563,58 @@ "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure_ai/gpt-sol-latest": { + "alias_of": "azure_ai/gpt-6.1-sol" + }, + "azure_ai/gpt-6.1-terra": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, + "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_above_272k_tokens": 1e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_272k_tokens": 2e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_272k_tokens": 7.5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/gpt-6-1-terra-now-generally-available-in-microsoft-foundry-build-agents-that-see/4567769", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, @@ -3966,8 +4627,12 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "azure_ai/gpt-terra-latest": { + "alias_of": "azure_ai/gpt-6.1-terra" + }, "azure_ai/gpt-5.5": { "deprecation_date": "2027-10-26", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, "cache_read_input_token_cost_priority": 1e-06, @@ -3977,9 +4642,8 @@ "input_cost_per_token_priority": 1e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, @@ -4015,12 +4679,12 @@ }, "azure_ai/gpt-chat-latest": { "cache_read_input_token_cost": 5e-07, - "deprecation_date": "2026-12-02", + "deprecation_date": "2027-05-18", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 5e-06, "litellm_provider": "azure_ai", - "max_input_tokens": 272000, + "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", @@ -4051,6 +4715,7 @@ "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-10-21", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_image_token": 8e-06, "input_cost_per_token": 5e-06, "litellm_provider": "azure_ai", @@ -4066,11 +4731,11 @@ "azure_ai/codex-mini": { "cache_read_input_token_cost": 3.75e-07, "deprecation_date": "2026-11-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 1.5e-06, "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 6e-06, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", @@ -4096,6 +4761,7 @@ }, "azure_ai/whisper": { "deprecation_date": "2026-12-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_second": 0.0001, "litellm_provider": "azure_ai", "mode": "audio_transcription", @@ -4112,9 +4778,8 @@ "input_cost_per_token_priority": 1e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, @@ -4150,6 +4815,7 @@ }, "azure_ai/gpt-5.5-2026-04-24": { "deprecation_date": "2027-10-26", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, "cache_read_input_token_cost_priority": 1e-06, @@ -4159,9 +4825,8 @@ "input_cost_per_token_priority": 1e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, @@ -4197,6 +4862,8 @@ }, "azure_ai/gpt-5.4": { "deprecation_date": "2027-09-02", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/gpt-5.5", "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_above_272k_tokens": 5e-07, "cache_read_input_token_cost_priority": 5e-07, @@ -4206,9 +4873,8 @@ "input_cost_per_token_priority": 5e-06, "input_cost_per_token_above_272k_tokens_priority": 1e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_above_272k_tokens": 2.25e-05, @@ -4245,6 +4911,8 @@ }, "azure_ai/gpt-5.4-2026-03-05": { "deprecation_date": "2027-09-02", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/gpt-5.5", "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_above_272k_tokens": 5e-07, "cache_read_input_token_cost_priority": 5e-07, @@ -4254,9 +4922,8 @@ "input_cost_per_token_priority": 5e-06, "input_cost_per_token_above_272k_tokens_priority": 1e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_above_272k_tokens": 2.25e-05, @@ -4293,6 +4960,7 @@ }, "azure_ai/gpt-5.4-pro": { "deprecation_date": "2027-09-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "cache_read_input_token_cost": 3e-06, "cache_read_input_token_cost_above_272k_tokens": 6e-06, "cache_read_input_token_cost_priority": 6e-06, @@ -4302,9 +4970,8 @@ "input_cost_per_token_priority": 6e-05, "input_cost_per_token_above_272k_tokens_priority": 0.00012, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, @@ -4339,6 +5006,7 @@ }, "azure_ai/gpt-5.4-pro-2026-03-05": { "deprecation_date": "2027-09-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "cache_read_input_token_cost": 3e-06, "cache_read_input_token_cost_above_272k_tokens": 6e-06, "cache_read_input_token_cost_priority": 6e-06, @@ -4348,9 +5016,8 @@ "input_cost_per_token_priority": 6e-05, "input_cost_per_token_above_272k_tokens_priority": 0.00012, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, @@ -4385,6 +5052,7 @@ }, "azure_ai/gpt-5.4-mini": { "deprecation_date": "2027-09-21", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_priority": 1.5e-07, "input_cost_per_token": 7.5e-07, @@ -4392,7 +5060,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "output_cost_per_token_priority": 9e-06, @@ -4425,8 +5092,12 @@ "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, + "azure_ai/gpt-mini-latest": { + "alias_of": "azure_ai/gpt-5.4-mini" + }, "azure_ai/gpt-5.4-mini-2026-03-17": { "deprecation_date": "2027-09-21", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_priority": 1.5e-07, "input_cost_per_token": 7.5e-07, @@ -4434,7 +5105,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "output_cost_per_token_priority": 9e-06, @@ -4469,6 +5139,7 @@ }, "azure_ai/gpt-5.4-nano": { "deprecation_date": "2027-09-21", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_priority": 4e-08, "input_cost_per_token": 2e-07, @@ -4476,7 +5147,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "output_cost_per_token_priority": 2.5e-06, @@ -4511,6 +5181,7 @@ }, "azure_ai/gpt-5.4-nano-2026-03-17": { "deprecation_date": "2027-09-21", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_priority": 4e-08, "input_cost_per_token": 2e-07, @@ -4518,7 +5189,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "output_cost_per_token_priority": 2.5e-06, @@ -4553,37 +5223,38 @@ }, "azure_ai/model_router": { "deprecation_date": "2027-05-20", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 1.4e-07, "output_cost_per_token": 0, "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/aoai/", "comment": "Flat cost of $0.14 per M input tokens for Azure AI Foundry Model Router infrastructure. Use pattern: azure_ai/model_router/ where deployment-name is your Azure deployment (e.g., azure-model-router)" }, "azure_ai/model-router": { "deprecation_date": "2027-05-20", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 1.4e-07, "output_cost_per_token": 0, "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/aoai/", "comment": "Catalog-name twin of azure_ai/model_router: the flat $0.14 per M input tokens is the router's own fee, the routed model is priced on top of it" }, "azure/eu/gpt-4o-2024-08-06": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.1", "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, "input_cost_per_token_batches": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, @@ -4595,8 +5266,31 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/eu/gpt-4o": { + "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.1", + "cache_creation_input_token_cost": 1.38e-06, + "cache_read_input_token_cost": 1.375e-06, + "input_cost_per_token": 2.75e-06, + "input_cost_per_token_batches": 1.375e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/eu/gpt-4o-2024-11-20": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.1", "cache_creation_input_token_cost": 1.38e-06, "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, @@ -4604,7 +5298,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, @@ -4615,17 +5308,46 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/eu/gpt-4o-mini": { + "cache_read_input_token_cost": 8.3e-08, + "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_token": 1.65e-07, + "input_cost_per_token_batches": 8.3e-08, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/eu/gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 8.3e-08, "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.65e-07, "input_cost_per_token_batches": 8.3e-08, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -4642,7 +5364,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2.2e-05, "output_cost_per_token": 2.64e-06, @@ -4653,37 +5374,18 @@ "supports_system_messages": true, "supports_tool_choice": true }, - "azure/eu/gpt-4o-realtime-preview-2024-10-01": { - "cache_creation_input_audio_token_cost": 2.2e-05, - "cache_read_input_token_cost": 2.75e-06, - "input_cost_per_audio_token": 0.00011, - "input_cost_per_token": 5.5e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "realtime", - "output_cost_per_audio_token": 0.00022, - "output_cost_per_token": 2.2e-05, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "azure/eu/gpt-4o-realtime-preview-2024-12-17": { - "cache_read_input_audio_token_cost": 2.5e-06, + "cache_read_input_audio_token_cost": 2.75e-06, "cache_read_input_token_cost": 2.75e-06, "input_cost_per_audio_token": 4.4e-05, "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", - "max_input_tokens": 128000, + "max_input_tokens": 16000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", - "output_cost_per_audio_token": 8e-05, + "output_cost_per_audio_token": 8.8e-05, "output_cost_per_token": 2.2e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_modalities": [ "text", "audio" @@ -4703,17 +5405,23 @@ "cache_read_input_token_cost": 1.375e-07, "cache_read_input_token_cost_priority": 2.75e-07, "deprecation_date": "2027-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.1", "input_cost_per_token": 1.375e-06, "input_cost_per_token_batches": 6.875e-07, "input_cost_per_token_priority": 2.75e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -4742,18 +5450,24 @@ "azure/eu/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.75e-08, "cache_read_input_token_cost_priority": 4.95e-08, - "deprecation_date": "2027-02-09", + "deprecation_date": "2027-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.4-mini", "input_cost_per_token": 2.75e-07, "input_cost_per_token_batches": 1.375e-07, "input_cost_per_token_priority": 4.95e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, "output_cost_per_token_priority": 3.96e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -4780,7 +5494,9 @@ "cache_read_input_token_cost_batches": 1.375e-08 }, "azure/eu/gpt-5.1": { - "deprecation_date": "2027-05-15", + "deprecation_date": "2027-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.2", "cache_read_input_token_cost": 1.375e-07, "cache_read_input_token_cost_batches": 6.875e-08, "cache_read_input_token_cost_priority": 2.75e-07, @@ -4788,7 +5504,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "supported_endpoints": [ @@ -4820,16 +5535,22 @@ "input_cost_per_token_priority": 2.75e-06, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.1-codex": { "deprecation_date": "2027-05-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.2-codex", "cache_read_input_token_cost": 1.375e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -4856,12 +5577,12 @@ }, "azure/eu/gpt-5.1-codex-mini": { "deprecation_date": "2027-05-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 2.75e-08, "input_cost_per_token": 2.75e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2.2e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -4889,15 +5610,21 @@ "azure/eu/gpt-5-nano-2025-08-07": { "cache_read_input_token_cost": 5.5e-09, "deprecation_date": "2027-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.4-nano", "input_cost_per_token": 5.5e-08, "input_cost_per_token_batches": 2.75e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -4923,15 +5650,34 @@ "supports_vision": true, "cache_read_input_token_cost_batches": 2.75e-09 }, + "azure/eu/o1": { + "cache_read_input_token_cost": 8.25e-06, + "deprecation_date": "2026-11-19", + "successor_model": "azure/eu/gpt-5.6-sol", + "input_cost_per_token": 1.65e-05, + "input_cost_per_token_batches": 8.25e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6.6e-05, + "output_cost_per_token_batches": 3.3e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/eu/o1-2024-12-17": { "cache_read_input_token_cost": 8.25e-06, "deprecation_date": "2026-11-19", + "successor_model": "azure/eu/gpt-5.6-sol", "input_cost_per_token": 1.65e-05, "input_cost_per_token_batches": 8.25e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6.6e-05, "output_cost_per_token_batches": 3.3e-05, @@ -4949,7 +5695,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, @@ -4959,15 +5704,35 @@ "supports_prompt_caching": true, "supports_vision": false }, + "azure/eu/o3-mini": { + "cache_read_input_token_cost": 6.05e-07, + "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.6-terra", + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, "azure/eu/o3-mini-2025-01-31": { "cache_read_input_token_cost": 6.05e-07, "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.6-terra", "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, @@ -4980,12 +5745,12 @@ "azure/global-standard/gpt-4o-2024-08-06": { "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 2.5e-06, "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -5000,12 +5765,12 @@ "azure/global-standard/gpt-4o-2024-11-20": { "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 2.5e-06, "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -5018,13 +5783,18 @@ }, "azure/global-standard/gpt-4o-mini": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.5e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -5033,13 +5803,14 @@ }, "azure/global/gpt-4o-2024-08-06": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/global/gpt-5.1", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -5053,13 +5824,14 @@ }, "azure/global/gpt-4o-2024-11-20": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/global/gpt-5.1", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -5072,7 +5844,8 @@ "supports_vision": true }, "azure/global/gpt-5.1": { - "deprecation_date": "2027-05-15", + "deprecation_date": "2027-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_batches": 6.25e-08, "cache_read_input_token_cost_priority": 2.5e-07, @@ -5080,7 +5853,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "supported_endpoints": [ @@ -5112,16 +5884,21 @@ "input_cost_per_token_priority": 2.5e-06, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/global/gpt-5.1-codex": { "deprecation_date": "2027-05-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -5148,12 +5925,12 @@ }, "azure/global/gpt-5.1-codex-mini": { "deprecation_date": "2027-05-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 2.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -5183,184 +5960,110 @@ "litellm_provider": "azure", "max_input_tokens": 4097, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-06, "supports_function_calling": true, "supports_tool_choice": true }, "azure/gpt-3.5-turbo-instruct-0914": { - "input_cost_per_token": 1.5e-06, + "input_cost_per_token": 1.65e-06, "litellm_provider": "azure_text", "max_input_tokens": 4097, - "max_tokens": 4097, + "max_output_tokens": 4097, "mode": "completion", - "output_cost_per_token": 2e-06 + "output_cost_per_token": 2.2e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/gpt-35-turbo": { "input_cost_per_token": 5e-07, "litellm_provider": "azure", "max_input_tokens": 4097, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-06, "supports_function_calling": true, "supports_tool_choice": true }, - "azure/gpt-35-turbo-16k": { - "deprecation_date": "2025-04-30", - "input_cost_per_token": 3e-06, - "litellm_provider": "azure", - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 4e-06, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models", - "supports_tool_choice": true - }, - "azure/gpt-35-turbo-16k-0613": { - "deprecation_date": "2025-04-30", - "input_cost_per_token": 3e-06, - "litellm_provider": "azure", - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 4e-06, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models", - "supports_function_calling": true, - "supports_tool_choice": true - }, "azure/gpt-35-turbo-instruct": { - "input_cost_per_token": 1.5e-06, + "input_cost_per_token": 1.65e-06, "litellm_provider": "azure_text", "max_input_tokens": 4097, - "max_tokens": 4097, + "max_output_tokens": 4097, "mode": "completion", - "output_cost_per_token": 2e-06 + "output_cost_per_token": 2.2e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/gpt-35-turbo-instruct-0914": { - "input_cost_per_token": 1.5e-06, + "input_cost_per_token": 1.65e-06, "litellm_provider": "azure_text", "max_input_tokens": 4097, - "max_tokens": 4097, + "max_output_tokens": 4097, "mode": "completion", - "output_cost_per_token": 2e-06 - }, - "azure/gpt-4": { - "deprecation_date": "2025-06-06", - "input_cost_per_token": 3e-05, - "litellm_provider": "azure", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 6e-05, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", - "supports_function_calling": true, - "supports_tool_choice": true + "output_cost_per_token": 2.2e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/gpt-4-0125-preview": { "input_cost_per_token": 1e-05, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true }, - "azure/gpt-4-0613": { - "deprecation_date": "2025-06-06", - "input_cost_per_token": 3e-05, - "litellm_provider": "azure", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 6e-05, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models", - "supports_function_calling": true, - "supports_tool_choice": true - }, "azure/gpt-4-1106-preview": { "input_cost_per_token": 1e-05, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true }, - "azure/gpt-4-32k": { - "deprecation_date": "2025-06-06", - "input_cost_per_token": 6e-05, - "litellm_provider": "azure", - "max_input_tokens": 32768, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.00012, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models", - "supports_tool_choice": true - }, - "azure/gpt-4-32k-0613": { - "deprecation_date": "2025-06-06", - "input_cost_per_token": 6e-05, - "litellm_provider": "azure", - "max_input_tokens": 32768, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.00012, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models", - "supports_tool_choice": true - }, "azure/gpt-4-turbo": { - "input_cost_per_token": 1e-05, + "input_cost_per_token": 1.1e-05, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 3e-05, + "output_cost_per_token": 3.3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true }, "azure/gpt-4-turbo-2024-04-09": { - "input_cost_per_token": 1e-05, + "input_cost_per_token": 1.1e-05, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 3e-05, + "output_cost_per_token": 3.3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-4-turbo-vision-preview": { - "input_cost_per_token": 1e-05, + "input_cost_per_token": 1.1e-05, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 3e-05, + "output_cost_per_token": 3.3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-4.1": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.1", "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_priority": 8.75e-07, "input_cost_per_token": 2e-06, @@ -5369,11 +6072,15 @@ "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, "output_cost_per_token_priority": 1.4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -5399,6 +6106,8 @@ }, "azure/gpt-4.1-2025-04-14": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.1", "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_priority": 8.75e-07, "input_cost_per_token": 2e-06, @@ -5407,11 +6116,15 @@ "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, "output_cost_per_token_priority": 1.4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -5437,6 +6150,8 @@ }, "azure/gpt-4.1-mini": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.4-mini", "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_priority": 1.75e-07, "input_cost_per_token": 4e-07, @@ -5445,11 +6160,15 @@ "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, "output_cost_per_token_priority": 2.8e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -5475,6 +6194,8 @@ }, "azure/gpt-4.1-mini-2025-04-14": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.4-mini", "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_priority": 1.75e-07, "input_cost_per_token": 4e-07, @@ -5483,11 +6204,15 @@ "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, "output_cost_per_token_priority": 2.8e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -5513,13 +6238,14 @@ }, "azure/gpt-4.1-nano": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.4-nano", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, @@ -5547,13 +6273,14 @@ }, "azure/gpt-4.1-nano-2025-04-14": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.4-nano", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, @@ -5579,37 +6306,20 @@ "supports_tool_choice": true, "supports_vision": true }, - "azure/gpt-4.5-preview": { - "cache_read_input_token_cost": 3.75e-05, - "deprecation_date": "2025-07-14", - "input_cost_per_token": 7.5e-05, - "input_cost_per_token_batches": 3.75e-05, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 0.00015, - "output_cost_per_token_batches": 7.5e-05, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "azure/gpt-4o": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.1", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -5618,13 +6328,14 @@ "supports_vision": true }, "azure/gpt-4o-2024-05-13": { - "deprecation_date": "2026-12-09", + "deprecation_date": "2027-01-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.1", "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, @@ -5637,13 +6348,14 @@ }, "azure/gpt-4o-2024-08-06": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.1", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -5657,13 +6369,14 @@ }, "azure/gpt-4o-2024-11-20": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.1", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -5677,12 +6390,12 @@ }, "azure/gpt-audio": { "deprecation_date": "2027-03-02", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 1e-05, @@ -5697,6 +6410,7 @@ "text", "audio" ], + "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, @@ -5710,12 +6424,12 @@ }, "azure/gpt-audio-2025-08-28": { "deprecation_date": "2027-03-02", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 1e-05, @@ -5730,6 +6444,7 @@ "text", "audio" ], + "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, @@ -5742,14 +6457,14 @@ }, "azure/gpt-audio-1.5": { "deprecation_date": "2027-08-24", - "input_cost_per_audio_token": 4e-05, + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_audio_token": 3.2e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", - "output_cost_per_audio_token": 8e-05, + "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, "supported_endpoints": [ "/v1/chat/completions" @@ -5762,6 +6477,7 @@ "text", "audio" ], + "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, @@ -5771,19 +6487,20 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/gpt-audio-1.5-2026-02-23": { "deprecation_date": "2027-08-24", - "input_cost_per_audio_token": 4e-05, + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_audio_token": 3.2e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", - "output_cost_per_audio_token": 8e-05, + "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/chat/completions" ], @@ -5795,6 +6512,8 @@ "text", "audio" ], + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, @@ -5807,12 +6526,12 @@ }, "azure/gpt-audio-mini": { "deprecation_date": "2027-06-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 6e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -5827,6 +6546,7 @@ "text", "audio" ], + "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, @@ -5839,12 +6559,12 @@ }, "azure/gpt-audio-mini-2025-10-06": { "deprecation_date": "2027-04-06", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 6e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -5859,6 +6579,8 @@ "text", "audio" ], + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, @@ -5875,7 +6597,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 1e-05, @@ -5890,6 +6611,7 @@ "text", "audio" ], + "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, @@ -5902,14 +6624,22 @@ }, "azure/gpt-4o-mini": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 7.5e-08, "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -5920,15 +6650,20 @@ "azure/gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 7.5e-08, "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.5e-07, "input_cost_per_token_batches": 7.5e-08, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_batches": 3e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -5938,15 +6673,15 @@ "supports_vision": true }, "azure/gpt-4o-mini-audio-preview-2024-12-17": { - "input_cost_per_audio_token": 4e-05, - "input_cost_per_token": 2.5e-06, + "input_cost_per_audio_token": 1e-05, + "input_cost_per_token": 1.5e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", - "output_cost_per_audio_token": 8e-05, - "output_cost_per_token": 1e-05, + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 6e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/chat/completions" ], @@ -5958,6 +6693,7 @@ "text", "audio" ], + "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, @@ -5976,7 +6712,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -5988,20 +6723,24 @@ "supports_tool_choice": true }, "azure/gpt-realtime": { + "cache_read_input_image_token_cost": 5e-07, "cache_creation_input_audio_token_cost": 4e-06, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, "deprecation_date": "2027-03-02", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, + "provider_specific_entry": { + "realtime_ga_only": 1 + }, "supported_endpoints": [ "/v1/realtime" ], @@ -6020,23 +6759,28 @@ "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/" }, "azure/gpt-realtime-2025-08-28": { + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "cache_read_input_image_token_cost": 5e-07, "cache_creation_input_audio_token_cost": 4e-06, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, "deprecation_date": "2027-03-02", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, + "provider_specific_entry": { + "realtime_ga_only": 1 + }, "supported_endpoints": [ "/v1/realtime" ], @@ -6057,20 +6801,25 @@ "supports_tool_choice": true }, "azure/gpt-realtime-1.5": { + "cache_read_input_image_token_cost": 5e-07, "cache_creation_input_audio_token_cost": 4e-06, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, "deprecation_date": "2027-08-24", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-realtime-2.1-2026-07-07", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, + "provider_specific_entry": { + "realtime_ga_only": 1 + }, "supported_endpoints": [ "/v1/realtime" ], @@ -6089,23 +6838,29 @@ "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/" }, "azure/gpt-realtime-1.5-2026-02-23": { + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "cache_read_input_image_token_cost": 5e-07, "cache_creation_input_audio_token_cost": 4e-06, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, "deprecation_date": "2027-08-24", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-realtime-2.1-2026-07-07", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, + "provider_specific_entry": { + "realtime_ga_only": 1 + }, "supported_endpoints": [ "/v1/realtime" ], @@ -6128,19 +6883,23 @@ "azure/gpt-realtime-2.1": { "cache_creation_input_audio_token_cost": 4e-07, "cache_read_input_audio_token_cost": 4e-07, + "cache_read_input_image_token_cost": 5e-07, "cache_read_input_token_cost": 4e-07, - "deprecation_date": "2027-07-31", + "deprecation_date": "2027-06-25", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", + "provider_specific_entry": { + "realtime_ga_only": 1 + }, "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 2.4e-05, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "supported_endpoints": [ "/v1/realtime" ], @@ -6157,25 +6916,31 @@ "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true }, "azure/gpt-realtime-2.1-mini": { "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_audio_token_cost": 3e-07, + "cache_read_input_image_token_cost": 8e-08, "cache_read_input_token_cost": 6e-08, - "deprecation_date": "2027-07-31", + "deprecation_date": "2027-06-25", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 1e-05, "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", + "provider_specific_entry": { + "realtime_ga_only": 1 + }, "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "supported_endpoints": [ "/v1/realtime" ], @@ -6192,24 +6957,31 @@ "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true }, "azure/gpt-realtime-mini": { + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "cache_read_input_image_token_cost": 8e-08, "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 6e-08, "deprecation_date": "2027-06-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 1e-05, "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, + "provider_specific_entry": { + "realtime_ga_only": 1 + }, "supported_endpoints": [ "/v1/realtime" ], @@ -6234,16 +7006,19 @@ "cache_read_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 6e-08, "deprecation_date": "2027-04-06", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 1e-05, "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, + "provider_specific_entry": { + "realtime_ga_only": 1 + }, "supported_endpoints": [ "/v1/realtime" ], @@ -6265,6 +7040,7 @@ }, "azure/gpt-4o-mini-transcribe": { "deprecation_date": "2027-06-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", @@ -6278,6 +7054,7 @@ }, "azure/gpt-4o-mini-tts": { "deprecation_date": "2027-06-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 6e-07, "litellm_provider": "azure", "mode": "audio_speech", @@ -6295,36 +7072,18 @@ "audio" ] }, - "azure/gpt-4o-realtime-preview-2024-10-01": { - "cache_creation_input_audio_token_cost": 2e-05, - "cache_read_input_token_cost": 2.5e-06, - "input_cost_per_audio_token": 0.0001, - "input_cost_per_token": 5e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "realtime", - "output_cost_per_audio_token": 0.0002, - "output_cost_per_token": 2e-05, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "azure/gpt-4o-realtime-preview-2024-12-17": { + "cache_read_input_audio_token_cost": 2.5e-06, "cache_read_input_token_cost": 2.5e-06, "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 5e-06, "litellm_provider": "azure", - "max_input_tokens": 128000, + "max_input_tokens": 16000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 2e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_modalities": [ "text", "audio" @@ -6341,27 +7100,31 @@ "supports_tool_choice": true }, "azure/gpt-4o-transcribe": { - "deprecation_date": "2026-12-31", - "input_cost_per_audio_token": 2.5e-06, + "deprecation_date": "2026-10-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_audio_token": 6e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 16000, "max_output_tokens": 2000, "mode": "audio_transcription", "output_cost_per_token": 1e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "azure/gpt-4o-transcribe-diarize": { "deprecation_date": "2027-04-15", - "input_cost_per_audio_token": 2.5e-06, + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_audio_token": 6e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 16000, "max_output_tokens": 2000, "mode": "audio_transcription", "output_cost_per_token": 1e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/audio/transcriptions" ] @@ -6370,7 +7133,12 @@ "deprecation_date": "2027-05-06", "input_cost_per_second": 0.0002833333333333333, "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, "mode": "audio_transcription", + "provider_specific_entry": { + "realtime_ga_only": 1 + }, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/gpt-realtime-whisper", "supported_endpoints": [ "/v1/realtime", @@ -6387,13 +7155,14 @@ "azure/gpt-5.1-2025-11-13": { "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_priority": 2.5e-07, - "deprecation_date": "2027-05-15", + "deprecation_date": "2027-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.2", "input_cost_per_token": 1.25e-06, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_priority": 2e-05, @@ -6423,6 +7192,11 @@ "default_reasoning_effort": "none", "input_cost_per_token_batches": 6.25e-07, "output_cost_per_token_batches": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_minimal_reasoning_effort": true, "cache_read_input_token_cost_batches": 6.25e-08 @@ -6431,12 +7205,13 @@ "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_priority": 2.5e-07, "deprecation_date": "2027-05-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.2-codex", "input_cost_per_token": 1.25e-06, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "output_cost_per_token_priority": 2e-05, @@ -6466,12 +7241,12 @@ "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_priority": 4.5e-08, "deprecation_date": "2027-05-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 2.5e-07, "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, "output_cost_per_token_priority": 3.6e-06, @@ -6499,6 +7274,8 @@ }, "azure/gpt-5": { "deprecation_date": "2027-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.1", "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_batches": 6.25e-08, "cache_read_input_token_cost_priority": 2.5e-07, @@ -6508,11 +7285,15 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -6541,17 +7322,23 @@ "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_priority": 2.5e-07, "deprecation_date": "2027-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.1", "input_cost_per_token": 1.25e-06, "input_cost_per_token_batches": 6.25e-07, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -6580,11 +7367,12 @@ "azure/gpt-5-codex": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2027-03-17", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.1-codex", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -6610,7 +7398,9 @@ "supports_vision": true }, "azure/gpt-5-mini": { - "deprecation_date": "2027-02-09", + "deprecation_date": "2027-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.4-mini", "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, @@ -6620,11 +7410,15 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, "output_cost_per_token_batches": 1e-06, "output_cost_per_token_priority": 3.6e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -6652,18 +7446,24 @@ "azure/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_priority": 4.5e-08, - "deprecation_date": "2027-02-09", + "deprecation_date": "2027-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.4-mini", "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, "output_cost_per_token_batches": 1e-06, "output_cost_per_token_priority": 3.6e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -6691,6 +7491,8 @@ }, "azure/gpt-5-nano": { "deprecation_date": "2027-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.4-nano", "cache_read_input_token_cost": 5e-09, "cache_read_input_token_cost_batches": 2.5e-09, "input_cost_per_token": 5e-08, @@ -6698,10 +7500,14 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -6729,15 +7535,21 @@ "azure/gpt-5-nano-2025-08-07": { "cache_read_input_token_cost": 5e-09, "deprecation_date": "2027-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.4-nano", "input_cost_per_token": 5e-08, "input_cost_per_token_batches": 2.5e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -6765,15 +7577,21 @@ }, "azure/gpt-5-pro": { "deprecation_date": "2027-04-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.2-pro", "input_cost_per_token": 1.5e-05, "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00012, "output_cost_per_token_batches": 6e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" @@ -6796,7 +7614,9 @@ "supports_vision": true }, "azure/gpt-5.1": { - "deprecation_date": "2027-05-15", + "deprecation_date": "2027-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.2", "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_batches": 6.25e-08, "cache_read_input_token_cost_priority": 2.5e-07, @@ -6804,7 +7624,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "supported_endpoints": [ @@ -6836,16 +7655,22 @@ "input_cost_per_token_priority": 2.5e-06, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5-chat": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2026-06-29", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-chat-latest", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -6866,11 +7691,12 @@ "azure/gpt-5.1-chat": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2026-06-29", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-chat-latest", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -6888,11 +7714,12 @@ "azure/gpt-5.2-chat": { "cache_read_input_token_cost": 1.75e-07, "deprecation_date": "2026-06-29", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-chat-latest", "input_cost_per_token": 1.75e-06, "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.4e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -6909,11 +7736,12 @@ "azure/gpt-5.3-chat": { "cache_read_input_token_cost": 1.75e-07, "deprecation_date": "2026-06-29", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-chat-latest", "input_cost_per_token": 1.75e-06, "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.4e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -6930,11 +7758,12 @@ "azure/us/gpt-5.1-chat": { "cache_read_input_token_cost": 1.375e-07, "deprecation_date": "2026-06-29", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-chat-latest", "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -6952,11 +7781,12 @@ "azure/us/gpt-5.2-chat": { "cache_read_input_token_cost": 1.925e-07, "deprecation_date": "2026-06-29", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-chat-latest", "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.54e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -6973,11 +7803,12 @@ "azure/us/gpt-5.3-chat": { "cache_read_input_token_cost": 1.925e-07, "deprecation_date": "2026-06-29", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-chat-latest", "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.54e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -6994,11 +7825,12 @@ "azure/eu/gpt-5.1-chat": { "cache_read_input_token_cost": 1.375e-07, "deprecation_date": "2026-06-29", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-chat-latest", "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7016,11 +7848,12 @@ "azure/eu/gpt-5.2-chat": { "cache_read_input_token_cost": 1.925e-07, "deprecation_date": "2026-06-29", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-chat-latest", "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.54e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7037,11 +7870,12 @@ "azure/eu/gpt-5.3-chat": { "cache_read_input_token_cost": 1.925e-07, "deprecation_date": "2026-06-29", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-chat-latest", "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.54e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7055,46 +7889,15 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "azure/us/o1-preview": { - "cache_read_input_token_cost": 8.25e-06, - "deprecation_date": "2025-07-28", - "input_cost_per_token": 1.65e-05, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 6.6e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supports_prompt_caching": true - }, - "azure/eu/o1-preview": { - "cache_read_input_token_cost": 8.25e-06, - "deprecation_date": "2025-07-28", - "input_cost_per_token": 1.65e-05, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 6.6e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supports_prompt_caching": true - }, "azure/gpt-5.1-codex": { "deprecation_date": "2027-05-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.2-codex", "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7122,11 +7925,11 @@ "azure/gpt-5.1-codex-max": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2027-05-18", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7153,12 +7956,12 @@ }, "azure/gpt-5.1-codex-mini": { "deprecation_date": "2027-05-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 2.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7185,6 +7988,8 @@ }, "azure/gpt-5.2": { "deprecation_date": "2027-06-08", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.4", "cache_read_input_token_cost": 1.75e-07, "cache_read_input_token_cost_batches": 8.75e-08, "cache_read_input_token_cost_priority": 3.5e-07, @@ -7194,11 +7999,15 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_batches": 7e-06, "output_cost_per_token_priority": 2.8e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -7228,17 +8037,23 @@ "cache_read_input_token_cost": 1.75e-07, "cache_read_input_token_cost_priority": 3.5e-07, "deprecation_date": "2027-06-08", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.4", "input_cost_per_token": 1.75e-06, "input_cost_per_token_batches": 8.75e-07, "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_batches": 7e-06, "output_cost_per_token_priority": 2.8e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -7268,11 +8083,12 @@ "azure/gpt-5.2-codex": { "cache_read_input_token_cost": 1.75e-07, "deprecation_date": "2027-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.3-codex", "input_cost_per_token": 1.75e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7301,15 +8117,20 @@ "cache_read_input_token_cost": 1.75e-07, "cache_read_input_token_cost_priority": 3.5e-07, "deprecation_date": "2027-08-24", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.75e-06, "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" @@ -7338,14 +8159,13 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, "output_cost_per_token_batches": 8.4e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -7377,14 +8197,13 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, "output_cost_per_token_batches": 8.4e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -7412,6 +8231,8 @@ }, "azure/gpt-5.4": { "deprecation_date": "2027-09-02", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.5", "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_above_272k_tokens": 5e-07, "cache_read_input_token_cost_above_272k_tokens_batches": 2.5e-07, @@ -7424,9 +8245,8 @@ "input_cost_per_token_priority": 5e-06, "input_cost_per_token_above_272k_tokens_priority": 1e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_above_272k_tokens": 2.25e-05, @@ -7470,6 +8290,8 @@ }, "azure/us/gpt-5.4": { "deprecation_date": "2027-09-02", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.5", "cache_read_input_token_cost": 2.75e-07, "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-07, @@ -7480,9 +8302,8 @@ "output_cost_per_token": 1.65e-05, "output_cost_per_token_priority": 3.3e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", @@ -7520,6 +8341,8 @@ }, "azure/eu/gpt-5.4": { "deprecation_date": "2027-09-02", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.5", "cache_read_input_token_cost": 2.75e-07, "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-07, @@ -7530,9 +8353,8 @@ "output_cost_per_token": 1.65e-05, "output_cost_per_token_priority": 3.3e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", @@ -7575,14 +8397,15 @@ "cache_read_input_token_cost_priority": 5e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06, "deprecation_date": "2027-09-02", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.5", "input_cost_per_token": 2.5e-06, "input_cost_per_token_above_272k_tokens": 5e-06, "input_cost_per_token_priority": 5e-06, "input_cost_per_token_above_272k_tokens_priority": 1e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_above_272k_tokens": 2.25e-05, @@ -7631,14 +8454,15 @@ "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost_priority": 5.5e-07, "deprecation_date": "2027-09-02", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.5", "input_cost_per_token": 2.75e-06, "input_cost_per_token_priority": 5.5e-06, "output_cost_per_token": 1.65e-05, "output_cost_per_token_priority": 3.3e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", @@ -7681,14 +8505,15 @@ "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost_priority": 5.5e-07, "deprecation_date": "2027-09-02", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.5", "input_cost_per_token": 2.75e-06, "input_cost_per_token_priority": 5.5e-06, "output_cost_per_token": 1.65e-05, "output_cost_per_token_priority": 3.3e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", @@ -7728,6 +8553,8 @@ }, "azure/gpt-5.4-pro": { "deprecation_date": "2027-09-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.5-pro", "cache_read_input_token_cost": 3e-06, "cache_read_input_token_cost_above_272k_tokens": 6e-06, "input_cost_per_token": 3e-05, @@ -7737,9 +8564,8 @@ "input_cost_per_token_batches": 1.5e-05, "input_cost_per_token_flex": 1.5e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, @@ -7748,9 +8574,9 @@ "output_cost_per_token_batches": 9e-05, "output_cost_per_token_flex": 9e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -7780,15 +8606,16 @@ "cache_read_input_token_cost": 3e-06, "cache_read_input_token_cost_above_272k_tokens": 6e-06, "deprecation_date": "2027-09-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.5-pro", "input_cost_per_token": 3e-05, "input_cost_per_token_above_272k_tokens": 6e-05, "input_cost_per_token_above_272k_tokens_flex": 3e-05, "input_cost_per_token_batches": 1.5e-05, "input_cost_per_token_flex": 1.5e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, @@ -7796,9 +8623,9 @@ "output_cost_per_token_batches": 9e-05, "output_cost_per_token_flex": 9e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -7842,16 +8669,15 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, "output_cost_per_token_priority": 4e-05, "output_cost_per_token_above_272k_tokens_priority": 6e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -7894,6 +8720,8 @@ "cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06, "cache_read_input_token_cost_flex": 2e-07, "deprecation_date": "2028-01-11", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-6-sol", "input_cost_per_token": 4e-06, "input_cost_per_token_above_272k_tokens": 8e-06, "input_cost_per_token_above_272k_tokens_flex": 4e-06, @@ -7903,7 +8731,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, @@ -7912,9 +8739,9 @@ "output_cost_per_token_above_272k_tokens_priority": 6e-05, "output_cost_per_token_flex": 1e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -7958,6 +8785,8 @@ "cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06, "cache_read_input_token_cost_flex": 2e-07, "deprecation_date": "2028-01-11", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-6-sol", "input_cost_per_token": 4e-06, "input_cost_per_token_above_272k_tokens": 8e-06, "input_cost_per_token_above_272k_tokens_flex": 4e-06, @@ -7967,7 +8796,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, @@ -7976,9 +8804,9 @@ "output_cost_per_token_above_272k_tokens_priority": 6e-05, "output_cost_per_token_flex": 1e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -8022,6 +8850,8 @@ "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, "cache_read_input_token_cost_flex": 1e-07, "deprecation_date": "2028-01-11", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-6.1-terra", "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, "input_cost_per_token_above_272k_tokens_flex": 2e-06, @@ -8031,7 +8861,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, @@ -8040,9 +8869,9 @@ "output_cost_per_token_above_272k_tokens_priority": 3.6e-05, "output_cost_per_token_flex": 6e-06, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -8086,6 +8915,8 @@ "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, "cache_read_input_token_cost_flex": 1e-07, "deprecation_date": "2028-01-11", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-6.1-terra", "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, "input_cost_per_token_above_272k_tokens_flex": 2e-06, @@ -8095,7 +8926,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, @@ -8104,9 +8934,9 @@ "output_cost_per_token_above_272k_tokens_priority": 3.6e-05, "output_cost_per_token_flex": 6e-06, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -8150,6 +8980,8 @@ "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08, "cache_read_input_token_cost_flex": 1e-08, "deprecation_date": "2028-01-11", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-6-luna", "input_cost_per_token": 2e-07, "input_cost_per_token_above_272k_tokens": 4e-07, "input_cost_per_token_above_272k_tokens_flex": 2e-07, @@ -8159,7 +8991,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_above_272k_tokens": 1.8e-06, @@ -8168,9 +8999,9 @@ "output_cost_per_token_above_272k_tokens_priority": 3.6e-06, "output_cost_per_token_flex": 6e-07, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -8214,6 +9045,8 @@ "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08, "cache_read_input_token_cost_flex": 1e-08, "deprecation_date": "2028-01-11", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-6-luna", "input_cost_per_token": 2e-07, "input_cost_per_token_above_272k_tokens": 4e-07, "input_cost_per_token_above_272k_tokens_flex": 2e-07, @@ -8223,7 +9056,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_above_272k_tokens": 1.8e-06, @@ -8232,9 +9064,9 @@ "output_cost_per_token_above_272k_tokens_priority": 3.6e-06, "output_cost_per_token_flex": 6e-07, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -8275,16 +9107,11 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_above_272k_tokens": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "search_context_cost_per_query": {"search_context_size_high":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -8301,7 +9128,7 @@ "supports_max_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -8311,7 +9138,18 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-05, + "cache_read_input_token_cost_above_272k_tokens_flex": 1e-06, + "input_cost_per_token_above_272k_tokens_flex": 1e-05, + "output_cost_per_token_above_272k_tokens_flex": 3.75e-05, + "input_cost_per_token_flex": 5e-06, + "output_cost_per_token_flex": 2.5e-05, + "cache_read_input_token_cost_flex": 5e-07, + "cache_creation_input_token_cost_flex": 6.25e-06 + }, + "azure/gpt-astra-latest": { + "alias_of": "azure/gpt-6-astra" }, "azure/gpt-6-astra-2026-09-03": { "cache_creation_input_token_cost": 1.25e-05, @@ -8324,16 +9162,11 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_above_272k_tokens": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "search_context_cost_per_query": {"search_context_size_high":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -8350,7 +9183,7 @@ "supports_max_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -8360,7 +9193,15 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-05, + "cache_read_input_token_cost_above_272k_tokens_flex": 1e-06, + "input_cost_per_token_above_272k_tokens_flex": 1e-05, + "output_cost_per_token_above_272k_tokens_flex": 3.75e-05, + "input_cost_per_token_flex": 5e-06, + "output_cost_per_token_flex": 2.5e-05, + "cache_read_input_token_cost_flex": 5e-07, + "cache_creation_input_token_cost_flex": 6.25e-06 }, "azure/gpt-6-luna": { "cache_creation_input_token_cost": 1.25e-07, @@ -8373,16 +9214,11 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_above_272k_tokens": 7.5e-07, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", + "search_context_cost_per_query": {"search_context_size_high":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -8409,7 +9245,18 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-07, + "cache_creation_input_token_cost_flex": 6.25e-08, + "cache_read_input_token_cost_above_272k_tokens_flex": 1e-08, + "cache_read_input_token_cost_flex": 5e-09, + "input_cost_per_token_above_272k_tokens_flex": 1e-07, + "input_cost_per_token_flex": 5e-08, + "output_cost_per_token_above_272k_tokens_flex": 3.75e-07, + "output_cost_per_token_flex": 2.5e-07 + }, + "azure/gpt-luna-latest": { + "alias_of": "azure/gpt-6-luna" }, "azure/gpt-6-luna-2026-09-22": { "cache_creation_input_token_cost": 1.25e-07, @@ -8422,16 +9269,11 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_above_272k_tokens": 7.5e-07, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", + "search_context_cost_per_query": {"search_context_size_high":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -8458,28 +9300,39 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-07, + "cache_creation_input_token_cost_flex": 6.25e-08, + "cache_read_input_token_cost_above_272k_tokens_flex": 1e-08, + "cache_read_input_token_cost_flex": 5e-09, + "input_cost_per_token_above_272k_tokens_flex": 1e-07, + "input_cost_per_token_flex": 5e-08, + "output_cost_per_token_above_272k_tokens_flex": 3.75e-07, + "output_cost_per_token_flex": 2.5e-07 }, "azure/gpt-6-sol": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_priority": 5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, + "cache_read_input_token_cost_priority": 4e-07, "deprecation_date": "2028-03-11", "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_priority": 8e-06, + "input_cost_per_token_priority": 4e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, + "output_cost_per_token_above_272k_tokens_priority": 3e-05, + "output_cost_per_token_priority": 2e-05, + "search_context_cost_per_query": {"search_context_size_high":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", @@ -8507,28 +9360,39 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_flex": 5e-06, + "cache_read_input_token_cost_flex": 1e-07, + "cache_creation_input_token_cost_flex": 1.25e-06, + "input_cost_per_token_above_272k_tokens_flex": 2e-06, + "output_cost_per_token_above_272k_tokens_flex": 7.5e-06, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-07, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06 }, "azure/gpt-6-sol-2026-09-22": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_priority": 5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, + "cache_read_input_token_cost_priority": 4e-07, "deprecation_date": "2028-03-11", "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_priority": 8e-06, + "input_cost_per_token_priority": 4e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, + "output_cost_per_token_above_272k_tokens_priority": 3e-05, + "output_cost_per_token_priority": 2e-05, + "search_context_cost_per_query": {"search_context_size_high":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", @@ -8556,28 +9420,35 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_flex": 5e-06, + "cache_read_input_token_cost_flex": 1e-07, + "cache_creation_input_token_cost_flex": 1.25e-06, + "input_cost_per_token_above_272k_tokens_flex": 2e-06, + "output_cost_per_token_above_272k_tokens_flex": 7.5e-06, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-07, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06 }, - "azure/gpt-6.1-sol": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, + "azure/gpt-6.1-terra": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, + "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_above_272k_tokens": 1e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_272k_tokens": 2e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_272k_tokens": 7.5e-06, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, - "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/gpt-6-1-terra-now-generally-available-in-microsoft-foundry-build-agents-that-see/4567769", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -8594,7 +9465,7 @@ "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -8606,25 +9477,24 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, - "azure/gpt-6.1-sol-2026-09-29": { + "azure/gpt-terra-latest": { + "alias_of": "azure/gpt-6.1-terra" + }, + "azure/gpt-6.1-sol": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "deprecation_date": "2028-03-11", "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, + "search_context_cost_per_query": {"search_context_size_high":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ "/v1/chat/completions", @@ -8642,7 +9512,7 @@ "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -8652,22 +9522,35 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_flex": 5e-06, + "cache_read_input_token_cost_flex": 5e-08, + "cache_creation_input_token_cost_flex": 1.25e-06, + "input_cost_per_token_above_272k_tokens_flex": 2e-06, + "output_cost_per_token_above_272k_tokens_flex": 7.5e-06, + "cache_read_input_token_cost_above_272k_tokens_flex": 1e-07, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06 }, - "azure/gpt-chat-latest": { - "cache_read_input_token_cost": 5e-07, - "deprecation_date": "2026-12-02", - "input_cost_per_token": 5e-06, + "azure/gpt-sol-latest": { + "alias_of": "azure/gpt-6.1-sol" + }, + "azure/gpt-6.1-sol-2026-09-29": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "deprecation_date": "2028-03-11", + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, "litellm_provider": "azure", - "max_input_tokens": 272000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3e-05, - "reasoning_effort_levels": [ - "medium" - ], - "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "search_context_cost_per_query": {"search_context_size_high":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -8679,8 +9562,12 @@ "supported_output_modalities": [ "text" ], + "supports_computer_use": true, "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -8689,22 +9576,36 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true, + "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_flex": 5e-06, + "cache_read_input_token_cost_flex": 5e-08, + "cache_creation_input_token_cost_flex": 1.25e-06, + "input_cost_per_token_above_272k_tokens_flex": 2e-06, + "output_cost_per_token_above_272k_tokens_flex": 7.5e-06, + "cache_read_input_token_cost_above_272k_tokens_flex": 1e-07, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06 }, - "azure/chat-latest": { - "cache_read_input_token_cost": 5e-07, - "deprecation_date": "2026-12-02", - "input_cost_per_token": 5e-06, + "azure/us/gpt-6.1-terra": { + "cache_creation_input_token_cost": 1.375e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.75e-06, + "cache_read_input_token_cost": 5.5e-08, + "cache_read_input_token_cost_above_272k_tokens": 1.1e-07, + "input_cost_per_token": 1.1e-06, + "input_cost_per_token_above_272k_tokens": 2.2e-06, "litellm_provider": "azure", - "max_input_tokens": 272000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3e-05, - "reasoning_effort_levels": [ - "medium" - ], - "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "output_cost_per_token": 5.5e-06, + "output_cost_per_token_above_272k_tokens": 8.25e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/gpt-6-1-terra-now-generally-available-in-microsoft-foundry-build-agents-that-see/4567769", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -8716,8 +9617,12 @@ "supported_output_modalities": [ "text" ], + "supports_computer_use": true, "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -8726,38 +9631,31 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true }, - "azure/us/gpt-5.6": { - "cache_creation_input_token_cost": 5.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, - "cache_creation_input_token_cost_above_272k_tokens_priority": 2.2e-05, - "cache_creation_input_token_cost_priority": 1.1e-05, - "cache_read_input_token_cost": 4.4e-07, - "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, - "cache_read_input_token_cost_above_272k_tokens_priority": 1.76e-06, - "cache_read_input_token_cost_priority": 8.8e-07, - "input_cost_per_token": 4.4e-06, - "input_cost_per_token_above_272k_tokens": 8.8e-06, - "input_cost_per_token_above_272k_tokens_priority": 1.76e-05, - "input_cost_per_token_priority": 8.8e-06, + "azure/us/gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, + "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2.2e-07, + "deprecation_date": "2028-03-11", + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_above_272k_tokens": 4.4e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2.2e-05, - "output_cost_per_token_above_272k_tokens": 3.3e-05, - "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, - "output_cost_per_token_priority": 4.4e-05, + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_above_272k_tokens": 1.65e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ "/v1/chat/completions", - "/v1/batch", "/v1/responses" ], "supported_modalities": [ @@ -8767,8 +9665,12 @@ "supported_output_modalities": [ "text" ], + "supports_computer_use": true, "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -8778,42 +9680,29 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "supports_none_reasoning_effort": true, - "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": false + "supports_xhigh_reasoning_effort": true }, - "azure/us/gpt-5.6-sol": { - "cache_creation_input_token_cost": 5.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, - "cache_creation_input_token_cost_above_272k_tokens_priority": 2.2e-05, - "cache_creation_input_token_cost_priority": 1.1e-05, - "cache_read_input_token_cost": 4.4e-07, - "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, - "cache_read_input_token_cost_above_272k_tokens_priority": 1.76e-06, - "cache_read_input_token_cost_priority": 8.8e-07, - "deprecation_date": "2028-01-11", - "input_cost_per_token": 4.4e-06, - "input_cost_per_token_above_272k_tokens": 8.8e-06, - "input_cost_per_token_above_272k_tokens_priority": 1.76e-05, - "input_cost_per_token_priority": 8.8e-06, + "azure/eu/gpt-6.1-terra": { + "cache_creation_input_token_cost": 1.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 3e-06, + "cache_read_input_token_cost": 6e-08, + "cache_read_input_token_cost_above_272k_tokens": 1.2e-07, + "input_cost_per_token": 1.2e-06, + "input_cost_per_token_above_272k_tokens": 2.4e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2.2e-05, - "output_cost_per_token_above_272k_tokens": 3.3e-05, - "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, - "output_cost_per_token_priority": 4.4e-05, + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_272k_tokens": 9e-06, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/gpt-6-1-terra-now-generally-available-in-microsoft-foundry-build-agents-that-see/4567769", "supported_endpoints": [ "/v1/chat/completions", - "/v1/batch", "/v1/responses" ], "supported_modalities": [ @@ -8823,8 +9712,12 @@ "supported_output_modalities": [ "text" ], + "supports_computer_use": true, "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -8834,42 +9727,30 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "supports_none_reasoning_effort": true, - "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": false + "supports_xhigh_reasoning_effort": true }, - "azure/us/gpt-5.6-terra": { - "cache_creation_input_token_cost": 2.75e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, - "cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-05, - "cache_creation_input_token_cost_priority": 5.5e-06, - "cache_read_input_token_cost": 2.2e-07, - "cache_read_input_token_cost_above_272k_tokens": 4.4e-07, - "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-07, - "cache_read_input_token_cost_priority": 4.4e-07, - "deprecation_date": "2028-01-11", - "input_cost_per_token": 2.2e-06, - "input_cost_per_token_above_272k_tokens": 4.4e-06, - "input_cost_per_token_above_272k_tokens_priority": 8.8e-06, - "input_cost_per_token_priority": 4.4e-06, + "azure/eu/gpt-6.1-sol": { + "cache_creation_input_token_cost": 3e-06, + "cache_creation_input_token_cost_above_272k_tokens": 6e-06, + "cache_read_input_token_cost": 1.2e-07, + "cache_read_input_token_cost_above_272k_tokens": 2.4e-07, + "deprecation_date": "2028-03-11", + "input_cost_per_token": 2.4e-06, + "input_cost_per_token_above_272k_tokens": 4.8e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.32e-05, - "output_cost_per_token_above_272k_tokens": 1.98e-05, - "output_cost_per_token_above_272k_tokens_priority": 3.96e-05, - "output_cost_per_token_priority": 2.64e-05, + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_272k_tokens": 1.8e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ "/v1/chat/completions", - "/v1/batch", "/v1/responses" ], "supported_modalities": [ @@ -8879,8 +9760,12 @@ "supported_output_modalities": [ "text" ], + "supports_computer_use": true, "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -8890,42 +9775,29 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "supports_none_reasoning_effort": true, - "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": false + "supports_xhigh_reasoning_effort": true }, - "azure/us/gpt-5.6-luna": { - "cache_creation_input_token_cost": 2.75e-07, - "cache_creation_input_token_cost_above_272k_tokens": 5.5e-07, - "cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-06, - "cache_creation_input_token_cost_priority": 5.5e-07, - "cache_read_input_token_cost": 2.2e-08, - "cache_read_input_token_cost_above_272k_tokens": 4.4e-08, - "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-08, - "cache_read_input_token_cost_priority": 4.4e-08, - "deprecation_date": "2028-01-11", - "input_cost_per_token": 2.2e-07, - "input_cost_per_token_above_272k_tokens": 4.4e-07, - "input_cost_per_token_above_272k_tokens_priority": 8.8e-07, - "input_cost_per_token_priority": 4.4e-07, + "azure/apac/gpt-6.1-terra": { + "cache_creation_input_token_cost": 1.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 3e-06, + "cache_read_input_token_cost": 6e-08, + "cache_read_input_token_cost_above_272k_tokens": 1.2e-07, + "input_cost_per_token": 1.2e-06, + "input_cost_per_token_above_272k_tokens": 2.4e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.32e-06, - "output_cost_per_token_above_272k_tokens": 1.98e-06, - "output_cost_per_token_above_272k_tokens_priority": 3.96e-06, - "output_cost_per_token_priority": 2.64e-06, + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_272k_tokens": 9e-06, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/gpt-6-1-terra-now-generally-available-in-microsoft-foundry-build-agents-that-see/4567769", "supported_endpoints": [ "/v1/chat/completions", - "/v1/batch", "/v1/responses" ], "supported_modalities": [ @@ -8935,8 +9807,12 @@ "supported_output_modalities": [ "text" ], + "supports_computer_use": true, "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -8946,31 +9822,28 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "supports_none_reasoning_effort": true, - "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": false + "supports_xhigh_reasoning_effort": true }, - "azure/us/gpt-6-astra": { - "deprecation_date": "2028-01-11", - "cache_creation_input_token_cost": 1.375e-05, - "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05, - "cache_read_input_token_cost": 1.1e-06, - "cache_read_input_token_cost_above_272k_tokens": 2.2e-06, - "input_cost_per_token": 1.1e-05, - "input_cost_per_token_above_272k_tokens": 2.2e-05, + "azure/apac/gpt-6.1-sol": { + "cache_creation_input_token_cost": 3e-06, + "cache_creation_input_token_cost_above_272k_tokens": 6e-06, + "cache_read_input_token_cost": 1.2e-07, + "cache_read_input_token_cost_above_272k_tokens": 2.4e-07, + "deprecation_date": "2028-03-11", + "input_cost_per_token": 2.4e-06, + "input_cost_per_token_above_272k_tokens": 4.8e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 5.5e-05, - "output_cost_per_token_above_272k_tokens": 8.25e-05, + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_272k_tokens": 1.8e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -8984,10 +9857,10 @@ ], "supports_computer_use": true, "supports_function_calling": true, - "supports_max_reasoning_effort": false, + "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -8999,27 +9872,20 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, - "azure/us/gpt-6-luna": { - "deprecation_date": "2028-03-11", - "cache_creation_input_token_cost": 1.375e-07, - "cache_creation_input_token_cost_above_272k_tokens": 2.75e-07, - "cache_read_input_token_cost": 1.1e-08, - "cache_read_input_token_cost_above_272k_tokens": 2.2e-08, - "input_cost_per_token": 1.1e-07, - "input_cost_per_token_above_272k_tokens": 2.2e-07, + "azure/gpt-chat-latest": { + "cache_read_input_token_cost": 5e-07, + "deprecation_date": "2027-05-18", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_token": 5e-06, "litellm_provider": "azure", - "max_input_tokens": 922000, + "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 5.5e-07, - "output_cost_per_token_above_272k_tokens": 8.25e-07, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", + "output_cost_per_token": 3e-05, + "reasoning_effort_levels": [ + "medium" + ], + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -9031,12 +9897,8 @@ "supported_output_modalities": [ "text" ], - "supports_computer_use": true, "supports_function_calling": true, - "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -9045,28 +9907,335 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "supports_xhigh_reasoning_effort": true + "supports_web_search": true }, - "azure/us/gpt-6-sol": { - "deprecation_date": "2028-03-11", - "cache_creation_input_token_cost": 2.75e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, - "cache_read_input_token_cost": 2.2e-07, - "cache_read_input_token_cost_above_272k_tokens": 4.4e-07, - "input_cost_per_token": 2.2e-06, - "input_cost_per_token_above_272k_tokens": 4.4e-06, + "azure/chat-latest": { + "cache_read_input_token_cost": 5e-07, + "deprecation_date": "2027-05-18", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_token": 5e-06, "litellm_provider": "azure", - "max_input_tokens": 922000, + "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.1e-05, - "output_cost_per_token_above_272k_tokens": 1.65e-05, + "output_cost_per_token": 3e-05, + "reasoning_effort_levels": [ + "medium" + ], + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "azure/us/gpt-5.6": { + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2.2e-05, + "cache_creation_input_token_cost_priority": 1.1e-05, + "cache_read_input_token_cost": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.76e-06, + "cache_read_input_token_cost_priority": 8.8e-07, + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_above_272k_tokens": 8.8e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.76e-05, + "input_cost_per_token_priority": 8.8e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_above_272k_tokens": 3.3e-05, + "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, + "output_cost_per_token_priority": 4.4e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure/us/gpt-5.6-sol": { + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2.2e-05, + "cache_creation_input_token_cost_priority": 1.1e-05, + "cache_read_input_token_cost": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.76e-06, + "cache_read_input_token_cost_priority": 8.8e-07, + "deprecation_date": "2028-01-11", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-6-sol", + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_above_272k_tokens": 8.8e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.76e-05, + "input_cost_per_token_priority": 8.8e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_above_272k_tokens": 3.3e-05, + "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, + "output_cost_per_token_priority": 4.4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure/us/gpt-5.6-terra": { + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-05, + "cache_creation_input_token_cost_priority": 5.5e-06, + "cache_read_input_token_cost": 2.2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-07, + "cache_read_input_token_cost_priority": 4.4e-07, + "deprecation_date": "2028-01-11", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-6.1-terra", + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_above_272k_tokens": 4.4e-06, + "input_cost_per_token_above_272k_tokens_priority": 8.8e-06, + "input_cost_per_token_priority": 4.4e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.32e-05, + "output_cost_per_token_above_272k_tokens": 1.98e-05, + "output_cost_per_token_above_272k_tokens_priority": 3.96e-05, + "output_cost_per_token_priority": 2.64e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure/us/gpt-5.6-luna": { + "cache_creation_input_token_cost": 2.75e-07, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-07, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-06, + "cache_creation_input_token_cost_priority": 5.5e-07, + "cache_read_input_token_cost": 2.2e-08, + "cache_read_input_token_cost_above_272k_tokens": 4.4e-08, + "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-08, + "cache_read_input_token_cost_priority": 4.4e-08, + "deprecation_date": "2028-01-11", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-6-luna", + "input_cost_per_token": 2.2e-07, + "input_cost_per_token_above_272k_tokens": 4.4e-07, + "input_cost_per_token_above_272k_tokens_priority": 8.8e-07, + "input_cost_per_token_priority": 4.4e-07, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.32e-06, + "output_cost_per_token_above_272k_tokens": 1.98e-06, + "output_cost_per_token_above_272k_tokens_priority": 3.96e-06, + "output_cost_per_token_priority": 2.64e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure/us/gpt-6-astra": { + "deprecation_date": "2028-01-11", + "cache_creation_input_token_cost": 1.375e-05, + "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05, + "cache_read_input_token_cost": 1.1e-06, + "cache_read_input_token_cost_above_272k_tokens": 2.2e-06, + "input_cost_per_token": 1.1e-05, + "input_cost_per_token_above_272k_tokens": 2.2e-05, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5.5e-05, + "output_cost_per_token_above_272k_tokens": 8.25e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": false, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure/us/gpt-6-luna": { + "deprecation_date": "2028-03-11", + "cache_creation_input_token_cost": 1.375e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.75e-07, + "cache_read_input_token_cost": 1.1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2.2e-08, + "input_cost_per_token": 1.1e-07, + "input_cost_per_token_above_272k_tokens": 2.2e-07, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5.5e-07, + "output_cost_per_token_above_272k_tokens": 8.25e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ @@ -9097,14 +10266,66 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "azure/us/gpt-6-sol": { + "deprecation_date": "2028-03-11", + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-05, + "cache_creation_input_token_cost_priority": 5.5e-06, + "cache_read_input_token_cost": 2.2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-07, + "cache_read_input_token_cost_priority": 4.4e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_above_272k_tokens": 4.4e-06, + "input_cost_per_token_above_272k_tokens_priority": 8.8e-06, + "input_cost_per_token_priority": 4.4e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_above_272k_tokens": 1.65e-05, + "output_cost_per_token_above_272k_tokens_priority": 3.3e-05, + "output_cost_per_token_priority": 2.2e-05, + "search_context_cost_per_query": {"search_context_size_high":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, + "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, "azure/us/gpt-chat-latest": { "cache_read_input_token_cost": 5.5e-07, - "deprecation_date": "2026-12-02", + "deprecation_date": "2027-05-18", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", - "max_input_tokens": 272000, + "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.3e-05, "reasoning_effort_levels": [ @@ -9150,16 +10371,15 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "output_cost_per_token_above_272k_tokens": 3.3e-05, "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, "output_cost_per_token_priority": 4.4e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -9198,6 +10418,8 @@ "cache_read_input_token_cost_above_272k_tokens_priority": 1.76e-06, "cache_read_input_token_cost_priority": 8.8e-07, "deprecation_date": "2028-01-11", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-6-sol", "input_cost_per_token": 4.4e-06, "input_cost_per_token_above_272k_tokens": 8.8e-06, "input_cost_per_token_above_272k_tokens_priority": 1.76e-05, @@ -9205,16 +10427,15 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "output_cost_per_token_above_272k_tokens": 3.3e-05, "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, "output_cost_per_token_priority": 4.4e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9254,6 +10475,8 @@ "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-07, "cache_read_input_token_cost_priority": 4.4e-07, "deprecation_date": "2028-01-11", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-6.1-terra", "input_cost_per_token": 2.2e-06, "input_cost_per_token_above_272k_tokens": 4.4e-06, "input_cost_per_token_above_272k_tokens_priority": 8.8e-06, @@ -9261,16 +10484,15 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.32e-05, "output_cost_per_token_above_272k_tokens": 1.98e-05, "output_cost_per_token_above_272k_tokens_priority": 3.96e-05, "output_cost_per_token_priority": 2.64e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9310,6 +10532,8 @@ "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-08, "cache_read_input_token_cost_priority": 4.4e-08, "deprecation_date": "2028-01-11", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-6-luna", "input_cost_per_token": 2.2e-07, "input_cost_per_token_above_272k_tokens": 4.4e-07, "input_cost_per_token_above_272k_tokens_priority": 8.8e-07, @@ -9317,16 +10541,15 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.32e-06, "output_cost_per_token_above_272k_tokens": 1.98e-06, "output_cost_per_token_above_272k_tokens_priority": 3.96e-06, "output_cost_per_token_priority": 2.64e-06, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9358,6 +10581,8 @@ }, "azure/gpt-5.5": { "deprecation_date": "2027-10-26", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.6", "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, "cache_read_input_token_cost_above_272k_tokens_batches": 5e-07, @@ -9374,9 +10599,8 @@ "input_cost_per_token_batches": 2.5e-06, "input_cost_per_token_flex": 2.5e-06, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, @@ -9385,9 +10609,9 @@ "output_cost_per_token_above_272k_tokens_priority": 9e-05, "output_cost_per_token_batches": 1.5e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9419,6 +10643,8 @@ }, "azure/us/gpt-5.5": { "deprecation_date": "2027-10-26", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.6", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-07, @@ -9433,16 +10659,15 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token_above_272k_tokens_batches": 2.475e-05, "output_cost_per_token_batches": 1.65e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9474,6 +10699,8 @@ }, "azure/eu/gpt-5.5": { "deprecation_date": "2027-10-26", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.6", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-07, @@ -9488,16 +10715,15 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token_above_272k_tokens_batches": 2.475e-05, "output_cost_per_token_batches": 1.65e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9540,18 +10766,17 @@ "input_cost_per_token_priority": 1.25e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, "output_cost_per_token_priority": 7.5e-05, "output_cost_per_token_above_272k_tokens_priority": 9e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -9577,6 +10802,8 @@ "supports_vision": true, "supports_web_search": true, "deprecation_date": "2027-10-26", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.6", "input_cost_per_token_above_272k_tokens_batches": 5e-06, "input_cost_per_token_above_272k_tokens_flex": 5e-06, "input_cost_per_token_batches": 2.5e-06, @@ -9587,6 +10814,8 @@ }, "azure/gpt-5.5-2026-04-24": { "deprecation_date": "2027-10-26", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.6", "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, "cache_read_input_token_cost_priority": 1.25e-06, @@ -9600,9 +10829,8 @@ "input_cost_per_token_above_272k_tokens_priority": 2e-05, "input_cost_per_token_flex": 2.5e-06, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_batches": 1.5e-05, @@ -9610,9 +10838,9 @@ "output_cost_per_token_priority": 7.5e-05, "output_cost_per_token_above_272k_tokens_priority": 9e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -9659,14 +10887,13 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -9692,6 +10919,8 @@ "supports_vision": true, "supports_web_search": true, "deprecation_date": "2027-10-26", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.6", "input_cost_per_token_above_272k_tokens_batches": 5.5e-06, "input_cost_per_token_batches": 2.75e-06, "output_cost_per_token_above_272k_tokens_batches": 2.475e-05, @@ -9700,6 +10929,8 @@ }, "azure/us/gpt-5.5-2026-04-24": { "deprecation_date": "2027-10-26", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.6", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, "cache_read_input_token_cost_priority": 1.375e-06, @@ -9712,14 +10943,13 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -9766,14 +10996,13 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -9799,6 +11028,8 @@ "supports_vision": true, "supports_web_search": true, "deprecation_date": "2027-10-26", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.6", "input_cost_per_token_above_272k_tokens_batches": 5.5e-06, "input_cost_per_token_batches": 2.75e-06, "output_cost_per_token_above_272k_tokens_batches": 2.475e-05, @@ -9807,6 +11038,8 @@ }, "azure/eu/gpt-5.5-2026-04-24": { "deprecation_date": "2027-10-26", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.6", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, "cache_read_input_token_cost_priority": 1.375e-06, @@ -9819,14 +11052,13 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -9868,14 +11100,13 @@ "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/batch", @@ -9912,14 +11143,13 @@ "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/batch", @@ -9946,6 +11176,7 @@ }, "azure/gpt-5.4-mini": { "deprecation_date": "2027-09-21", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, @@ -9954,13 +11185,12 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -9996,22 +11226,25 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true }, + "azure/gpt-mini-latest": { + "alias_of": "azure/gpt-5.4-mini" + }, "azure/gpt-5.4-mini-2026-03-17": { "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_flex": 3.75e-08, "cache_read_input_token_cost_priority": 1.5e-07, "deprecation_date": "2027-09-21", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 7.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -10050,6 +11283,7 @@ }, "azure/gpt-5.4-nano": { "deprecation_date": "2027-09-21", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_batches": 1e-08, "cache_read_input_token_cost_flex": 1e-08, @@ -10057,13 +11291,12 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -10101,17 +11334,17 @@ "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_flex": 1e-08, "deprecation_date": "2027-09-21", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 2e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -10147,38 +11380,46 @@ "cache_read_input_token_cost_batches": 1e-08 }, "azure/gpt-image-1": { + "cache_read_input_image_token_cost": 2.5e-06, "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2026-10-23", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-image-1.5", "input_cost_per_image_token": 1e-05, "input_cost_per_token": 5e-06, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 4e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "azure/hd/1024-x-1024/dall-e-3": { - "input_cost_per_pixel": 7.629e-08, + "input_cost_per_pixel": 8.39233e-08, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/hd/1024-x-1792/dall-e-3": { - "input_cost_per_pixel": 6.539e-08, + "input_cost_per_pixel": 7.19343e-08, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/hd/1792-x-1024/dall-e-3": { - "input_cost_per_pixel": 6.539e-08, + "input_cost_per_pixel": 7.19343e-08, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/high/1024-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 1.59263611e-07, "litellm_provider": "azure", "mode": "image_generation", @@ -10189,6 +11430,7 @@ }, "azure/high/1024-x-1536/gpt-image-1": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 1.58945719e-07, "litellm_provider": "azure", "mode": "image_generation", @@ -10199,6 +11441,7 @@ }, "azure/high/1536-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 1.58945719e-07, "litellm_provider": "azure", "mode": "image_generation", @@ -10209,6 +11452,7 @@ }, "azure/low/1024-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 1.0490417e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -10219,6 +11463,7 @@ }, "azure/low/1024-x-1536/gpt-image-1": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 1.0172526e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -10229,6 +11474,7 @@ }, "azure/low/1536-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 1.0172526e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -10239,6 +11485,7 @@ }, "azure/medium/1024-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 4.0054321e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -10249,6 +11496,7 @@ }, "azure/medium/1024-x-1536/gpt-image-1": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 4.0054321e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -10259,6 +11507,7 @@ }, "azure/medium/1536-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 4.0054321e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -10268,52 +11517,68 @@ ] }, "azure/gpt-image-1-mini": { + "cache_read_input_image_token_cost": 2.5e-07, "cache_read_input_token_cost": 2e-07, "deprecation_date": "2027-04-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_image_token": 2.5e-06, "input_cost_per_token": 2e-06, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 8e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "azure/gpt-image-1.5": { + "cache_read_input_image_token_cost": 2e-06, "deprecation_date": "2026-12-16", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-image-2", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, "input_cost_per_image_token": 8e-06, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3.2e-05, + "output_cost_per_token": 1e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "azure/gpt-image-1.5-2025-12-16": { + "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2026-12-16", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-image-2", "input_cost_per_token": 5e-06, "input_cost_per_image_token": 8e-06, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3.2e-05, + "output_cost_per_token": 1e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "azure/gpt-image-2": { + "cache_read_input_image_token_cost": 2e-06, "deprecation_date": "2027-10-21", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, "input_cost_per_image_token": 8e-06, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10322,13 +11587,16 @@ "supports_pdf_input": true }, "azure/gpt-image-2.5-flare": { + "cache_read_input_image_token_cost": 2e-06, "deprecation_date": "2027-09-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, "input_cost_per_image_token": 8e-06, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10337,13 +11605,16 @@ "supports_pdf_input": true }, "azure/gpt-image-2.5-sunburst": { + "cache_read_input_image_token_cost": 2e-06, "deprecation_date": "2027-09-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, "input_cost_per_image_token": 8e-06, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10352,13 +11623,16 @@ "supports_pdf_input": true }, "azure/gpt-image-2-2026-04-21": { + "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-10-21", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 5e-06, "input_cost_per_image_token": 8e-06, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10368,6 +11642,7 @@ }, "azure/low/1024-x-1024/gpt-image-1-mini": { "deprecation_date": "2027-04-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 2.0751953125e-09, "litellm_provider": "azure", "mode": "image_generation", @@ -10378,6 +11653,7 @@ }, "azure/low/1024-x-1536/gpt-image-1-mini": { "deprecation_date": "2027-04-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 2.0751953125e-09, "litellm_provider": "azure", "mode": "image_generation", @@ -10388,6 +11664,7 @@ }, "azure/low/1536-x-1024/gpt-image-1-mini": { "deprecation_date": "2027-04-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 2.0345052083e-09, "litellm_provider": "azure", "mode": "image_generation", @@ -10398,6 +11675,7 @@ }, "azure/medium/1024-x-1024/gpt-image-1-mini": { "deprecation_date": "2027-04-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 8.056640625e-09, "litellm_provider": "azure", "mode": "image_generation", @@ -10408,6 +11686,7 @@ }, "azure/medium/1024-x-1536/gpt-image-1-mini": { "deprecation_date": "2027-04-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 8.056640625e-09, "litellm_provider": "azure", "mode": "image_generation", @@ -10418,6 +11697,7 @@ }, "azure/medium/1536-x-1024/gpt-image-1-mini": { "deprecation_date": "2027-04-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 7.9752604167e-09, "litellm_provider": "azure", "mode": "image_generation", @@ -10428,6 +11708,7 @@ }, "azure/high/1024-x-1024/gpt-image-1-mini": { "deprecation_date": "2027-04-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 3.173828125e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -10438,6 +11719,7 @@ }, "azure/high/1024-x-1536/gpt-image-1-mini": { "deprecation_date": "2027-04-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 3.173828125e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -10448,6 +11730,7 @@ }, "azure/high/1536-x-1024/gpt-image-1-mini": { "deprecation_date": "2027-04-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 3.1575520833e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -10460,7 +11743,7 @@ "input_cost_per_token": 8e-06, "litellm_provider": "azure", "max_input_tokens": 32000, - "max_tokens": 32000, + "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_function_calling": true @@ -10469,19 +11752,19 @@ "input_cost_per_token": 8e-06, "litellm_provider": "azure", "max_input_tokens": 32000, - "max_tokens": 32000, + "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_function_calling": true }, "azure/o1": { "deprecation_date": "2026-11-19", + "successor_model": "azure/gpt-5.6-sol", "cache_read_input_token_cost": 7.5e-06, "input_cost_per_token": 1.5e-05, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6e-05, "supports_function_calling": true, @@ -10494,12 +11777,12 @@ "azure/o1-2024-12-17": { "cache_read_input_token_cost": 7.5e-06, "deprecation_date": "2026-11-19", + "successor_model": "azure/gpt-5.6-sol", "input_cost_per_token": 1.5e-05, "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6e-05, "output_cost_per_token_batches": 3e-05, @@ -10518,7 +11801,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, @@ -10536,7 +11818,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, @@ -10549,14 +11830,22 @@ }, "azure/o3": { "deprecation_date": "2026-11-19", + "successor_model": "azure/gpt-5.6-sol", "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, + "output_cost_per_token_batches": 4e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -10579,16 +11868,21 @@ }, "azure/o3-2025-04-16": { "deprecation_date": "2026-11-19", + "successor_model": "azure/gpt-5.6-sol", "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -10613,21 +11907,21 @@ "azure/o3-deep-research": { "cache_read_input_token_cost": 2.5e-06, "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.6-sol", "input_cost_per_token": 1e-05, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 4e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ - "/v1/chat/completions", "/v1/batch", "/v1/responses" ], @@ -10651,14 +11945,18 @@ }, "azure/o3-mini": { "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.6-terra", "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, + "output_cost_per_token_batches": 2.2e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -10668,12 +11966,13 @@ "azure/o3-mini-2025-01-31": { "cache_read_input_token_cost": 5.5e-07, "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.6-terra", "input_cost_per_token": 1.1e-06, "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, @@ -10685,18 +11984,23 @@ }, "azure/o3-pro": { "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.6-sol", "input_cost_per_token": 2e-05, "input_cost_per_token_batches": 1e-05, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ - "/v1/chat/completions", "/v1/batch", "/v1/responses" ], @@ -10717,18 +12021,23 @@ }, "azure/o3-pro-2025-06-10": { "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.6-sol", "input_cost_per_token": 2e-05, "input_cost_per_token_batches": 1e-05, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ - "/v1/chat/completions", "/v1/batch", "/v1/responses" ], @@ -10749,14 +12058,23 @@ }, "azure/o4-mini": { "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.6-terra", "cache_read_input_token_cost": 2.75e-07, "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, + "output_cost_per_token_batches": 2.2e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -10780,15 +12098,21 @@ "azure/o4-mini-2025-04-16": { "cache_read_input_token_cost": 2.75e-07, "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.6-terra", "input_cost_per_token": 1.1e-06, "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": false, @@ -10805,52 +12129,55 @@ "output_cost_per_token": 0.0 }, "azure/standard/1024-x-1024/dall-e-3": { - "input_cost_per_pixel": 3.81469e-08, + "input_cost_per_pixel": 4.19617e-08, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/standard/1024-x-1792/dall-e-3": { - "input_cost_per_pixel": 4.359e-08, + "input_cost_per_pixel": 4.79562e-08, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/standard/1792-x-1024/dall-e-3": { - "input_cost_per_pixel": 4.359e-08, + "input_cost_per_pixel": 4.79562e-08, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/text-embedding-3-large": { "deprecation_date": "2028-02-09", - "input_cost_per_token": 1.3e-07, + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_token": 1.43e-07, "litellm_provider": "azure", - "max_input_tokens": 8191, - "max_tokens": 8191, + "max_input_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/text-embedding-3-small": { "deprecation_date": "2028-02-09", - "input_cost_per_token": 2e-08, + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_token": 2.2e-08, "litellm_provider": "azure", - "max_input_tokens": 8191, - "max_tokens": 8191, + "max_input_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/text-embedding-ada-002": { "deprecation_date": "2028-02-09", - "input_cost_per_token": 1e-07, + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_token": 1.1e-07, "litellm_provider": "azure", - "max_input_tokens": 8191, - "max_tokens": 8191, + "max_input_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/speech/azure-tts": { "input_cost_per_character": 1.5e-05, @@ -10877,18 +12204,24 @@ }, "azure/tts-1": { "deprecation_date": "2026-12-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_character": 1.5e-05, "litellm_provider": "azure", - "mode": "audio_speech" + "mode": "audio_speech", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule" }, "azure/tts-1-hd": { "deprecation_date": "2026-12-15", - "input_cost_per_character": 3e-05, + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_character": 3.3e-05, "litellm_provider": "azure", - "mode": "audio_speech" + "mode": "audio_speech", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule" }, "azure/us/gpt-4.1-2025-04-14": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.1", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_priority": 9.63e-07, "input_cost_per_token": 2.2e-06, @@ -10897,11 +12230,15 @@ "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, "output_cost_per_token_priority": 1.54e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -10927,6 +12264,8 @@ }, "azure/us/gpt-4.1-mini-2025-04-14": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.4-mini", "cache_read_input_token_cost": 1.1e-07, "cache_read_input_token_cost_priority": 1.93e-07, "input_cost_per_token": 4.4e-07, @@ -10935,11 +12274,15 @@ "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.76e-06, "output_cost_per_token_batches": 8.8e-07, "output_cost_per_token_priority": 3.08e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -10965,13 +12308,14 @@ }, "azure/us/gpt-4.1-nano-2025-04-14": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.4-nano", "cache_read_input_token_cost": 2.8e-08, "input_cost_per_token": 1.1e-07, "input_cost_per_token_batches": 5.5e-08, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, @@ -10999,13 +12343,14 @@ }, "azure/us/gpt-4o-2024-08-06": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.1", "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, "input_cost_per_token_batches": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, @@ -11017,8 +12362,31 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/us/gpt-4o": { + "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.1", + "cache_creation_input_token_cost": 1.38e-06, + "cache_read_input_token_cost": 1.375e-06, + "input_cost_per_token": 2.75e-06, + "input_cost_per_token_batches": 1.375e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/us/gpt-4o-2024-11-20": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.1", "cache_creation_input_token_cost": 1.38e-06, "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, @@ -11026,7 +12394,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, @@ -11037,17 +12404,46 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/us/gpt-4o-mini": { + "cache_read_input_token_cost": 8.3e-08, + "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_token": 1.65e-07, + "input_cost_per_token_batches": 8.3e-08, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/us/gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 8.3e-08, "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.65e-07, "input_cost_per_token_batches": 8.3e-08, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -11064,7 +12460,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2.2e-05, "output_cost_per_token": 2.64e-06, @@ -11075,37 +12470,18 @@ "supports_system_messages": true, "supports_tool_choice": true }, - "azure/us/gpt-4o-realtime-preview-2024-10-01": { - "cache_creation_input_audio_token_cost": 2.2e-05, - "cache_read_input_token_cost": 2.75e-06, - "input_cost_per_audio_token": 0.00011, - "input_cost_per_token": 5.5e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "realtime", - "output_cost_per_audio_token": 0.00022, - "output_cost_per_token": 2.2e-05, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "azure/us/gpt-4o-realtime-preview-2024-12-17": { - "cache_read_input_audio_token_cost": 2.5e-06, + "cache_read_input_audio_token_cost": 2.75e-06, "cache_read_input_token_cost": 2.75e-06, "input_cost_per_audio_token": 4.4e-05, "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", - "max_input_tokens": 128000, + "max_input_tokens": 16000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", - "output_cost_per_audio_token": 8e-05, + "output_cost_per_audio_token": 8.8e-05, "output_cost_per_token": 2.2e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_modalities": [ "text", "audio" @@ -11125,17 +12501,23 @@ "cache_read_input_token_cost": 1.375e-07, "cache_read_input_token_cost_priority": 2.75e-07, "deprecation_date": "2027-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.1", "input_cost_per_token": 1.375e-06, "input_cost_per_token_batches": 6.875e-07, "input_cost_per_token_priority": 2.75e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -11164,18 +12546,24 @@ "azure/us/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.75e-08, "cache_read_input_token_cost_priority": 4.95e-08, - "deprecation_date": "2027-02-09", + "deprecation_date": "2027-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.4-mini", "input_cost_per_token": 2.75e-07, "input_cost_per_token_batches": 1.375e-07, "input_cost_per_token_priority": 4.95e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, "output_cost_per_token_priority": 3.96e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -11204,15 +12592,21 @@ "azure/us/gpt-5-nano-2025-08-07": { "cache_read_input_token_cost": 5.5e-09, "deprecation_date": "2027-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.4-nano", "input_cost_per_token": 5.5e-08, "input_cost_per_token_batches": 2.75e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -11239,7 +12633,9 @@ "cache_read_input_token_cost_batches": 2.75e-09 }, "azure/us/gpt-5.1": { - "deprecation_date": "2027-05-15", + "deprecation_date": "2027-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.2", "cache_read_input_token_cost": 1.375e-07, "cache_read_input_token_cost_batches": 6.875e-08, "cache_read_input_token_cost_priority": 2.75e-07, @@ -11247,7 +12643,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "supported_endpoints": [ @@ -11279,16 +12674,22 @@ "input_cost_per_token_priority": 2.75e-06, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.1-codex": { "deprecation_date": "2027-05-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.2-codex", "cache_read_input_token_cost": 1.375e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -11315,12 +12716,12 @@ }, "azure/us/gpt-5.1-codex-mini": { "deprecation_date": "2027-05-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 2.75e-08, "input_cost_per_token": 2.75e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2.2e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -11345,15 +12746,34 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/us/o1": { + "cache_read_input_token_cost": 8.25e-06, + "deprecation_date": "2026-11-19", + "successor_model": "azure/us/gpt-5.6-sol", + "input_cost_per_token": 1.65e-05, + "input_cost_per_token_batches": 8.25e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6.6e-05, + "output_cost_per_token_batches": 3.3e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/us/o1-2024-12-17": { "cache_read_input_token_cost": 8.25e-06, "deprecation_date": "2026-11-19", + "successor_model": "azure/us/gpt-5.6-sol", "input_cost_per_token": 1.65e-05, "input_cost_per_token_batches": 8.25e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6.6e-05, "output_cost_per_token_batches": 3.3e-05, @@ -11371,7 +12791,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, @@ -11381,18 +12800,61 @@ "supports_prompt_caching": true, "supports_vision": false }, + "azure/us/o3": { + "deprecation_date": "2026-11-19", + "successor_model": "azure/us/gpt-5.6-sol", + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 8.8e-06, + "output_cost_per_token_batches": 4.4e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/us/o3-2025-04-16": { "deprecation_date": "2026-11-19", + "successor_model": "azure/us/gpt-5.6-sol", "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 2.2e-06, "input_cost_per_token_batches": 1.1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -11414,15 +12876,35 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/us/o3-mini": { + "cache_read_input_token_cost": 6.05e-07, + "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.6-terra", + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, "azure/us/o3-mini-2025-01-31": { "cache_read_input_token_cost": 6.05e-07, "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.6-terra", "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, @@ -11432,18 +12914,51 @@ "supports_tool_choice": true, "supports_vision": false }, + "azure/us/o4-mini": { + "cache_read_input_token_cost": 3.03e-07, + "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.6-terra", + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/us/o4-mini-2025-04-16": { "cache_read_input_token_cost": 3.03e-07, "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.6-terra", "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": false, @@ -11454,17 +12969,21 @@ "supports_vision": true }, "azure/whisper-1": { - "deprecation_date": "2026-12-15", + "deprecation_date": "2027-02-26", + "deprecation_source": "https://management.azure.com/subscriptions/a88257a5-3323-4ef9-95bf-5681a46c9624/providers/Microsoft.CognitiveServices/locations/eastus/models?api-version=2024-10-01", "input_cost_per_second": 0.0001, "litellm_provider": "azure", "mode": "audio_transcription", - "output_cost_per_second": 0.0001 + "output_cost_per_second": 0.0001, + "source": "https://management.azure.com/subscriptions/a88257a5-3323-4ef9-95bf-5681a46c9624/providers/Microsoft.CognitiveServices/locations/eastus/models?api-version=2024-10-01" }, "azure_ai/Cohere-embed-v3-english": { + "deprecation_date": "2027-02-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/Cohere-Embed-V5-Fast", "input_cost_per_token": 1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -11472,10 +12991,12 @@ "supports_embedding_image_input": true }, "azure_ai/Cohere-embed-v3-multilingual": { + "deprecation_date": "2027-02-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/Cohere-Embed-V5-Fast", "input_cost_per_token": 1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -11483,11 +13004,12 @@ "supports_embedding_image_input": true }, "azure_ai/Codestral-2501": { + "deprecation_date": "2027-02-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 3e-07, "litellm_provider": "azure_ai", "max_input_tokens": 256000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -11500,10 +13022,14 @@ "supported_output_modalities": [ "text" ], - "supports_native_streaming": true + "supports_native_streaming": true, + "supports_pdf_input": false }, "azure_ai/FLUX-1.1-pro": { + "deprecation_date": "2027-01-05", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "litellm_provider": "azure_ai", + "max_input_tokens": 5000, "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/black-forest-labs-flux-1-kontext-pro-and-flux1-1-pro-now-available-in-azure-ai-f/4434659", @@ -11512,28 +13038,35 @@ ] }, "azure_ai/FLUX.1-Kontext-pro": { + "deprecation_date": "2027-01-05", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "litellm_provider": "azure_ai", + "max_input_tokens": 5000, "mode": "image_generation", "output_cost_per_image": 0.04, - "source": "https://marketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice", + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/black-forest-labs/", "supported_endpoints": [ "/v1/images/generations" ] }, "azure_ai/flux.2-pro": { + "deprecation_date": "2027-01-20", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "litellm_provider": "azure_ai", + "max_input_tokens": 32000, "mode": "image_generation", "output_cost_per_image": 0.04, - "source": "https://ai.azure.com/explore/models/flux.2-pro/version/1/registry/azureml-blackforestlabs", + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supported_endpoints": [ "/v1/images/generations" ] }, "azure_ai/FLUX.2-flex": { + "deprecation_date": "2027-01-20", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_pixel": 5e-08, "litellm_provider": "azure_ai", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "image_generation", "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/black-forest-labs/", "supported_endpoints": [ @@ -11555,11 +13088,11 @@ "litellm_provider": "azure_ai", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.85e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true @@ -11570,43 +13103,45 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.828e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/FW-GLM-5": { "deprecation_date": "2027-07-01", + "successor_model": "azure_ai/FW-GLM-5.2", "cache_read_input_token_cost": 2.2e-07, "input_cost_per_token": 1.1e-06, "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.52e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/FW-GLM-5.1": { "deprecation_date": "2027-07-01", + "successor_model": "azure_ai/FW-GLM-5.2", "cache_read_input_token_cost": 2.86e-07, "input_cost_per_token": 1.54e-06, "litellm_provider": "azure_ai", "max_input_tokens": 202800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.84e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true @@ -11617,11 +13152,11 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.84e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true @@ -11632,11 +13167,11 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 7.26e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true @@ -11647,7 +13182,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.46e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -11658,6 +13192,7 @@ "text" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true @@ -11669,7 +13204,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.3e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -11681,6 +13215,7 @@ "text" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -11692,7 +13227,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -11704,6 +13238,7 @@ "text" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -11715,7 +13250,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -11727,6 +13261,7 @@ "text" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -11738,7 +13273,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "reasoning_effort_levels": [ @@ -11755,11 +13289,15 @@ "text" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, + "azure_ai/kimi-latest": { + "alias_of": "azure_ai/FW-Kimi-K3" + }, "azure_ai/FW-MiniMax-M2.5": { "deprecation_date": "2027-07-01", "cache_read_input_token_cost": 3.3e-08, @@ -11767,11 +13305,11 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.32e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true @@ -11782,7 +13320,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 512000, "max_output_tokens": 512000, - "max_tokens": 512000, "mode": "chat", "output_cost_per_token": 1.32e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -11794,11 +13331,15 @@ "text" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, + "azure_ai/minimax-latest": { + "alias_of": "azure_ai/FW-MiniMax-M3" + }, "azure_ai/FW-Nemotron-Lightning-3.5-30B-A3B": { "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 6e-08, @@ -11814,6 +13355,7 @@ "text" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -11825,7 +13367,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.64e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -11836,6 +13377,7 @@ "text" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true @@ -11852,7 +13394,10 @@ "/v1/images/generations", "/v1/images/edits" ], - "deprecation_date": "2026-10-01" + "deprecation_date": "2026-10-01", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/MAI-Image-2.6", + "max_input_tokens": 32000 }, "azure_ai/MAI-Image-2.5-Flash": { "input_cost_per_image_token": 1.75e-06, @@ -11866,13 +13411,18 @@ "/v1/images/generations", "/v1/images/edits" ], - "deprecation_date": "2026-10-01" + "deprecation_date": "2026-10-01", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/MAI-Image-2.6-Flash", + "max_input_tokens": 32000 }, "azure_ai/MAI-Image-2.5-Pro": { "deprecation_date": "2026-10-01", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_image_token": 8e-06, "input_cost_per_token": 5e-06, "litellm_provider": "azure_ai", + "max_input_tokens": 32000, "mode": "image_generation", "output_cost_per_image": 0.1085, "output_cost_per_image_token": 0.000106, @@ -11888,7 +13438,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 256000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -11902,247 +13451,143 @@ "text" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/Llama-3.3-70B-Instruct": { + "deprecation_date": "2027-01-31", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 7.1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.1e-07, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true }, "azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8": { + "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 2.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_vision": true }, "azure_ai/Llama-4-Scout-17B-16E-Instruct": { + "deprecation_date": "2027-01-31", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 2e-07, "litellm_provider": "azure_ai", "max_input_tokens": 10000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 7.8e-07, "source": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/", "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "azure_ai/Meta-Llama-3-70B-Instruct": { - "input_cost_per_token": 1.1e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 8192, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 3.7e-07, - "supports_tool_choice": true - }, - "azure_ai/Meta-Llama-3.1-70B-Instruct": { - "input_cost_per_token": 2.68e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 3.54e-06, - "source": "https://marketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-70b-instruct-offer?tab=PlansAndPrice", - "supports_tool_choice": true - }, - "azure_ai/Phi-3-medium-128k-instruct": { - "input_cost_per_token": 1.7e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 6.8e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_tool_choice": true, - "supports_vision": false - }, - "azure_ai/Phi-3-medium-4k-instruct": { - "input_cost_per_token": 1.7e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 6.8e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_tool_choice": true, - "supports_vision": false - }, - "azure_ai/Phi-3-mini-128k-instruct": { - "input_cost_per_token": 1.3e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 5.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_tool_choice": true, - "supports_vision": false - }, - "azure_ai/Phi-3-mini-4k-instruct": { - "input_cost_per_token": 1.3e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 5.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_tool_choice": true, - "supports_vision": false - }, - "azure_ai/Phi-3-small-128k-instruct": { - "input_cost_per_token": 1.5e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_tool_choice": true, - "supports_vision": false - }, - "azure_ai/Phi-3-small-8k-instruct": { - "input_cost_per_token": 1.5e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_tool_choice": true, - "supports_vision": false - }, - "azure_ai/Phi-3.5-MoE-instruct": { - "input_cost_per_token": 1.6e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 6.4e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_tool_choice": true, - "supports_vision": false - }, - "azure_ai/Phi-3.5-mini-instruct": { - "input_cost_per_token": 1.3e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 5.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_tool_choice": true, - "supports_vision": false - }, - "azure_ai/Phi-3.5-vision-instruct": { - "input_cost_per_token": 1.3e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 5.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_pdf_input": false, "supports_tool_choice": true, "supports_vision": true }, "azure_ai/Phi-4": { + "deprecation_date": "2027-01-17", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "microsoft--phi-4", "input_cost_per_token": 1.25e-07, "litellm_provider": "azure_ai", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_vision": false }, "azure_ai/Phi-4-mini-instruct": { + "deprecation_date": "2027-01-17", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "microsoft--phi-4", "input_cost_per_token": 7.5e-08, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_function_calling": true + "supports_function_calling": true, + "supports_pdf_input": false }, "azure_ai/Phi-4-multimodal-instruct": { + "deprecation_date": "2027-01-17", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "microsoft--phi-4", "input_cost_per_audio_token": 4e-06, "input_cost_per_token": 8e-08, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3.2e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_audio_input": true, "supports_function_calling": true, + "supports_pdf_input": false, "supports_vision": true }, "azure_ai/Phi-4-mini-reasoning": { + "deprecation_date": "2027-01-17", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "microsoft--phi-4", "input_cost_per_token": 7.5e-08, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_function_calling": true + "supports_function_calling": true, + "supports_pdf_input": false }, "azure_ai/Phi-4-reasoning": { + "deprecation_date": "2027-01-17", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "microsoft--phi-4", "input_cost_per_token": 1.25e-07, "litellm_provider": "azure_ai", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_reasoning": true }, "azure_ai/mistral-document-ai-2512": { + "deprecation_date": "2027-02-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "litellm_provider": "azure_ai", "ocr_cost_per_page": 0.003, "mode": "ocr", "supported_endpoints": [ "/v1/ocr" ], - "source": "https://ai.azure.com/catalog/models/mistral-document-ai-2512" + "source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/mistral-ocr-4-0" }, "azure_ai/mistral-ocr-4-0": { "litellm_provider": "azure_ai", @@ -12156,6 +13601,7 @@ }, "azure_ai/Cohere-parse-v5": { "deprecation_date": "2026-12-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "litellm_provider": "azure_ai", "mode": "ocr", "ocr_cost_per_page": 0.0015, @@ -12165,15 +13611,18 @@ ] }, "azure_ai/cohere-command-a": { + "deprecation_date": "2027-02-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "coherelabs-command-a-plus-05-2026-fp81", "input_cost_per_token": 2.5e-06, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 8182, - "max_tokens": 8182, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true }, "azure_ai/doc-intelligence/prebuilt-read": { @@ -12204,153 +13653,146 @@ "source": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/" }, "azure_ai/MAI-DS-R1": { + "deprecation_date": "2026-02-27", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "input_cost_per_token": 1.35e-06, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", + "supports_pdf_input": false, "supports_reasoning": true, "supports_tool_choice": true }, - "azure_ai/cohere-rerank-v3-english": { - "input_cost_per_query": 0.002, - "input_cost_per_token": 0.0, - "litellm_provider": "azure_ai", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "rerank", - "output_cost_per_token": 0.0 - }, - "azure_ai/cohere-rerank-v3-multilingual": { - "input_cost_per_query": 0.002, - "input_cost_per_token": 0.0, - "litellm_provider": "azure_ai", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "rerank", - "output_cost_per_token": 0.0 - }, "azure_ai/cohere-rerank-v4.0-pro": { + "deprecation_date": "2027-09-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/cohere-rerank-v5-pro", "input_cost_per_query": 0.0025, "input_cost_per_token": 0.0, "litellm_provider": "azure_ai", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-cohere-rerank-4-0-in-microsoft-foundry/4477076" }, "azure_ai/cohere-rerank-v4.0-fast": { + "deprecation_date": "2027-09-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/cohere-rerank-v5-fast", "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, "litellm_provider": "azure_ai", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-cohere-rerank-4-0-in-microsoft-foundry/4477076" }, "azure_ai/deepseek-v3.2": { + "deprecation_date": "2027-11-01", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/deepseek-v4.1-flash", "input_cost_per_token": 5.8e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.68e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/deepseek-v3.2-speciale": { + "deprecation_date": "2027-11-01", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/deepseek-v4-pro", "input_cost_per_token": 5.8e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.68e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, - "azure_ai/deepseek-v3": { - "input_cost_per_token": 1.14e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 4.56e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_tool_choice": true - }, "azure_ai/deepseek-v4-pro": { "deprecation_date": "2028-02-20", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 1.74e-06, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.48e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_reasoning": true, "supports_tool_choice": true, "cache_read_input_token_cost": 1.45e-07, "supports_prompt_caching": true }, + "azure_ai/deepseek-pro-latest": { + "alias_of": "azure_ai/deepseek-v4-pro" + }, "azure_ai/deepseek-v4-flash": { "deprecation_date": "2028-02-20", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/DeepSeek-V4-Flash-0731", "input_cost_per_token": 1.9e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 5.1e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_reasoning": true, "supports_tool_choice": true, "cache_read_input_token_cost": 2.8e-08, "supports_prompt_caching": true }, + "azure_ai/deepseek-flash-latest": { + "alias_of": "azure_ai/deepseek-v4-flash" + }, "azure_ai/DeepSeek-V4-Flash-0731": { "cache_read_input_token_cost": 1.4e-08, "deprecation_date": "2026-12-03", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 4.4e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 1.32e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/embed-v-4-0": { + "deprecation_date": "2027-06-01", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/Cohere-Embed-V5-Fast", "input_cost_per_token": 1.2e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, - "max_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 3072, @@ -12366,15 +13808,18 @@ "input_cost_per_image_token": 4.7e-07 }, "azure_ai/grok-4": { + "deprecation_date": "2027-01-31", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/grok-4.3", "input_cost_per_token": 3e-06, "litellm_provider": "azure_ai", "max_input_tokens": 262000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_function_calling": true, + "supports_pdf_input": false, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true @@ -12387,12 +13832,12 @@ "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -12403,17 +13848,17 @@ "azure_ai/grok-4.6": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_200k_tokens": 1e-06, - "input_cost_per_token": 1.25e-06, + "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -12424,15 +13869,16 @@ "azure_ai/grok-4-20-reasoning": { "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-04-06", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure_ai", "max_input_tokens": 262000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -12443,15 +13889,16 @@ "azure_ai/grok-4-20-non-reasoning": { "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-04-06", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure_ai", "max_input_tokens": 262000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -12459,79 +13906,82 @@ "supports_web_search": true }, "azure_ai/grok-4-1-fast-non-reasoning": { + "deprecation_date": "2027-05-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 128000, + "max_output_tokens": 128000, "mode": "chat", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true }, "azure_ai/grok-4-1-fast-reasoning": { + "deprecation_date": "2027-05-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "token_count_framing": 149, + "token_count_tool_framing": 302, + "token_count_responses_framing": 145, + "token_count_responses_tool_framing": 100, + "max_input_tokens": 128000, + "max_output_tokens": 128000, "mode": "chat", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true }, "azure_ai/grok-code-fast-1": { + "deprecation_date": "2027-01-31", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 2e-07, "litellm_provider": "azure_ai", "max_input_tokens": 256000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_function_calling": true, + "supports_pdf_input": false, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true }, "azure_ai/jais-30b-chat": { - "input_cost_per_token": 0.0032, + "deprecation_date": "2026-01-30", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", + "input_cost_per_token": 3.2e-06, "litellm_provider": "azure_ai", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.00971, - "source": "https://ai.azure.com/catalog/models/jais-30b-chat" - }, - "azure_ai/jamba-instruct": { - "input_cost_per_token": 5e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 70000, - "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 7e-07, - "supports_tool_choice": true + "output_cost_per_token": 9.71e-06, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", + "supports_pdf_input": false }, "azure_ai/kimi-k2.5": { "deprecation_date": "2027-01-26", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 6e-07, "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, @@ -12540,11 +13990,11 @@ }, "azure_ai/kimi-k2.6": { "deprecation_date": "2027-04-16", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 9.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12556,6 +14006,7 @@ "text" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, @@ -12563,38 +14014,18 @@ "supports_prompt_caching": true }, "azure_ai/ministral-3b": { + "deprecation_date": "2026-12-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "ministral-ministral-4b-instruct", "input_cost_per_token": 4e-08, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 4e-08, "source": "https://marketplace.microsoft.com/en/marketplace/apps/000-000.ministral-3b-2410-offer?tab=Overview", "supports_function_calling": true, - "supports_tool_choice": true - }, - "azure_ai/mistral-large": { - "input_cost_per_token": 4e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 1.2e-05, - "supports_function_calling": true, - "supports_tool_choice": true - }, - "azure_ai/mistral-large-2407": { - "input_cost_per_token": 2e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 6e-06, - "source": "https://marketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview", - "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true }, "azure_ai/mistral-large-latest": { @@ -12602,11 +14033,11 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://marketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview", "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true }, "azure_ai/mistral-large-3": { @@ -12614,68 +14045,67 @@ "litellm_provider": "azure_ai", "max_input_tokens": 256000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_vision": true }, "azure_ai/mistral-medium-2505": { + "deprecation_date": "2026-12-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/mistral-medium-3-5", "input_cost_per_token": 4e-07, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true }, "azure_ai/mistral-nemo": { + "deprecation_date": "2026-01-30", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", + "successor_model": "azure_ai/mistral-small-2503", "input_cost_per_token": 1.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-07, - "source": "https://marketplace.microsoft.com/en/marketplace/apps/000-000.mistral-nemo-12b-2407?tab=PlansAndPrice", - "supports_function_calling": true - }, - "azure_ai/mistral-small": { - "input_cost_per_token": 1e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 3e-06, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_function_calling": true, - "supports_tool_choice": true + "supports_pdf_input": false }, "azure_ai/mistral-small-2503": { + "deprecation_date": "2027-02-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "mistralai-mistral-small-4-119b-2603", "input_cost_per_token": 1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_vision": true }, "babbage-002": { "deprecation_date": "2026-09-28", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 4e-07, "input_cost_per_token_batches": 2e-07, "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, @@ -12687,7 +14117,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_tool_choice": true }, @@ -12697,7 +14126,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_tool_choice": true }, @@ -12707,7 +14135,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_tool_choice": true }, @@ -12717,7 +14144,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_tool_choice": true }, @@ -12742,7 +14168,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -12752,7 +14177,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2:1": { @@ -12761,7 +14185,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -12771,7 +14194,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -12781,7 +14203,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2:1": { @@ -12790,7 +14211,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -12799,7 +14219,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 7.55e-06, "supports_tool_choice": true @@ -12809,7 +14228,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true @@ -12819,19 +14237,23 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true }, "bedrock/ap-northeast-1/deepseek.v3.2": { "input_cost_per_token": 7.4e-07, + "input_cost_per_token_batches": 3.7e-07, + "input_cost_per_token_flex": 3.7e-07, + "input_cost_per_token_priority": 1.295e-06, "litellm_provider": "bedrock", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_input_tokens": 156000, + "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.22e-06, + "output_cost_per_token_batches": 1.11e-06, + "output_cost_per_token_flex": 1.11e-06, + "output_cost_per_token_priority": 3.885e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -12839,32 +14261,41 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.md" }, "bedrock/ap-northeast-1/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3.6e-07, + "input_cost_per_token_batches": 1.8e-07, + "input_cost_per_token_flex": 1.8e-07, + "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_batches": 7.2e-07, + "output_cost_per_token_flex": 7.2e-07, + "output_cost_per_token_priority": 2.52e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/ap-northeast-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, + "input_cost_per_token_batches": 1.8e-07, + "input_cost_per_token_flex": 1.8e-07, + "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -12872,71 +14303,91 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "output_cost_per_token": 1.44e-06 + "output_cost_per_token": 1.44e-06, + "output_cost_per_token_batches": 7.2e-07, + "output_cost_per_token_flex": 7.2e-07, + "output_cost_per_token_priority": 2.52e-06 }, "bedrock/ap-northeast-1/moonshotai.kimi-k2-thinking": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "input_cost_per_token": 7.3e-07, + "input_cost_per_token_flex": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.03e-06, + "output_cost_per_token_flex": 1.52e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "supports_function_calling": true, "supports_reasoning": true }, "bedrock/ap-northeast-1/moonshotai.kimi-k2.5": { "input_cost_per_token": 7.2e-07, + "input_cost_per_token_batches": 3.6e-07, + "input_cost_per_token_flex": 3.6e-07, + "input_cost_per_token_priority": 1.26e-06, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.6e-06, + "output_cost_per_token_batches": 1.8e-06, + "output_cost_per_token_flex": 1.8e-06, + "output_cost_per_token_priority": 6.3e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/ap-northeast-1/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html", + "supports_audio_input": false, "supports_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_audio_input": false, - "supports_response_schema": true, - "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "supports_vision": false }, "bedrock/moonshotai.kimi-k2-thinking": { - "input_cost_per_token": 7.3e-07, + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, "mode": "chat", - "output_cost_per_token": 3.03e-06, + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_flex": 1.25e-06, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_reasoning": true }, "bedrock/moonshotai.kimi-k2.5": { "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, + "input_cost_per_token_priority": 1.05e-06, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, "mode": "chat", - "output_cost_per_token": 3.03e-06, - "source": "https://platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart", + "output_cost_per_token": 3e-06, + "output_cost_per_token_flex": 1.5e-06, + "output_cost_per_token_priority": 5.25e-06, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -12947,31 +14398,40 @@ "supports_response_schema": true }, "bedrock/ap-south-1/meta.llama3-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md", "input_cost_per_token": 3.18e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 4.2e-06 + "output_cost_per_token": 4.2e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/ap-south-1/meta.llama3-8b-instruct-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md", "input_cost_per_token": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 7.2e-07 + "output_cost_per_token": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/ap-south-1/deepseek.v3.2": { "input_cost_per_token": 7.4e-07, + "input_cost_per_token_batches": 3.7e-07, + "input_cost_per_token_flex": 3.7e-07, + "input_cost_per_token_priority": 1.295e-06, "litellm_provider": "bedrock", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_input_tokens": 156000, + "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.22e-06, + "output_cost_per_token_batches": 1.11e-06, + "output_cost_per_token_flex": 1.11e-06, + "output_cost_per_token_priority": 3.885e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -12979,32 +14439,41 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.md" }, "bedrock/ap-south-1/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3.6e-07, + "input_cost_per_token_batches": 1.8e-07, + "input_cost_per_token_flex": 1.8e-07, + "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_batches": 7.2e-07, + "output_cost_per_token_flex": 7.2e-07, + "output_cost_per_token_priority": 2.52e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/ap-south-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, + "input_cost_per_token_batches": 1.8e-07, + "input_cost_per_token_flex": 1.8e-07, + "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -13012,59 +14481,74 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "output_cost_per_token": 1.44e-06 + "output_cost_per_token": 1.44e-06, + "output_cost_per_token_batches": 7.2e-07, + "output_cost_per_token_flex": 7.2e-07, + "output_cost_per_token_priority": 2.52e-06 }, "bedrock/ap-south-1/moonshotai.kimi-k2-thinking": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "input_cost_per_token": 7.1e-07, + "input_cost_per_token_flex": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 2.94e-06, + "output_cost_per_token_flex": 1.47e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "supports_function_calling": true, "supports_reasoning": true }, "bedrock/ap-south-1/moonshotai.kimi-k2.5": { "input_cost_per_token": 7.2e-07, + "input_cost_per_token_batches": 3.6e-07, + "input_cost_per_token_flex": 3.6e-07, + "input_cost_per_token_priority": 1.26e-06, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.6e-06, + "output_cost_per_token_batches": 1.8e-06, + "output_cost_per_token_flex": 1.8e-06, + "output_cost_per_token_priority": 6.3e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/ap-south-1/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html", + "supports_audio_input": false, "supports_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_audio_input": false, - "supports_response_schema": true, - "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "supports_vision": false }, "bedrock/ap-southeast-2/minimax.minimax-m2.5": { "input_cost_per_token": 3.1e-07, + "input_cost_per_token_batches": 1.55e-07, + "input_cost_per_token_flex": 1.55e-07, + "input_cost_per_token_priority": 5.425e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -13072,116 +14556,135 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "output_cost_per_token": 1.24e-06 + "output_cost_per_token": 1.24e-06, + "output_cost_per_token_batches": 6.2e-07, + "output_cost_per_token_flex": 6.2e-07, + "output_cost_per_token_priority": 2.17e-06 }, "bedrock/ap-southeast-3/deepseek.v3.2": { "input_cost_per_token": 7.4e-07, + "input_cost_per_token_flex": 3.7e-07, "litellm_provider": "bedrock", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_input_tokens": 156000, + "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.22e-06, + "output_cost_per_token_flex": 1.11e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.md", + "supports_audio_input": false, "supports_function_calling": true, - "supports_reasoning": true, "supports_native_structured_output": true, - "supports_tool_choice": true, - "supports_audio_input": false, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "supports_tool_choice": true, + "supports_vision": false }, "bedrock/ap-southeast-3/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html", "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html", + "supports_audio_input": false, "supports_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_audio_input": false, - "supports_response_schema": true, - "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "supports_vision": false }, "bedrock/ap-southeast-3/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", + "supports_audio_input": false, "supports_function_calling": true, "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_audio_input": false, - "supports_response_schema": true, - "supports_vision": false, - "output_cost_per_token": 1.44e-06 + "supports_vision": false }, "bedrock/ap-southeast-3/moonshotai.kimi-k2.5": { "input_cost_per_token": 7.2e-07, + "input_cost_per_token_flex": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.6e-06, + "output_cost_per_token_flex": 1.8e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html", + "supports_audio_input": false, "supports_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_audio_input": false, - "supports_response_schema": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "supports_vision": true }, "bedrock/ap-southeast-3/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html", + "supports_audio_input": false, "supports_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_audio_input": false, - "supports_response_schema": true, - "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "supports_vision": false }, "bedrock/ca-central-1/meta.llama3-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md", "input_cost_per_token": 3.05e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 4.03e-06 + "output_cost_per_token": 4.03e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/ca-central-1/meta.llama3-8b-instruct-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md", "input_cost_per_token": 3.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 6.9e-07 + "output_cost_per_token": 6.9e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/eu-north-1/deepseek.v3.2": { "input_cost_per_token": 7.4e-07, + "input_cost_per_token_batches": 3.7e-07, + "input_cost_per_token_flex": 3.7e-07, + "input_cost_per_token_priority": 1.295e-06, "litellm_provider": "bedrock", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_input_tokens": 156000, + "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.22e-06, + "output_cost_per_token_batches": 1.11e-06, + "output_cost_per_token_flex": 1.11e-06, + "output_cost_per_token_priority": 3.885e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -13189,32 +14692,41 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.md" }, "bedrock/eu-north-1/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3.6e-07, + "input_cost_per_token_batches": 1.8e-07, + "input_cost_per_token_flex": 1.8e-07, + "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_batches": 7.2e-07, + "output_cost_per_token_flex": 7.2e-07, + "output_cost_per_token_priority": 2.52e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/eu-north-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, + "input_cost_per_token_batches": 1.8e-07, + "input_cost_per_token_flex": 1.8e-07, + "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -13222,23 +14734,31 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "output_cost_per_token": 1.44e-06 + "output_cost_per_token": 1.44e-06, + "output_cost_per_token_batches": 7.2e-07, + "output_cost_per_token_flex": 7.2e-07, + "output_cost_per_token_priority": 2.52e-06 }, "bedrock/eu-north-1/moonshotai.kimi-k2.5": { "input_cost_per_token": 7.2e-07, + "input_cost_per_token_batches": 3.6e-07, + "input_cost_per_token_flex": 3.6e-07, + "input_cost_per_token_priority": 1.26e-06, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.6e-06, + "output_cost_per_token_batches": 1.8e-06, + "output_cost_per_token_flex": 1.8e-06, + "output_cost_per_token_priority": 6.3e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/eu-central-1/1-month-commitment/anthropic.claude-instant-v1": { "cost_per_second": 0.01635, @@ -13246,7 +14766,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -13256,7 +14775,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2:1": { @@ -13265,7 +14783,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -13275,7 +14792,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -13285,7 +14801,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2:1": { @@ -13294,7 +14809,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -13303,7 +14817,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 8.38e-06, "supports_tool_choice": true @@ -13313,7 +14826,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05 }, @@ -13322,35 +14834,43 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true }, "bedrock/eu-central-1/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3.6e-07, + "input_cost_per_token_batches": 1.8e-07, + "input_cost_per_token_flex": 1.8e-07, + "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_batches": 7.2e-07, + "output_cost_per_token_flex": 7.2e-07, + "output_cost_per_token_priority": 2.52e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/eu-central-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, + "input_cost_per_token_batches": 1.8e-07, + "input_cost_per_token_flex": 1.8e-07, + "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -13358,66 +14878,83 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "output_cost_per_token": 1.44e-06 + "output_cost_per_token": 1.44e-06, + "output_cost_per_token_batches": 7.2e-07, + "output_cost_per_token_flex": 7.2e-07, + "output_cost_per_token_priority": 2.52e-06 }, "bedrock/eu-central-1/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html", + "supports_audio_input": false, "supports_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_audio_input": false, - "supports_response_schema": true, - "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "supports_vision": false }, "bedrock/eu-west-1/meta.llama3-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md", "input_cost_per_token": 2.86e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 3.78e-06 + "output_cost_per_token": 3.78e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/eu-west-1/meta.llama3-8b-instruct-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md", "input_cost_per_token": 3.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 6.5e-07 + "output_cost_per_token": 6.5e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/eu-west-1/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3.6e-07, + "input_cost_per_token_batches": 1.8e-07, + "input_cost_per_token_flex": 1.8e-07, + "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_batches": 7.2e-07, + "output_cost_per_token_flex": 7.2e-07, + "output_cost_per_token_priority": 2.52e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/eu-west-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, + "input_cost_per_token_batches": 1.8e-07, + "input_cost_per_token_flex": 1.8e-07, + "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -13425,66 +14962,83 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "output_cost_per_token": 1.44e-06 + "output_cost_per_token": 1.44e-06, + "output_cost_per_token_batches": 7.2e-07, + "output_cost_per_token_flex": 7.2e-07, + "output_cost_per_token_priority": 2.52e-06 }, "bedrock/eu-west-1/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html", + "supports_audio_input": false, "supports_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_audio_input": false, - "supports_response_schema": true, - "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "supports_vision": false }, "bedrock/eu-west-2/meta.llama3-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md", "input_cost_per_token": 3.45e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 4.55e-06 + "output_cost_per_token": 4.55e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/eu-west-2/meta.llama3-8b-instruct-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md", "input_cost_per_token": 3.9e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 7.8e-07 + "output_cost_per_token": 7.8e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/eu-west-2/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 4.7e-07, + "input_cost_per_token_batches": 2.35e-07, + "input_cost_per_token_flex": 2.35e-07, + "input_cost_per_token_priority": 8.225e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.86e-06, + "output_cost_per_token_batches": 9.3e-07, + "output_cost_per_token_flex": 9.3e-07, + "output_cost_per_token_priority": 3.255e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/eu-west-2/minimax.minimax-m2.5": { "input_cost_per_token": 4.7e-07, + "input_cost_per_token_batches": 2.35e-07, + "input_cost_per_token_flex": 2.35e-07, + "input_cost_per_token_priority": 8.225e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -13492,17 +15046,25 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "output_cost_per_token": 1.86e-06 + "output_cost_per_token": 1.86e-06, + "output_cost_per_token_batches": 9.3e-07, + "output_cost_per_token_flex": 9.3e-07, + "output_cost_per_token_priority": 3.255e-06 }, "bedrock/eu-west-2/nvidia.nemotron-super-3-120b": { "input_cost_per_token": 2.3e-07, + "input_cost_per_token_batches": 1.15e-07, + "input_cost_per_token_flex": 1.15e-07, + "input_cost_per_token_priority": 4.025e-07, "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.01e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 5.05e-07, + "output_cost_per_token_flex": 5.05e-07, + "output_cost_per_token_priority": 1.7675e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_reasoning": true, @@ -13513,106 +15075,118 @@ }, "bedrock/eu-west-2/qwen.qwen3-coder-next": { "input_cost_per_token": 7.8e-07, + "input_cost_per_token_batches": 3.9e-07, + "input_cost_per_token_flex": 3.9e-07, + "input_cost_per_token_priority": 1.365e-06, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.86e-06, + "output_cost_per_token_batches": 9.3e-07, + "output_cost_per_token_flex": 9.3e-07, + "output_cost_per_token_priority": 3.255e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", "input_cost_per_token": 2e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.6e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", "supports_tool_choice": true }, "bedrock/eu-west-3/mistral.mistral-large-2402-v1:0": { "input_cost_per_token": 5.2e-06, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.56e-05, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md", "supports_function_calling": true }, "bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", "input_cost_per_token": 5.9e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 9.1e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", "supports_tool_choice": true }, "bedrock/eu-south-1/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html", "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html", + "supports_audio_input": false, "supports_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_audio_input": false, - "supports_response_schema": true, - "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "supports_vision": false }, "bedrock/eu-south-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", + "supports_audio_input": false, "supports_function_calling": true, "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_audio_input": false, - "supports_response_schema": true, - "supports_vision": false, - "output_cost_per_token": 1.44e-06 + "supports_vision": false }, "bedrock/eu-south-1/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html", + "supports_audio_input": false, "supports_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_audio_input": false, - "supports_response_schema": true, - "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "supports_vision": false }, "bedrock/invoke/anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "metadata": { "notes": "Anthropic via Invoke route does not currently support pdf input." }, @@ -13626,31 +15200,40 @@ "cache_creation_input_token_cost": 3.75e-06 }, "bedrock/sa-east-1/meta.llama3-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md", "input_cost_per_token": 4.45e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 5.88e-06 + "output_cost_per_token": 5.88e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/sa-east-1/meta.llama3-8b-instruct-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md", "input_cost_per_token": 5e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.01e-06 + "output_cost_per_token": 1.01e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/sa-east-1/deepseek.v3.2": { "input_cost_per_token": 7.4e-07, + "input_cost_per_token_batches": 3.7e-07, + "input_cost_per_token_flex": 3.7e-07, + "input_cost_per_token_priority": 1.295e-06, "litellm_provider": "bedrock", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_input_tokens": 156000, + "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.22e-06, + "output_cost_per_token_batches": 1.11e-06, + "output_cost_per_token_flex": 1.11e-06, + "output_cost_per_token_priority": 3.885e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -13658,32 +15241,41 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.md" }, "bedrock/sa-east-1/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3.6e-07, + "input_cost_per_token_batches": 1.8e-07, + "input_cost_per_token_flex": 1.8e-07, + "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_batches": 7.2e-07, + "output_cost_per_token_flex": 7.2e-07, + "output_cost_per_token_priority": 2.52e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/sa-east-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, + "input_cost_per_token_batches": 1.8e-07, + "input_cost_per_token_flex": 1.8e-07, + "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -13691,50 +15283,63 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "output_cost_per_token": 1.44e-06 + "output_cost_per_token": 1.44e-06, + "output_cost_per_token_batches": 7.2e-07, + "output_cost_per_token_flex": 7.2e-07, + "output_cost_per_token_priority": 2.52e-06 }, "bedrock/sa-east-1/moonshotai.kimi-k2-thinking": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "input_cost_per_token": 7.3e-07, + "input_cost_per_token_flex": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.03e-06, + "output_cost_per_token_flex": 1.52e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "supports_function_calling": true, "supports_reasoning": true }, "bedrock/sa-east-1/moonshotai.kimi-k2.5": { "input_cost_per_token": 7.2e-07, + "input_cost_per_token_batches": 3.6e-07, + "input_cost_per_token_flex": 3.6e-07, + "input_cost_per_token_priority": 1.26e-06, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.6e-06, + "output_cost_per_token_batches": 1.8e-06, + "output_cost_per_token_flex": 1.8e-06, + "output_cost_per_token_priority": 6.3e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/sa-east-1/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html", + "supports_audio_input": false, "supports_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_audio_input": false, - "supports_response_schema": true, - "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "supports_vision": false }, "bedrock/us-east-1/1-month-commitment/anthropic.claude-instant-v1": { "cost_per_second": 0.011, @@ -13742,7 +15347,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -13752,7 +15356,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/us-east-1/1-month-commitment/anthropic.claude-v2:1": { @@ -13761,7 +15364,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -13771,7 +15373,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -13781,7 +15382,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/us-east-1/6-month-commitment/anthropic.claude-v2:1": { @@ -13790,7 +15390,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -13799,7 +15398,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-06, "supports_tool_choice": true @@ -13809,7 +15407,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true @@ -13819,68 +15416,79 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true }, "bedrock/us-east-1/meta.llama3-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md", "input_cost_per_token": 2.65e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 3.5e-06 + "output_cost_per_token": 3.5e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/us-east-1/meta.llama3-8b-instruct-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md", "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 6e-07 + "output_cost_per_token": 6e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", "supports_tool_choice": true }, "bedrock/us-east-1/mistral.mistral-large-2402-v1:0": { "input_cost_per_token": 4e-06, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.2e-05, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md", "supports_function_calling": true }, "bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", "input_cost_per_token": 4.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 7e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", "supports_tool_choice": true }, "bedrock/us-east-1/deepseek.v3.2": { "input_cost_per_token": 6.2e-07, + "input_cost_per_token_batches": 3.1e-07, + "input_cost_per_token_flex": 3.1e-07, + "input_cost_per_token_priority": 1.085e-06, "litellm_provider": "bedrock", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_input_tokens": 156000, + "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.85e-06, + "output_cost_per_token_batches": 9.25e-07, + "output_cost_per_token_flex": 9.25e-07, + "output_cost_per_token_priority": 3.2375e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -13888,91 +15496,122 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.md" }, "bedrock/us-east-1/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.2e-06, + "output_cost_per_token_batches": 6e-07, + "output_cost_per_token_flex": 6e-07, + "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-east-1/minimax.minimax-m2.5": { "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.25e-07, "output_cost_per_token": 1.2e-06, + "output_cost_per_token_flex": 6e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", + "output_cost_per_token_batches": 6e-07, + "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-east-1/moonshotai.kimi-k2-thinking": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_flex": 1.25e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "supports_function_calling": true, "supports_reasoning": true }, "bedrock/us-east-1/moonshotai.kimi-k2.5": { "input_cost_per_token": 6e-07, + "input_cost_per_token_batches": 3e-07, + "input_cost_per_token_flex": 3e-07, + "input_cost_per_token_priority": 1.05e-06, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 3e-06, + "output_cost_per_token_batches": 1.5e-06, + "output_cost_per_token_flex": 1.5e-06, + "output_cost_per_token_priority": 5.25e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-east-1/qwen.qwen3-coder-next": { "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "input_cost_per_token_flex": 2.5e-07, + "input_cost_per_token_priority": 8.75e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, + "output_cost_per_token_batches": 6e-07, + "output_cost_per_token_flex": 6e-07, + "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-east-2/deepseek.v3.2": { "input_cost_per_token": 6.2e-07, + "input_cost_per_token_batches": 3.1e-07, + "input_cost_per_token_flex": 3.1e-07, + "input_cost_per_token_priority": 1.085e-06, "litellm_provider": "bedrock", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_input_tokens": 156000, + "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.85e-06, + "output_cost_per_token_batches": 9.25e-07, + "output_cost_per_token_flex": 9.25e-07, + "output_cost_per_token_priority": 3.2375e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -13980,32 +15619,41 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.md" }, "bedrock/us-east-2/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.2e-06, + "output_cost_per_token_batches": 6e-07, + "output_cost_per_token_flex": 6e-07, + "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-east-2/minimax.minimax-m2.5": { "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -14013,50 +15661,63 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "output_cost_per_token": 1.2e-06 + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_batches": 6e-07, + "output_cost_per_token_flex": 6e-07, + "output_cost_per_token_priority": 2.1e-06 }, "bedrock/us-east-2/moonshotai.kimi-k2-thinking": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_flex": 1.25e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "supports_function_calling": true, "supports_reasoning": true }, "bedrock/us-east-2/moonshotai.kimi-k2.5": { "input_cost_per_token": 6e-07, + "input_cost_per_token_batches": 3e-07, + "input_cost_per_token_flex": 3e-07, + "input_cost_per_token_priority": 1.05e-06, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 3e-06, + "output_cost_per_token_batches": 1.5e-06, + "output_cost_per_token_flex": 1.5e-06, + "output_cost_per_token_priority": 5.25e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-east-2/qwen.qwen3-coder-next": { "input_cost_per_token": 5e-07, + "input_cost_per_token_flex": 2.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, + "output_cost_per_token_flex": 6e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html", + "supports_audio_input": false, "supports_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_audio_input": false, - "supports_response_schema": true, - "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "supports_vision": false }, "bedrock/us-gov-east-1/amazon.nova-pro-v1:0": { "cache_read_input_token_cost": 2.4e-07, @@ -14064,7 +15725,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.84e-06, "supports_function_calling": true, @@ -14078,16 +15738,14 @@ "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536 }, "bedrock/us-gov-east-1/amazon.titan-embed-text-v2:0": { - "input_cost_per_token": 2e-07, + "input_cost_per_token": 3e-08, "litellm_provider": "bedrock", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024 @@ -14097,7 +15755,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.7e-06 }, @@ -14106,7 +15763,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 4e-07 }, @@ -14115,7 +15771,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-06 }, @@ -14123,12 +15778,14 @@ "cache_creation_input_token_cost": 4.5e-06, "cache_creation_input_token_cost_above_1hr": 7.2e-06, "cache_read_input_token_cost": 3.6e-07, + "deprecation_date": "2027-04-27", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "bedrock/us-gov-east-1/anthropic.claude-sonnet-5-5", "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -14142,18 +15799,24 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "bedrock/us-gov-east-1/claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, "cache_creation_input_token_cost_above_1hr": 7.2e-06, "cache_read_input_token_cost": 3.6e-07, + "deprecation_date": "2027-04-27", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -14167,14 +15830,15 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md", + "token_count_model": {"model":"anthropic.claude-sonnet-4-5-20250929-v1:0","litellm_provider":"bedrock"} }, "bedrock/us-gov-east-1/meta.llama3-70b-instruct-v1:0": { "input_cost_per_token": 2.65e-06, "litellm_provider": "bedrock", "max_input_tokens": 8000, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 3.5e-06, "supports_pdf_input": true @@ -14184,7 +15848,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8000, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 2.65e-06, "supports_pdf_input": true @@ -14192,14 +15855,15 @@ "bedrock/us-gov-west-1/amazon.nova-2-multimodal-embeddings-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 8172, - "max_tokens": 8172, "mode": "embedding", "input_cost_per_token": 1.62e-07, "input_cost_per_image": 7.2e-05, "input_cost_per_video_per_second": 0.00084, "input_cost_per_audio_per_second": 0.000168, + "input_cost_per_token_batches": 8.1e-08, "output_cost_per_token": 0.0, "output_vector_size": 3072, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supports_embedding_image_input": true, "supports_image_input": true, "supports_video_input": true, @@ -14208,12 +15872,14 @@ "bedrock/us-gov-west-1/amazon.nova-lite-v1:0": { "cache_read_input_token_cost": 1.8e-08, "input_cost_per_token": 7.2e-08, + "input_cost_per_token_batches": 3.6e-08, "litellm_provider": "bedrock", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 2.88e-07, + "output_cost_per_token_batches": 1.44e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -14224,12 +15890,14 @@ "bedrock/us-gov-west-1/amazon.nova-micro-v1:0": { "cache_read_input_token_cost": 1.05e-08, "input_cost_per_token": 4.2e-08, + "input_cost_per_token_batches": 2.1e-08, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.68e-07, + "output_cost_per_token_batches": 8.4e-08, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, @@ -14237,13 +15905,21 @@ }, "bedrock/us-gov-west-1/amazon.nova-pro-v1:0": { "cache_read_input_token_cost": 2.4e-07, + "cache_read_input_token_cost_flex": 1.2e-07, + "cache_read_input_token_cost_priority": 4.2e-07, "input_cost_per_token": 9.6e-07, + "input_cost_per_token_batches": 4.8e-07, + "input_cost_per_token_flex": 4.8e-07, + "input_cost_per_token_priority": 1.68e-06, "litellm_provider": "bedrock", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.84e-06, + "output_cost_per_token_batches": 1.92e-06, + "output_cost_per_token_flex": 1.92e-06, + "output_cost_per_token_priority": 6.72e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -14255,35 +15931,31 @@ "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536 }, "bedrock/us-gov-west-1/amazon.titan-embed-text-v2:0": { - "input_cost_per_token": 2e-07, + "input_cost_per_token": 1.1e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024 }, "bedrock/us-gov-west-1/amazon.titan-text-express-v1": { - "input_cost_per_token": 1.3e-06, + "input_cost_per_token": 8e-07, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", - "output_cost_per_token": 1.7e-06 + "output_cost_per_token": 1.6e-06 }, "bedrock/us-gov-west-1/amazon.titan-text-lite-v1": { "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 4e-07 }, @@ -14292,7 +15964,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-06 }, @@ -14300,12 +15971,14 @@ "cache_creation_input_token_cost": 4.5e-06, "cache_creation_input_token_cost_above_1hr": 7.2e-06, "cache_read_input_token_cost": 3.6e-07, + "deprecation_date": "2027-04-27", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "bedrock/us-gov-west-1/anthropic.claude-sonnet-5-5", "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -14319,18 +15992,24 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "bedrock/us-gov-west-1/claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, "cache_creation_input_token_cost_above_1hr": 7.2e-06, "cache_read_input_token_cost": 3.6e-07, + "deprecation_date": "2027-04-27", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -14344,45 +16023,55 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md", + "token_count_model": {"model":"anthropic.claude-sonnet-4-5-20250929-v1:0","litellm_provider":"bedrock"} }, "bedrock/us-gov-west-1/meta.llama3-70b-instruct-v1:0": { + "deprecation_date": "2027-05-09", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 2.65e-06, "litellm_provider": "bedrock", "max_input_tokens": 8000, - "max_output_tokens": 2048, - "max_tokens": 2048, + "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 3.5e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md", "supports_pdf_input": true }, "bedrock/us-gov-west-1/meta.llama3-8b-instruct-v1:0": { + "deprecation_date": "2027-05-09", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 8000, - "max_output_tokens": 2048, - "max_tokens": 2048, + "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md", "supports_pdf_input": true }, "bedrock/us-west-1/meta.llama3-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md", "input_cost_per_token": 2.65e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 3.5e-06 + "output_cost_per_token": 3.5e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/us-west-1/meta.llama3-8b-instruct-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md", "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 6e-07 + "output_cost_per_token": 6e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/us-west-2/1-month-commitment/anthropic.claude-instant-v1": { "cost_per_second": 0.011, @@ -14390,7 +16079,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -14400,7 +16088,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/us-west-2/1-month-commitment/anthropic.claude-v2:1": { @@ -14409,7 +16096,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -14419,7 +16105,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -14429,7 +16114,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/us-west-2/6-month-commitment/anthropic.claude-v2:1": { @@ -14438,7 +16122,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -14447,7 +16130,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-06, "supports_tool_choice": true @@ -14457,7 +16139,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true @@ -14467,50 +16148,57 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true }, "bedrock/us-west-2/mistral.mistral-7b-instruct-v0:2": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", "supports_tool_choice": true }, "bedrock/us-west-2/mistral.mistral-large-2402-v1:0": { "input_cost_per_token": 4e-06, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.2e-05, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md", "supports_function_calling": true }, "bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", "input_cost_per_token": 4.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 7e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", "supports_tool_choice": true }, "bedrock/us-west-2/deepseek.v3.2": { "input_cost_per_token": 6.2e-07, + "input_cost_per_token_batches": 3.1e-07, + "input_cost_per_token_flex": 3.1e-07, + "input_cost_per_token_priority": 1.085e-06, "litellm_provider": "bedrock", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_input_tokens": 156000, + "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.85e-06, + "output_cost_per_token_batches": 9.25e-07, + "output_cost_per_token_flex": 9.25e-07, + "output_cost_per_token_priority": 3.2375e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -14518,82 +16206,104 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.md" }, "bedrock/us-west-2/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.2e-06, + "output_cost_per_token_batches": 6e-07, + "output_cost_per_token_flex": 6e-07, + "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-west-2/minimax.minimax-m2.5": { "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.25e-07, "output_cost_per_token": 1.2e-06, + "output_cost_per_token_flex": 6e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", + "output_cost_per_token_batches": 6e-07, + "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-west-2/moonshotai.kimi-k2-thinking": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_flex": 1.25e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "supports_function_calling": true, "supports_reasoning": true }, "bedrock/us-west-2/moonshotai.kimi-k2.5": { "input_cost_per_token": 6e-07, + "input_cost_per_token_batches": 3e-07, + "input_cost_per_token_flex": 3e-07, + "input_cost_per_token_priority": 1.05e-06, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 3e-06, + "output_cost_per_token_batches": 1.5e-06, + "output_cost_per_token_flex": 1.5e-06, + "output_cost_per_token_priority": 5.25e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-west-2/qwen.qwen3-coder-next": { "input_cost_per_token": 5e-07, + "input_cost_per_token_flex": 2.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, + "output_cost_per_token_flex": 6e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html", + "supports_audio_input": false, "supports_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_audio_input": false, - "supports_response_schema": true, - "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "supports_vision": false }, "bedrock/us.anthropic.claude-3-5-haiku-20241022-v1:0": { "cache_creation_input_token_cost": 1e-06, @@ -14602,7 +16312,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-06, "supports_assistant_prefill": true, @@ -14687,34 +16396,43 @@ "/v1/images/generations" ] }, - "cerebras/llama-3.3-70b": { - "input_cost_per_token": 8.5e-07, + "cerebras/llama-3.1-70b": { + "input_cost_per_token": 6e-07, "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.2e-06, + "output_cost_per_token": 6e-07, "supports_function_calling": true, "supports_tool_choice": true }, - "cerebras/llama3.1-70b": { - "input_cost_per_token": 6e-07, + "cerebras/llama-3.1-8b": { + "input_cost_per_token": 1e-07, "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 6e-07, + "output_cost_per_token": 1e-07, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "cerebras/llama-3.3-70b": { + "deprecation_date": "2026-02-16", + "input_cost_per_token": 8.5e-07, + "litellm_provider": "cerebras", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, "supports_function_calling": true, "supports_tool_choice": true }, "cerebras/llama3.1-8b": { + "deprecation_date": "2026-05-27", "input_cost_per_token": 1e-07, "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-07, "supports_function_calling": true, @@ -14725,7 +16443,6 @@ "litellm_provider": "cerebras", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.5e-07, "source": "https://www.cerebras.ai/blog/openai-gpt-oss-120b-runs-fastest-on-cerebras", @@ -14736,11 +16453,11 @@ "supports_tool_choice": true }, "cerebras/qwen-3-32b": { + "deprecation_date": "2026-02-16", "input_cost_per_token": 4e-07, "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 8e-07, "source": "https://inference-docs.cerebras.ai/support/pricing", @@ -14753,7 +16470,6 @@ "litellm_provider": "cerebras", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.49e-06, "source": "https://api.cerebras.ai/public/v1/models/qwen-3.8-27b", @@ -14769,7 +16485,6 @@ "litellm_provider": "nlp_cloud", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 5e-07 }, @@ -14785,10 +16500,13 @@ "/v1/audio/transcriptions" ], "deprecation_date": "2027-02-26", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-live-transcribe", "input_cost_per_second": 0.0001, "source": "https://developers.openai.com/api/docs/pricing" }, "claude-haiku-4-5-20251001": { + "supports_web_search": true, "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, "cache_creation_input_token_cost_batches": 6.25e-07, @@ -14799,7 +16517,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, @@ -14826,7 +16543,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, @@ -14846,26 +16562,19 @@ "claude-sonnet-4-5": { "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_creation_input_token_cost_above_200k_tokens_batches": 3.75e-06, "cache_creation_input_token_cost_batches": 1.875e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "cache_read_input_token_cost_above_200k_tokens_batches": 3e-07, "cache_read_input_token_cost_batches": 1.5e-07, - "input_cost_per_token_above_200k_tokens_batches": 3e-06, + "deprecation_date": "2026-11-30", + "deprecation_source": "https://platform.claude.com/docs/en/about-claude/model-deprecations", + "successor_model": "claude-sonnet-5-5", "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "anthropic", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, - "output_cost_per_token_above_200k_tokens_batches": 1.125e-05, "output_cost_per_token_batches": 7.5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -14888,26 +16597,19 @@ "claude-sonnet-4-5-20250929": { "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_creation_input_token_cost_above_200k_tokens_batches": 3.75e-06, "cache_creation_input_token_cost_batches": 1.875e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "cache_read_input_token_cost_above_200k_tokens_batches": 3e-07, "cache_read_input_token_cost_batches": 1.5e-07, - "input_cost_per_token_above_200k_tokens_batches": 3e-06, + "deprecation_date": "2026-11-30", + "deprecation_source": "https://platform.claude.com/docs/en/about-claude/model-deprecations", + "successor_model": "claude-sonnet-5-5", "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "anthropic", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, - "output_cost_per_token_above_200k_tokens_batches": 1.125e-05, "output_cost_per_token_batches": 7.5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -14929,6 +16631,7 @@ "source": "https://docs.anthropic.com/en/docs/about-claude/pricing" }, "claude-sonnet-5": { + "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_1hr": 4e-06, @@ -14940,7 +16643,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -14950,6 +16652,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -14977,14 +16680,13 @@ "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_1hr": 4e-06, "cache_creation_input_token_cost_batches": 1.25e-06, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_batches": 1e-07, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -15015,10 +16717,14 @@ "supports_forced_tool_use": false, "thinking_always_on": true, "prompt_cache_min_tokens": 512, - "source": "https://platform.claude.com/docs/en/models/sonnet-5-5/overview", + "source": "https://platform.claude.com/docs/en/about-claude/pricing", "supports_web_search": true }, + "claude-sonnet-latest": { + "alias_of": "claude-sonnet-5-5" + }, "claude-sonnet-4-6": { + "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, @@ -15030,7 +16736,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, @@ -15041,7 +16746,7 @@ }, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -15070,11 +16775,12 @@ "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "deprecation_date": "2027-04-08", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md", "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -15089,9 +16795,12 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.5e-06, - "output_cost_per_token_batches": 7.5e-06 + "output_cost_per_token_batches": 7.5e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md", + "token_count_model": {"model":"anthropic.claude-sonnet-4-5-20250929-v1:0","litellm_provider":"bedrock"} }, "claude-opus-4-5-20251101": { + "supports_web_search": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, @@ -15102,7 +16811,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -15136,7 +16844,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -15161,6 +16868,7 @@ "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-opus-4-6": { + "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, @@ -15172,7 +16880,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -15215,7 +16922,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -15246,6 +16952,7 @@ "prompt_cache_min_tokens": 4096 }, "claude-opus-4-7": { + "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, @@ -15257,7 +16964,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -15285,7 +16991,6 @@ "us": 1.1 }, "supports_output_config": true, - "supports_speed": true, "prompt_cache_min_tokens": 2048, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, @@ -15301,7 +17006,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -15329,10 +17033,10 @@ "us": 1.1 }, "supports_output_config": true, - "supports_speed": true, "prompt_cache_min_tokens": 2048 }, "claude-fable-5": { + "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, @@ -15344,7 +17048,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, @@ -15377,6 +17080,7 @@ "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-fable-5-1": { + "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, @@ -15388,7 +17092,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, @@ -15421,7 +17124,11 @@ "supports_native_structured_output": true, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, + "claude-fable-latest": { + "alias_of": "claude-fable-5-2" + }, "claude-opus-5-5": { + "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 5e-06, "cache_creation_input_token_cost_above_1hr": 8e-06, @@ -15433,7 +17140,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_batches": 1e-05, @@ -15459,7 +17165,56 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, + "provider_specific_entry": {"us":1.1,"fast":2}, + "supports_output_config": true, + "supports_speed": true, + "supports_fast_mode": true, + "prompt_cache_min_tokens": 512, + "source": "https://platform.claude.com/docs/en/about-claude/pricing" + }, + "claude-opus-latest": { + "alias_of": "claude-opus-5-5" + }, + "claude-opus-5": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, + "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_on_by_default": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, "provider_specific_entry": { + "us": 1.1, "fast": 2.0 }, "supports_output_config": true, @@ -15468,7 +17223,8 @@ "prompt_cache_min_tokens": 512, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, - "claude-opus-5": { + "claude-opus-4-8": { + "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, @@ -15480,54 +17236,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.5e-05, - "output_cost_per_token_batches": 1.25e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_adaptive_thinking": true, - "supports_mid_conversation_system": true, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_thinking_cache_preservation": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_native_structured_output": true, - "supports_sampling_params": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_max_reasoning_effort": true, - "provider_specific_entry": { - "us": 1.1, - "fast": 2.0 - }, - "supports_output_config": true, - "supports_speed": true, - "supports_fast_mode": true, - "prompt_cache_min_tokens": 512, - "source": "https://platform.claude.com/docs/en/about-claude/pricing" - }, - "claude-opus-4-8": { - "supports_anthropic_compaction": true, - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "cache_creation_input_token_cost_batches": 3.125e-06, - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_batches": 2.5e-07, - "input_cost_per_token": 5e-06, - "input_cost_per_token_batches": 2.5e-06, - "litellm_provider": "anthropic", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -15562,12 +17270,87 @@ "prompt_cache_min_tokens": 1024, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, + "cloudflare/clef-omni": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "cloudflare", + "max_input_tokens": 64000, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://developers.cloudflare.com/workers-ai/models/clef-omni/", + "supports_audio_input": true, + "supports_video_input": true, + "supports_vision": true + }, + "cloudflare/@cf/cloudflare/clef-omni": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "cloudflare", + "max_input_tokens": 64000, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://developers.cloudflare.com/workers-ai/models/clef-omni/", + "supports_audio_input": true, + "supports_video_input": true, + "supports_vision": true + }, + "cloudflare/clef": { + "input_cost_per_token": 2.4e-07, + "litellm_provider": "cloudflare", + "max_input_tokens": 65536, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/", + "supports_vision": true + }, + "cloudflare/clef-flash": { + "input_cost_per_token": 9e-08, + "litellm_provider": "cloudflare", + "max_input_tokens": 65536, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/", + "supports_vision": true + }, + "cloudflare/@cf/cloudflare/clef": { + "input_cost_per_token": 2.4e-07, + "litellm_provider": "cloudflare", + "max_input_tokens": 65536, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/", + "supports_vision": true + }, + "cloudflare/@cf/cloudflare/clef-flash": { + "input_cost_per_token": 9e-08, + "litellm_provider": "cloudflare", + "max_input_tokens": 65536, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/", + "supports_vision": true + }, + "cloudflare/clairic": { + "input_cost_per_token": 1e-07, + "litellm_provider": "cloudflare", + "max_input_tokens": 65536, + "mode": "extraction", + "output_cost_per_token": 0.0, + "source": "https://developers.cloudflare.com/workers-ai/models/clairic/", + "supports_vision": true + }, + "cloudflare/@cf/cloudflare/clairic": { + "input_cost_per_token": 1e-07, + "litellm_provider": "cloudflare", + "max_input_tokens": 65536, + "mode": "extraction", + "output_cost_per_token": 0.0, + "source": "https://developers.cloudflare.com/workers-ai/models/clairic/", + "supports_vision": true + }, "cloudflare/@cf/meta/llama-2-7b-chat-fp16": { "input_cost_per_token": 1.923e-06, "litellm_provider": "cloudflare", "max_input_tokens": 3072, "max_output_tokens": 3072, - "max_tokens": 3072, "mode": "chat", "output_cost_per_token": 1.923e-06, "rpm": 300 @@ -15577,7 +17360,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 2048, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 1.923e-06, "rpm": 300 @@ -15587,7 +17369,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.923e-06, "rpm": 300 @@ -15597,7 +17378,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.923e-06, "rpm": 300 @@ -15607,7 +17387,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 7.5e-07, "rpm": 300, @@ -15619,7 +17398,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "rpm": 300 @@ -15629,7 +17407,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 80000, "max_output_tokens": 80000, - "max_tokens": 80000, "mode": "chat", "output_cost_per_token": 3.35e-07, "rpm": 300 @@ -15639,7 +17416,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-08, "rpm": 300 @@ -15649,7 +17425,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 15000, "max_output_tokens": 15000, - "max_tokens": 15000, "mode": "chat", "output_cost_per_token": 0.0, "rpm": 300 @@ -15660,7 +17435,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "rpm": 20, @@ -15672,7 +17446,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 80000, "max_output_tokens": 80000, - "max_tokens": 80000, "mode": "chat", "output_cost_per_token": 4.881e-06, "rpm": 300, @@ -15683,7 +17456,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.87e-07, "rpm": 300 @@ -15693,7 +17465,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 60000, "max_output_tokens": 60000, - "max_tokens": 60000, "mode": "chat", "output_cost_per_token": 2.01e-07, "rpm": 300 @@ -15704,7 +17475,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "rpm": 20, @@ -15716,7 +17486,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-07, "rpm": 300, @@ -15728,7 +17497,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "rpm": 300 @@ -15738,7 +17506,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 24000, "max_output_tokens": 24000, - "max_tokens": 24000, "mode": "chat", "output_cost_per_token": 2.253e-06, "rpm": 300, @@ -15749,7 +17516,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 131000, "max_output_tokens": 131000, - "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 1.12e-07, "rpm": 300, @@ -15760,7 +17526,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1e-06, "rpm": 300 @@ -15771,7 +17536,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, "rpm": 20, @@ -15783,7 +17547,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 1.5e-06, "rpm": 300, @@ -15795,7 +17558,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.55e-07, "rpm": 300 @@ -15805,7 +17567,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3.35e-07, "rpm": 300, @@ -15817,7 +17578,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 3500, "max_output_tokens": 3500, - "max_tokens": 3500, "mode": "chat", "output_cost_per_token": 0.0, "rpm": 300 @@ -15827,7 +17587,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 3e-07, "rpm": 300, @@ -15839,7 +17598,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.55e-07, "rpm": 300, @@ -15850,7 +17608,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6.76e-07, "rpm": 300, @@ -15861,7 +17618,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-07, "rpm": 300, @@ -15873,7 +17629,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 131000, "max_output_tokens": 131000, - "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 8.5e-07, "rpm": 300, @@ -15884,18 +17639,18 @@ "litellm_provider": "cloudflare", "max_input_tokens": 24000, "max_output_tokens": 24000, - "max_tokens": 24000, "mode": "chat", "output_cost_per_token": 1e-06, "rpm": 300, "supports_reasoning": true }, "codestral/codestral-2405": { + "deprecation_date": "2025-06-16", + "deprecation_source": "https://docs.mistral.ai/getting-started/models/", "input_cost_per_token": 0.0, "litellm_provider": "codestral", "max_input_tokens": 32000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://docs.mistral.ai/capabilities/code_generation/", @@ -15907,7 +17662,6 @@ "litellm_provider": "codestral", "max_input_tokens": 32000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://docs.mistral.ai/capabilities/code_generation/", @@ -15919,7 +17673,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -15930,7 +17683,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -15940,7 +17692,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -15950,7 +17701,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -15960,7 +17710,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536, @@ -15971,7 +17720,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536, @@ -15982,7 +17730,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536, @@ -15993,7 +17740,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "cohere", "max_input_tokens": 128000, - "max_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536, @@ -16001,6 +17747,26 @@ "input_cost_per_image_token": 4.7e-07, "source": "https://cohere.com/pricing" }, + "cohere/embed-v5.0-pro": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "cohere", + "max_input_tokens": 128000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 2048, + "supports_embedding_image_input": true, + "source": "https://cohere.com/pricing" + }, + "cohere/embed-v5.0-fast": { + "input_cost_per_token": 8e-08, + "litellm_provider": "cohere", + "max_input_tokens": 128000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 2048, + "supports_embedding_image_input": true, + "source": "https://cohere.com/pricing" + }, "cohere/parse-v5.0": { "litellm_provider": "cohere", "mode": "ocr", @@ -16014,18 +17780,17 @@ "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, "litellm_provider": "bedrock", - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "max_input_tokens": 4096, + "max_output_tokens": 4096, "mode": "rerank", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-cohere-rerank-3-5.md" }, "command-a-03-2025": { "input_cost_per_token": 2.5e-06, "litellm_provider": "cohere_chat", "max_input_tokens": 256000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, @@ -16037,7 +17802,6 @@ "litellm_provider": "cohere_chat", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "source": "https://docs.cohere.com/docs/models" }, @@ -16046,7 +17810,6 @@ "litellm_provider": "cohere_chat", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://docs.cohere.com/docs/command-a-plus", @@ -16061,7 +17824,6 @@ "litellm_provider": "cohere", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 2e-06 }, @@ -16070,7 +17832,6 @@ "litellm_provider": "cohere_chat", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -16081,7 +17842,6 @@ "litellm_provider": "cohere_chat", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, @@ -16092,22 +17852,161 @@ "litellm_provider": "cohere_chat", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://docs.cohere.com/v2/docs/command-r7b", "supports_function_calling": true, "supports_tool_choice": true }, + "coralbricks/glm-5.3-fast": { + "cache_creation_input_token_cost": 1.68e-06, + "cache_read_input_token_cost": 0.0, + "input_cost_per_token": 1.12e-06, + "litellm_provider": "coralbricks", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://www.coralbricks.ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "coralbricks/glm-5.3-fp4": { + "cache_creation_input_token_cost": 1.68e-06, + "cache_read_input_token_cost": 0.0, + "input_cost_per_token": 1.12e-06, + "litellm_provider": "coralbricks", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://www.coralbricks.ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "coralbricks/glm-5.3": { + "cache_creation_input_token_cost": 1.68e-06, + "cache_read_input_token_cost": 0.0, + "input_cost_per_token": 1.12e-06, + "litellm_provider": "coralbricks", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://www.coralbricks.ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "coralbricks/deepseek-v4.1-flash-fast": { + "cache_creation_input_token_cost": 9e-08, + "cache_read_input_token_cost": 0.0, + "input_cost_per_token": 1e-08, + "litellm_provider": "coralbricks", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.coralbricks.ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "coralbricks/deepseek-v4.1-flash-fast-fp4": { + "cache_creation_input_token_cost": 9e-08, + "cache_read_input_token_cost": 0.0, + "input_cost_per_token": 1e-08, + "litellm_provider": "coralbricks", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.coralbricks.ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "coralbricks/deepseek-v4.1-flash": { + "cache_creation_input_token_cost": 9e-08, + "cache_read_input_token_cost": 0.0, + "input_cost_per_token": 1e-08, + "litellm_provider": "coralbricks", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.coralbricks.ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "computer-use-preview": { "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 3e-06, "litellm_provider": "openai", "max_input_tokens": 8192, "max_output_tokens": 1024, - "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 1.2e-05, + "fedramp_uplift_multiplier": 1.1, "supported_endpoints": [ "/v1/responses" ], @@ -16129,13 +18028,46 @@ "supports_vision": true, "source": "https://platform.openai.com/docs/models/computer-use-preview" }, + "computer-use-preview-2025-03-11": { + "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", + "input_cost_per_token": 3e-06, + "litellm_provider": "openai", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "fedramp_uplift_multiplier": 1.1, + "supported_endpoints": [ + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "source": "https://developers.openai.com/api/docs/models/computer-use-preview" + }, "deepseek-chat": { "cache_read_input_token_cost": 2.8e-08, + "deprecation_date": "2026-07-24", + "deprecation_source": "https://api-docs.deepseek.com/updates", "input_cost_per_token": 2.8e-07, "litellm_provider": "deepseek", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.2e-07, "source": "https://api-docs.deepseek.com/quick_start/pricing", @@ -16152,11 +18084,12 @@ }, "deepseek-reasoner": { "cache_read_input_token_cost": 2.8e-08, + "deprecation_date": "2026-07-24", + "deprecation_source": "https://api-docs.deepseek.com/updates", "input_cost_per_token": 2.8e-07, "litellm_provider": "deepseek", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.2e-07, "source": "https://api-docs.deepseek.com/quick_start/pricing", @@ -16178,7 +18111,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -16194,7 +18126,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -16210,7 +18141,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4.8e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -16226,7 +18156,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 202745, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -16242,7 +18171,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -16258,7 +18186,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 229376, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -16274,7 +18201,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -16286,7 +18212,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -16315,7 +18240,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -16345,7 +18269,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 30720, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -16358,7 +18281,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -16371,7 +18293,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -16384,7 +18305,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, @@ -16398,7 +18318,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, @@ -16411,7 +18330,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -16442,7 +18360,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -16473,7 +18390,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -16505,7 +18421,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -16519,7 +18434,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -16532,7 +18446,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -16546,7 +18459,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -16559,7 +18471,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -16570,7 +18481,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -16619,7 +18529,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -16664,7 +18573,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -16713,7 +18621,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -16758,7 +18665,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -16795,7 +18701,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -16832,7 +18737,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -16870,7 +18774,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -16882,7 +18785,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -16895,7 +18797,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -16908,7 +18809,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -16922,7 +18822,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.4e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -16935,7 +18834,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.87e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -16948,7 +18846,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 260096, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -16986,7 +18883,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17013,12 +18909,13 @@ ] }, "dashscope/qwen3.7-max": { + "cache_creation_input_token_cost": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "explicit_cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 2.5e-06, "litellm_provider": "dashscope", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 7.5e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17032,7 +18929,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17068,7 +18964,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 991808, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17079,6 +18974,9 @@ "supports_tool_choice": true, "supports_vision": true }, + "dashscope/qwen-max-latest": { + "alias_of": "dashscope/qwen3.8-max" + }, "dashscope/qwen3.8-flash": { "cache_creation_input_token_cost": 2e-07, "cache_read_input_token_cost": 1.6e-08, @@ -17086,7 +18984,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 991808, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.7e-07, "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", @@ -17099,13 +18996,15 @@ "supports_vision": true, "supports_web_search": true }, + "dashscope/qwen-flash-latest": { + "alias_of": "dashscope/qwen3.8-flash" + }, "dashscope/qwen3.8-omni-flash": { "cache_read_input_token_cost": 1.6e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "dashscope", "max_input_tokens": 991808, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.7e-07, "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", @@ -17124,7 +19023,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 98304, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17135,25 +19033,31 @@ "dashscope/qwen-image-2.0": { "litellm_provider": "dashscope", "mode": "image_generation", - "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "output_cost_per_image": 0.035, + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supported_endpoints": [ - "/v1/images/generations" + "/v1/images/generations", + "/v1/images/edits" ] }, "dashscope/qwen-image-2.0-pro": { "litellm_provider": "dashscope", "mode": "image_generation", - "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "output_cost_per_image": 0.075, + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supported_endpoints": [ - "/v1/images/generations" + "/v1/images/generations", + "/v1/images/edits" ] }, "dashscope/qwen-image-3.0": { "litellm_provider": "dashscope", "mode": "image_generation", - "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "output_cost_per_image": 0.03, + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supported_endpoints": [ - "/v1/images/generations" + "/v1/images/generations", + "/v1/images/edits" ] }, "dashscope/qwen-image-3.0-pro": { @@ -17161,16 +19065,337 @@ "mode": "image_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supported_endpoints": [ - "/v1/images/generations" + "/v1/images/generations", + "/v1/images/edits" + ] + }, + "dashscope/qwen3-tts-flash": { + "input_cost_per_character": 1e-05, + "litellm_provider": "dashscope", + "mode": "audio_speech", + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "dashscope/qwen-audio-3.1-tts-flash": { + "input_cost_per_token": 2.3e-07, + "output_cost_per_token": 1.87e-06, + "litellm_provider": "dashscope", + "mode": "audio_speech", + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "dashscope/qwen-audio-3.1-tts-plus": { + "input_cost_per_character": 3e-05, + "litellm_provider": "dashscope", + "mode": "audio_speech", + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "dashscope/qwen-audio-3.0-tts-plus": { + "input_cost_per_character": 2e-05, + "litellm_provider": "dashscope", + "mode": "audio_speech", + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "dashscope/qwen-audio-3.0-tts-flash": { + "input_cost_per_character": 1.5e-05, + "litellm_provider": "dashscope", + "mode": "audio_speech", + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", + "supported_endpoints": [ + "/v1/audio/speech" ] }, + "dashscope/wan3.0-video": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video", + "output_cost_per_second": 0.165025, + "output_cost_per_second_480p": 0.041256, + "output_cost_per_second_720p": 0.082513, + "output_cost_per_second_1080p": 0.165025, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 3.0 all-in-one video generation (text, first/last frame, multimodal reference, edit, extend). Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/wan3.0-video-prime": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video-prime", + "output_cost_per_second": 0.254399, + "output_cost_per_second_480p": 0.0636, + "output_cost_per_second_720p": 0.127199, + "output_cost_per_second_1080p": 0.254399, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 3.0 fast tier. Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/happyhorse-1.1-t2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-t2v", + "output_cost_per_second": 0.165026, + "output_cost_per_second_480p": 0.0618845, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.165026, + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.1 text-to-video. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/happyhorse-1.1-i2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-i2v", + "output_cost_per_second": 0.165026, + "output_cost_per_second_480p": 0.0618845, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.165026, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.1 image-to-video from a first frame. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/happyhorse-1.1-r2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-r2v", + "output_cost_per_second": 0.165026, + "output_cost_per_second_480p": 0.0618845, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.165026, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "HappyHorse 1.1 reference-to-video, 1 to 9 reference images. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/happyhorse-1.0-t2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-t2v", + "output_cost_per_second": 0.220034, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.220034, + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.0 text-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/happyhorse-1.0-i2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-i2v", + "output_cost_per_second": 0.220034, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.220034, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.0 image-to-video from a first frame. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/happyhorse-1.0-r2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-r2v", + "output_cost_per_second": 0.220034, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.220034, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "HappyHorse 1.0 reference-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/wan2.7-t2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-t2v", + "output_cost_per_second": 0.143353, + "output_cost_per_second_720p": 0.086012, + "output_cost_per_second_1080p": 0.143353, + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 2.7 text-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/wan2.7-i2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-i2v", + "output_cost_per_second": 0.143353, + "output_cost_per_second_720p": 0.086012, + "output_cost_per_second_1080p": 0.143353, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 2.7 image-to-video (first frame, first and last frame, continuation). No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/wan2.7-r2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-r2v", + "output_cost_per_second": 0.143353, + "output_cost_per_second_720p": 0.086012, + "output_cost_per_second_1080p": 0.143353, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "Wan 2.7 reference-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, "qwencloud/deepseek-v4-flash": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 2e-07, "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.qwencloud.com/models", @@ -17186,7 +19411,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.qwencloud.com/models", @@ -17202,7 +19426,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4.8e-06, "source": "https://www.qwencloud.com/models", @@ -17218,7 +19441,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 202745, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.qwencloud.com/models", @@ -17234,7 +19456,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.qwencloud.com/models", @@ -17250,7 +19471,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 229376, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.qwencloud.com/models", @@ -17266,7 +19486,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://www.qwencloud.com/models", @@ -17278,7 +19497,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -17307,7 +19525,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -17337,7 +19554,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 30720, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.4e-06, "source": "https://www.qwencloud.com/models", @@ -17350,7 +19566,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.qwencloud.com/models", @@ -17363,7 +19578,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 129024, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.qwencloud.com/models", @@ -17376,7 +19590,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, @@ -17390,7 +19603,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, @@ -17403,7 +19615,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -17434,7 +19645,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -17465,7 +19675,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -17497,7 +19706,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -17511,7 +19719,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://www.qwencloud.com/models", @@ -17524,7 +19731,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -17538,7 +19744,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -17551,7 +19756,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -17562,7 +19766,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -17611,7 +19814,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -17656,7 +19858,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -17705,7 +19906,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -17750,7 +19950,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -17787,7 +19986,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -17824,7 +20022,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -17862,7 +20059,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.qwencloud.com/models", @@ -17874,7 +20070,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.qwencloud.com/models", @@ -17887,7 +20082,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://www.qwencloud.com/models", @@ -17900,7 +20094,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.qwencloud.com/models", @@ -17914,7 +20107,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.4e-07, "source": "https://www.qwencloud.com/models", @@ -17927,7 +20119,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.87e-06, "source": "https://www.qwencloud.com/models", @@ -17940,7 +20131,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 260096, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -17978,7 +20168,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -18005,12 +20194,13 @@ ] }, "qwencloud/qwen3.7-max": { + "cache_creation_input_token_cost": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "explicit_cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 2.5e-06, "litellm_provider": "qwencloud", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 7.5e-06, "source": "https://www.qwencloud.com/models", @@ -18024,7 +20214,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -18060,7 +20249,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 991808, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://www.qwencloud.com/models", @@ -18076,7 +20264,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 98304, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://www.qwencloud.com/models", @@ -18116,13 +20303,287 @@ "/v1/images/generations" ] }, + "qwencloud/wan3.0-video": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video", + "output_cost_per_second": 0.2, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.1, + "output_cost_per_second_1080p": 0.2, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 3.0 all-in-one video generation (text, first/last frame, multimodal reference, edit, extend). Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/wan3.0-video-prime": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video-prime", + "output_cost_per_second": 0.28, + "output_cost_per_second_480p": 0.068, + "output_cost_per_second_720p": 0.14, + "output_cost_per_second_1080p": 0.28, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 3.0 fast tier. Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/happyhorse-1.1-t2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-t2v", + "output_cost_per_second": 0.18, + "output_cost_per_second_480p": 0.07, + "output_cost_per_second_720p": 0.14, + "output_cost_per_second_1080p": 0.18, + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.1 text-to-video. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/happyhorse-1.1-i2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-i2v", + "output_cost_per_second": 0.18, + "output_cost_per_second_480p": 0.07, + "output_cost_per_second_720p": 0.14, + "output_cost_per_second_1080p": 0.18, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.1 image-to-video from a first frame. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/happyhorse-1.1-r2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-r2v", + "output_cost_per_second": 0.18, + "output_cost_per_second_480p": 0.07, + "output_cost_per_second_720p": 0.14, + "output_cost_per_second_1080p": 0.18, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "HappyHorse 1.1 reference-to-video, 1 to 9 reference images. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/happyhorse-1.0-t2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-t2v", + "output_cost_per_second": 0.24, + "output_cost_per_second_720p": 0.14, + "output_cost_per_second_1080p": 0.24, + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.0 text-to-video. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/happyhorse-1.0-i2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-i2v", + "output_cost_per_second": 0.24, + "output_cost_per_second_720p": 0.14, + "output_cost_per_second_1080p": 0.24, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.0 image-to-video from a first frame. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/happyhorse-1.0-r2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-r2v", + "output_cost_per_second": 0.24, + "output_cost_per_second_720p": 0.14, + "output_cost_per_second_1080p": 0.24, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "HappyHorse 1.0 reference-to-video. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/wan2.7-t2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-t2v", + "output_cost_per_second": 0.15, + "output_cost_per_second_720p": 0.1, + "output_cost_per_second_1080p": 0.15, + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 2.7 text-to-video. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/wan2.7-i2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-i2v", + "output_cost_per_second": 0.15, + "output_cost_per_second_720p": 0.1, + "output_cost_per_second_1080p": 0.15, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 2.7 image-to-video (first frame, first and last frame, continuation). No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/wan2.7-r2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-r2v", + "output_cost_per_second": 0.15, + "output_cost_per_second_720p": 0.1, + "output_cost_per_second_1080p": 0.15, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "Wan 2.7 reference-to-video. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, "qwen_ai_platform/deepseek-v4-flash": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 2e-07, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -18138,7 +20599,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -18154,7 +20614,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4.8e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -18170,7 +20629,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 202745, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -18186,7 +20644,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -18202,7 +20659,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 229376, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -18218,7 +20674,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -18230,7 +20685,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -18259,7 +20713,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -18289,7 +20742,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 30720, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -18302,7 +20754,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -18315,7 +20766,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 129024, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -18328,7 +20778,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, @@ -18342,7 +20791,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, @@ -18355,7 +20803,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -18386,7 +20833,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -18417,7 +20863,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -18449,7 +20894,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -18463,7 +20907,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -18476,7 +20919,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -18490,7 +20932,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -18503,7 +20944,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -18514,7 +20954,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -18563,7 +21002,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -18608,7 +21046,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -18657,7 +21094,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -18702,7 +21138,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -18739,7 +21174,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -18776,7 +21210,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -18814,7 +21247,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -18826,7 +21258,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -18839,7 +21270,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -18852,7 +21282,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -18866,7 +21295,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.4e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -18879,7 +21307,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.87e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -18892,7 +21319,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 260096, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -18930,7 +21356,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -18957,12 +21382,13 @@ ] }, "qwen_ai_platform/qwen3.7-max": { + "cache_creation_input_token_cost": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "explicit_cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 2.5e-06, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 7.5e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -18976,7 +21402,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -19012,7 +21437,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -19030,7 +21454,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.7e-07, "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", @@ -19049,7 +21472,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.7e-07, "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", @@ -19068,7 +21490,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 98304, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -19108,6 +21529,281 @@ "/v1/images/generations" ] }, + "qwen_ai_platform/wan3.0-video": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video", + "output_cost_per_second": 0.165025, + "output_cost_per_second_480p": 0.041256, + "output_cost_per_second_720p": 0.082513, + "output_cost_per_second_1080p": 0.165025, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 3.0 all-in-one video generation (text, first/last frame, multimodal reference, edit, extend). Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/wan3.0-video-prime": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video-prime", + "output_cost_per_second": 0.254399, + "output_cost_per_second_480p": 0.0636, + "output_cost_per_second_720p": 0.127199, + "output_cost_per_second_1080p": 0.254399, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 3.0 fast tier. Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/happyhorse-1.1-t2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-t2v", + "output_cost_per_second": 0.165026, + "output_cost_per_second_480p": 0.0618845, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.165026, + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.1 text-to-video. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/happyhorse-1.1-i2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-i2v", + "output_cost_per_second": 0.165026, + "output_cost_per_second_480p": 0.0618845, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.165026, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.1 image-to-video from a first frame. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/happyhorse-1.1-r2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-r2v", + "output_cost_per_second": 0.165026, + "output_cost_per_second_480p": 0.0618845, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.165026, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "HappyHorse 1.1 reference-to-video, 1 to 9 reference images. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/happyhorse-1.0-t2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-t2v", + "output_cost_per_second": 0.220034, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.220034, + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.0 text-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/happyhorse-1.0-i2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-i2v", + "output_cost_per_second": 0.220034, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.220034, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.0 image-to-video from a first frame. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/happyhorse-1.0-r2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-r2v", + "output_cost_per_second": 0.220034, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.220034, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "HappyHorse 1.0 reference-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/wan2.7-t2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-t2v", + "output_cost_per_second": 0.143353, + "output_cost_per_second_720p": 0.086012, + "output_cost_per_second_1080p": 0.143353, + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 2.7 text-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/wan2.7-i2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-i2v", + "output_cost_per_second": 0.143353, + "output_cost_per_second_720p": 0.086012, + "output_cost_per_second_1080p": 0.143353, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 2.7 image-to-video (first frame, first and last frame, continuation). No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/wan2.7-r2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-r2v", + "output_cost_per_second": 0.143353, + "output_cost_per_second_720p": 0.086012, + "output_cost_per_second_1080p": 0.143353, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "Wan 2.7 reference-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, "databricks/databricks-bge-large-en": { "cache_creation_input_token_cost": 1.0003e-07, "cache_read_input_token_cost": 1.0003e-07, @@ -19115,7 +21811,6 @@ "input_dbu_cost_per_token": 1.429e-06, "litellm_provider": "databricks", "max_input_tokens": 512, - "max_tokens": 512, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -19126,20 +21821,20 @@ "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "databricks/databricks-claude-fable-5": { - "cache_creation_input_token_cost": 1.250004e-05, + "cache_creation_input_token_cost": 1.249997e-05, + "cache_creation_input_token_cost_above_1hr": 1.999998e-05, "cache_read_input_token_cost": 1.00002e-06, - "input_cost_per_token": 1.000006e-05, - "input_dbu_cost_per_token": 0.000142858, + "input_cost_per_token": 9.99999e-06, + "input_dbu_cost_per_token": 0.00014286, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 5.000002e-05, - "output_dbu_cost_per_token": 0.000714286, + "output_dbu_cost_per_token": 0.00071429, "prompt_cache_min_tokens": 512, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_adaptive_thinking": true, @@ -19155,20 +21850,20 @@ "thinking_always_on": true }, "databricks/databricks-claude-fable-5-1": { - "cache_creation_input_token_cost": 1.250004e-05, - "cache_read_input_token_cost": 2.5004e-07, - "input_cost_per_token": 1.000006e-05, - "input_dbu_cost_per_token": 0.000142858, + "cache_creation_input_token_cost": 1.249997e-05, + "cache_creation_input_token_cost_above_1hr": 1.999998e-05, + "cache_read_input_token_cost": 2.4997e-07, + "input_cost_per_token": 9.99999e-06, + "input_dbu_cost_per_token": 0.00014286, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 5.000002e-05, - "output_dbu_cost_per_token": 0.000714286, + "output_dbu_cost_per_token": 0.00071429, "prompt_cache_min_tokens": 512, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_adaptive_thinking": true, @@ -19184,15 +21879,18 @@ "supports_vision": true, "thinking_always_on": true }, + "databricks/claude-fable-latest": { + "alias_of": "databricks/databricks-claude-fable-5-2" + }, "databricks/databricks-claude-haiku-4-5": { "cache_creation_input_token_cost": 1.24999e-06, + "cache_creation_input_token_cost_above_1hr": 1.99997e-06, "cache_read_input_token_cost": 1.0003e-07, "input_cost_per_token": 1.00002e-06, "input_dbu_cost_per_token": 1.4286e-05, "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -19210,19 +21908,19 @@ }, "databricks/databricks-claude-opus-4": { "cache_creation_input_token_cost": 1.874999e-05, + "cache_creation_input_token_cost_above_1hr": 2.999997e-05, "cache_read_input_token_cost": 1.50003e-06, - "input_cost_per_token": 1.5000020000000002e-05, - "input_dbu_cost_per_token": 0.000214286, + "input_cost_per_token": 1.500002e-05, + "input_dbu_cost_per_token": 0.00021429, "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 7.500003000000001e-05, - "output_dbu_cost_per_token": 0.001071429, + "output_cost_per_token": 7.50001e-05, + "output_dbu_cost_per_token": 0.0010714, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, @@ -19234,19 +21932,19 @@ }, "databricks/databricks-claude-opus-4-1": { "cache_creation_input_token_cost": 1.874999e-05, + "cache_creation_input_token_cost_above_1hr": 2.999997e-05, "cache_read_input_token_cost": 1.50003e-06, - "input_cost_per_token": 1.5000020000000002e-05, - "input_dbu_cost_per_token": 0.000214286, + "input_cost_per_token": 1.500002e-05, + "input_dbu_cost_per_token": 0.00021429, "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 7.500003000000001e-05, - "output_dbu_cost_per_token": 0.001071429, + "output_cost_per_token": 7.50001e-05, + "output_dbu_cost_per_token": 0.0010714, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, @@ -19258,19 +21956,19 @@ }, "databricks/databricks-claude-opus-4-5": { "cache_creation_input_token_cost": 6.25002e-06, + "cache_creation_input_token_cost_above_1hr": 9.99999e-06, "cache_read_input_token_cost": 5.0001e-07, "input_cost_per_token": 5.00003e-06, "input_dbu_cost_per_token": 7.1429e-05, "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 2.5000010000000002e-05, - "output_dbu_cost_per_token": 0.000357143, + "output_cost_per_token": 2.500001e-05, + "output_dbu_cost_per_token": 0.00035714, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, @@ -19283,21 +21981,21 @@ }, "databricks/databricks-claude-opus-4-6": { "cache_creation_input_token_cost": 6.25002e-06, + "cache_creation_input_token_cost_above_1hr": 9.99999e-06, "cache_read_input_token_cost": 5.0001e-07, "input_cost_per_token": 5.00003e-06, "input_dbu_cost_per_token": 7.1429e-05, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 2.5000010000000002e-05, - "output_dbu_cost_per_token": 0.000357143, + "output_cost_per_token": 2.500001e-05, + "output_dbu_cost_per_token": 0.00035714, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_function_calling": true, "supports_legacy_thinking": true, "supports_prompt_caching": true, @@ -19308,19 +22006,19 @@ }, "databricks/databricks-claude-opus-4-7": { "cache_creation_input_token_cost": 6.25002e-06, + "cache_creation_input_token_cost_above_1hr": 9.99999e-06, "cache_read_input_token_cost": 5.0001e-07, "input_cost_per_token": 5.00003e-06, "input_dbu_cost_per_token": 7.1429e-05, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 2.500001e-05, - "output_dbu_cost_per_token": 0.000357143, + "output_dbu_cost_per_token": 0.00035714, "prompt_cache_min_tokens": 2048, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_adaptive_thinking": true, @@ -19335,19 +22033,19 @@ }, "databricks/databricks-claude-opus-4-8": { "cache_creation_input_token_cost": 6.25002e-06, + "cache_creation_input_token_cost_above_1hr": 9.99999e-06, "cache_read_input_token_cost": 5.0001e-07, "input_cost_per_token": 5.00003e-06, "input_dbu_cost_per_token": 7.1429e-05, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 2.500001e-05, - "output_dbu_cost_per_token": 0.000357143, + "output_dbu_cost_per_token": 0.00035714, "prompt_cache_min_tokens": 1024, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_adaptive_thinking": true, @@ -19363,22 +22061,23 @@ }, "databricks/databricks-claude-opus-5": { "cache_creation_input_token_cost": 6.25002e-06, + "cache_creation_input_token_cost_above_1hr": 9.99999e-06, "cache_read_input_token_cost": 5.0001e-07, "input_cost_per_token": 5.00003e-06, "input_dbu_cost_per_token": 7.1429e-05, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 2.500001e-05, - "output_dbu_cost_per_token": 0.000357143, + "output_dbu_cost_per_token": 0.00035714, "prompt_cache_min_tokens": 512, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_function_calling": true, "supports_mid_conversation_system": true, @@ -19398,7 +22097,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, @@ -19424,21 +22122,24 @@ "supports_xhigh_reasoning_effort": true, "thinking_always_on": true }, + "databricks/claude-opus-latest": { + "alias_of": "databricks/databricks-claude-opus-5-5" + }, "databricks/databricks-claude-sonnet-4": { "cache_creation_input_token_cost": 3.74997e-06, "cache_read_input_token_cost": 3.0002e-07, "deprecation_date": "2026-10-09", - "input_cost_per_token": 2.9999900000000002e-06, + "successor_model": "databricks/databricks-claude-sonnet-5", + "input_cost_per_token": 2.99999e-06, "input_dbu_cost_per_token": 4.2857e-05, "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 1.5000020000000002e-05, + "output_cost_per_token": 1.500002e-05, "output_dbu_cost_per_token": 0.000214286, "prompt_cache_min_tokens": 1024, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", @@ -19457,7 +22158,6 @@ "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -19474,19 +22174,19 @@ }, "databricks/databricks-claude-sonnet-4-5": { "cache_creation_input_token_cost": 3.74997e-06, + "cache_creation_input_token_cost_above_1hr": 5.99998e-06, "cache_read_input_token_cost": 3.0002e-07, - "input_cost_per_token": 2.9999900000000002e-06, + "input_cost_per_token": 2.99999e-06, "input_dbu_cost_per_token": 4.2857e-05, "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 1.5000020000000002e-05, - "output_dbu_cost_per_token": 0.000214286, + "output_cost_per_token": 1.500002e-05, + "output_dbu_cost_per_token": 0.00021429, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, @@ -19498,21 +22198,21 @@ }, "databricks/databricks-claude-sonnet-4-6": { "cache_creation_input_token_cost": 3.74997e-06, + "cache_creation_input_token_cost_above_1hr": 5.99998e-06, "cache_read_input_token_cost": 3.0002e-07, - "input_cost_per_token": 2.9999900000000002e-06, + "input_cost_per_token": 2.99999e-06, "input_dbu_cost_per_token": 4.2857e-05, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 1.5000020000000002e-05, - "output_dbu_cost_per_token": 0.000214286, + "output_cost_per_token": 1.500002e-05, + "output_dbu_cost_per_token": 0.00021429, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_function_calling": true, "supports_legacy_thinking": true, "supports_prompt_caching": true, @@ -19522,23 +22222,24 @@ "prompt_cache_min_tokens": 1024 }, "databricks/databricks-claude-sonnet-5": { - "cache_creation_input_token_cost": 3.74997e-06, - "cache_read_input_token_cost": 3.0002e-07, - "input_cost_per_token": 2.99999e-06, - "input_dbu_cost_per_token": 4.2857e-05, + "cache_creation_input_token_cost": 2.49998e-06, + "cache_creation_input_token_cost_above_1hr": 4.00001e-06, + "cache_read_input_token_cost": 1.9999e-07, + "input_cost_per_token": 1.99997e-06, + "input_dbu_cost_per_token": 2.8571e-05, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { - "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields. Introductory launch rates of 28.571 input / 142.857 output / 35.714 cache write / 2.857 cache read DBU run through 2026-08-31; the standard rates are listed here because entries carry no expiry date." + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", - "output_cost_per_token": 1.500002e-05, - "output_dbu_cost_per_token": 0.000214286, + "output_cost_per_token": 9.99999e-06, + "output_dbu_cost_per_token": 0.00014286, "prompt_cache_min_tokens": 1024, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_function_calling": true, "supports_mid_conversation_system": true, @@ -19552,19 +22253,22 @@ "databricks/databricks-deepseek-v4-flash-0731": { "cache_creation_input_token_cost": 1.4e-07, "cache_read_input_token_cost": 2.8e-08, + "deprecation_date": "2026-11-05", + "deprecation_source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "input_cost_per_token": 1.4e-07, "input_dbu_cost_per_token": 2e-06, "litellm_provider": "databricks", + "token_count_framing": 97, "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference. Context/max output are the DeepSeek-published model limits (1M context, 384K max output)." }, "mode": "chat", "output_cost_per_token": 2.8e-07, "output_dbu_cost_per_token": 4e-06, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", + "successor_model": "databricks/databricks-deepseek-v4-1-flash-1017", "supported_modalities": [ "text" ], @@ -19577,22 +22281,33 @@ "supports_tool_choice": true, "supports_vision": false }, + "databricks/system.ai.deepseek-v4-flash-0731": { + "deprecation_date": "2026-11-05", + "deprecation_source": "https://docs.databricks.com/aws/en/machine-learning/retired-models-policy", + "litellm_provider": "databricks", + "mode": "chat", + "source": "https://docs.databricks.com/aws/en/machine-learning/retired-models-policy", + "successor_model": "databricks/databricks-deepseek-v4-1-flash-1017", + "token_count_framing": 97 + }, "databricks/databricks-deepseek-v4-pro-0813": { "cache_creation_input_token_cost": 1.31999e-06, "cache_read_input_token_cost": 1.3202e-07, + "deprecation_date": "2026-10-30", + "deprecation_source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "input_cost_per_token": 1.31999e-06, "input_dbu_cost_per_token": 1.8857e-05, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference. Context/max output are the DeepSeek-published model limits (1M context, 384K max output)." }, "mode": "chat", "output_cost_per_token": 3.95997e-06, "output_dbu_cost_per_token": 5.6571e-05, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", + "successor_model": "databricks/databricks-deepseek-v4-1-flash-1017", "supported_modalities": [ "text" ], @@ -19609,12 +22324,12 @@ "cache_creation_input_token_cost": 3.0002e-07, "cache_read_input_token_cost": 3.0002e-08, "deprecation_date": "2026-10-02", + "successor_model": "databricks/databricks-gemini-3-5-flash", "input_cost_per_token": 3.0001999999999996e-07, "input_dbu_cost_per_token": 4.285999999999999e-06, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -19648,7 +22363,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -19677,13 +22391,15 @@ }, "databricks/databricks-gemini-3-1-flash-lite": { "cache_creation_input_token_cost": 3.1248e-07, + "cache_read_input_audio_token_cost": 6.251e-08, "cache_read_input_token_cost": 3.122e-08, + "input_cost_per_audio_token": 6.2503e-07, + "input_cost_per_image_token": 3.1248e-07, "input_cost_per_token": 3.1248e-07, "input_dbu_cost_per_token": 4.464e-06, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -19705,17 +22421,28 @@ ], "supports_vision": true, "supports_audio_input": true, - "supports_video_input": true + "supports_video_input": true, + "input_cost_per_token_priority": 5.6252e-07, + "output_cost_per_token_priority": 3.37498e-06, + "cache_read_input_token_cost_priority": 5.628e-08, + "cache_creation_input_token_cost_priority": 5.6252e-07, + "input_cost_per_audio_token_priority": 1.12497e-06, + "cache_read_input_audio_token_cost_priority": 1.1249e-07 }, "databricks/databricks-gemini-3-1-flash-image": { + "cache_creation_input_token_cost": 6.2503e-07, + "cache_read_input_token_cost": 6.2503e-07, + "input_cost_per_image_token": 6.2503e-07, + "input_cost_per_token": 6.2503e-07, "litellm_provider": "databricks", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "metadata": { - "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", + "output_cost_per_image_token": 7.50001e-05, + "output_cost_per_token": 3.74997e-06, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", @@ -19729,14 +22456,19 @@ "supports_vision": true }, "databricks/databricks-gemini-3-pro-image": { + "cache_creation_input_token_cost": 2.49998e-06, + "cache_read_input_token_cost": 2.49998e-06, + "input_cost_per_image_token": 2.49998e-06, + "input_cost_per_token": 2.49998e-06, "litellm_provider": "databricks", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "metadata": { - "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", + "output_cost_per_image_token": 0.0001500002, + "output_cost_per_token": 1.500002e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", @@ -19752,23 +22484,21 @@ "databricks/databricks-gemini-3-1-pro": { "cache_creation_input_token_cost": 2.49998e-06, "cache_read_input_token_cost": 2.4997e-07, + "cache_read_input_token_cost_above_200k_tokens": 5.0001e-07, "input_cost_per_token": 2.49998e-06, + "input_cost_per_token_above_200k_tokens": 5.00003e-06, "input_dbu_cost_per_token": 3.5714e-05, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 1.5000020000000002e-05, + "output_cost_per_token": 1.500002e-05, + "output_cost_per_token_above_200k_tokens": 2.25e-05, "output_dbu_cost_per_token": 0.000214286, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_tool_choice": true, - "supports_reasoning": true, "supported_modalities": [ "text", "image", @@ -19778,19 +22508,32 @@ "supported_output_modalities": [ "text" ], - "supports_vision": true, "supports_audio_input": true, - "supports_video_input": true + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "input_cost_per_token_priority": 4.50002e-06, + "output_cost_per_token_priority": 2.699998e-05, + "cache_read_input_token_cost_priority": 4.5003e-07, + "cache_creation_input_token_cost_priority": 4.50002e-06, + "input_cost_per_token_above_200k_tokens_priority": 8.99997e-06, + "output_cost_per_token_above_200k_tokens_priority": 4.049997e-05, + "cache_read_input_token_cost_above_200k_tokens_priority": 8.9999e-07 }, "databricks/databricks-gemini-3-flash": { "cache_creation_input_token_cost": 6.2503e-07, + "cache_read_input_audio_token_cost": 1.2502e-07, "cache_read_input_token_cost": 6.251e-08, + "input_cost_per_audio_token": 1.24999e-06, + "input_cost_per_image_token": 6.2503e-07, "input_cost_per_token": 6.2503e-07, "input_dbu_cost_per_token": 8.929e-06, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -19812,7 +22555,13 @@ ], "supports_vision": true, "supports_audio_input": true, - "supports_video_input": true + "supports_video_input": true, + "input_cost_per_token_priority": 1.12497e-06, + "output_cost_per_token_priority": 6.75003e-06, + "cache_read_input_token_cost_priority": 1.1249e-07, + "cache_creation_input_token_cost_priority": 1.12497e-06, + "input_cost_per_audio_token_priority": 2.25001e-06, + "cache_read_input_audio_token_cost_priority": 2.2498e-07 }, "databricks/databricks-gemini-3-pro": { "cache_creation_input_token_cost": 2.49998e-06, @@ -19822,7 +22571,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -19835,15 +22583,18 @@ "supports_tool_choice": true }, "databricks/databricks-gemini-3-8-flash": { + "cache_creation_input_token_cost": 7.4998e-07, + "cache_read_input_token_cost": 7.497e-08, + "input_cost_per_token": 7.4998e-07, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { - "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "output_cost_per_token": 3.74997e-06, + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text", "image", @@ -19855,19 +22606,29 @@ ], "supports_function_calling": true, "supports_reasoning": true, + "supports_sampling_params": false, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "input_cost_per_token_priority": 1.35002e-06, + "output_cost_per_token_priority": 6.75003e-06, + "cache_read_input_token_cost_priority": 1.3503e-07, + "cache_creation_input_token_cost_priority": 1.35002e-06, + "supports_audio_input": true, + "supports_video_input": true }, "databricks/databricks-gemini-3-7-flash": { + "cache_creation_input_token_cost": 7.4998e-07, + "cache_read_input_token_cost": 7.497e-08, + "input_cost_per_token": 7.4998e-07, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { - "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "output_cost_per_token": 3.74997e-06, + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text", "image", @@ -19879,25 +22640,31 @@ ], "supports_function_calling": true, "supports_reasoning": true, + "supports_sampling_params": false, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "input_cost_per_token_priority": 1.35002e-06, + "output_cost_per_token_priority": 6.75003e-06, + "cache_read_input_token_cost_priority": 1.3503e-07, + "cache_creation_input_token_cost_priority": 1.35002e-06, + "supports_audio_input": true, + "supports_video_input": true }, "databricks/databricks-gemini-3-6-flash": { - "cache_creation_input_token_cost": 1.87502e-06, - "cache_read_input_token_cost": 1.8753e-07, - "input_cost_per_token": 1.87502e-06, - "input_dbu_cost_per_token": 2.6786e-05, + "cache_creation_input_token_cost": 7.4998e-07, + "cache_read_input_token_cost": 7.497e-08, + "input_cost_per_token": 7.4998e-07, + "input_dbu_cost_per_token": 1.0714e-05, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", - "output_cost_per_token": 9.37503e-06, - "output_dbu_cost_per_token": 0.000133929, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "output_cost_per_token": 3.74997e-06, + "output_dbu_cost_per_token": 5.3571e-05, + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text", "image", @@ -19910,8 +22677,15 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_sampling_params": false, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "input_cost_per_token_priority": 1.35002e-06, + "output_cost_per_token_priority": 6.75003e-06, + "cache_read_input_token_cost_priority": 1.3503e-07, + "cache_creation_input_token_cost_priority": 1.35002e-06, + "supports_audio_input": true, + "supports_video_input": true }, "databricks/databricks-gemini-3-5-flash": { "cache_creation_input_token_cost": 1.87502e-06, @@ -19921,14 +22695,13 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 1.124998e-05, "output_dbu_cost_per_token": 0.000160714, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text", "image", @@ -19942,7 +22715,13 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "input_cost_per_token_priority": 3.37498e-06, + "output_cost_per_token_priority": 2.025002e-05, + "cache_read_input_token_cost_priority": 3.3747e-07, + "cache_creation_input_token_cost_priority": 3.37498e-06, + "supports_audio_input": true, + "supports_video_input": true }, "databricks/databricks-gemini-3-5-flash-lite": { "cache_creation_input_token_cost": 3.7499e-07, @@ -19952,14 +22731,13 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 3.12501e-06, "output_dbu_cost_per_token": 4.4643e-05, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text", "image", @@ -19973,18 +22751,24 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "input_cost_per_token_priority": 6.7501e-07, + "output_cost_per_token_priority": 5.62499e-06, + "cache_read_input_token_cost_priority": 6.748e-08, + "cache_creation_input_token_cost_priority": 6.7501e-07, + "supports_audio_input": true, + "supports_video_input": true }, "databricks/databricks-gemma-3-12b": { "cache_creation_input_token_cost": 1.5001e-07, "cache_read_input_token_cost": 1.5001e-07, - "input_cost_per_token": 1.5000999999999998e-07, + "input_cost_per_token": 1.5001e-07, "input_dbu_cost_per_token": 2.1429999999999996e-06, "litellm_provider": "databricks", "max_input_tokens": 128000, "max_output_tokens": 32000, - "max_tokens": 32000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -20001,7 +22785,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference." }, @@ -20019,7 +22802,14 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": false, + "input_cost_per_token_priority": 2.45e-06, + "output_cost_per_token_priority": 7.7e-06, + "cache_read_input_token_cost_priority": 4.55e-07, + "cache_creation_input_token_cost_priority": 2.45e-06, + "deprecation_date": "2027-02-04", + "deprecation_source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", + "successor_model": "databricks/databricks-glm-5-3" }, "databricks/databricks-glm-5-3": { "cache_creation_input_token_cost": 1.4e-06, @@ -20029,7 +22819,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, @@ -20050,7 +22839,14 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false, - "thinking_always_on": true + "thinking_always_on": true, + "input_cost_per_token_priority": 2.45e-06, + "output_cost_per_token_priority": 7.7e-06, + "cache_read_input_token_cost_priority": 4.55e-07, + "cache_creation_input_token_cost_priority": 2.45e-06 + }, + "databricks/glm-latest": { + "alias_of": "databricks/databricks-glm-5-3" }, "databricks/databricks-glm-5-3-flash": { "cache_creation_input_token_cost": 1.5001e-07, @@ -20060,7 +22856,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, @@ -20080,7 +22875,14 @@ "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, - "thinking_always_on": true + "thinking_always_on": true, + "input_cost_per_token_priority": 2.625e-07, + "output_cost_per_token_priority": 8.75e-07, + "cache_read_input_token_cost_priority": 5.25e-08, + "cache_creation_input_token_cost_priority": 2.625e-07 + }, + "databricks/glm-flash-latest": { + "alias_of": "databricks/databricks-glm-5-3-flash" }, "databricks/databricks-gpt-5": { "cache_creation_input_token_cost": 1.24999e-06, @@ -20090,17 +22892,20 @@ "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 9.999990000000002e-06, + "output_cost_per_token": 9.99999e-06, "output_dbu_cost_per_token": 0.000142857, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, "supports_prompt_caching": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "input_cost_per_token_priority": 2.49998e-06, + "output_cost_per_token_priority": 1.999998e-05, + "cache_read_input_token_cost_priority": 2.4997e-07, + "cache_creation_input_token_cost_priority": 2.49998e-06 }, "databricks/databricks-gpt-5-1": { "cache_creation_input_token_cost": 1.24999e-06, @@ -20110,17 +22915,20 @@ "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 9.999990000000002e-06, + "output_cost_per_token": 9.99999e-06, "output_dbu_cost_per_token": 0.000142857, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, "supports_prompt_caching": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "input_cost_per_token_priority": 2.49998e-06, + "output_cost_per_token_priority": 1.999998e-05, + "cache_read_input_token_cost_priority": 2.4997e-07, + "cache_creation_input_token_cost_priority": 2.49998e-06 }, "databricks/databricks-gpt-5-2": { "cache_creation_input_token_cost": 1.75e-06, @@ -20130,7 +22938,6 @@ "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -20140,7 +22947,11 @@ "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, "supports_prompt_caching": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "input_cost_per_token_priority": 3.5e-06, + "output_cost_per_token_priority": 2.8e-05, + "cache_read_input_token_cost_priority": 3.5e-07, + "cache_creation_input_token_cost_priority": 3.5e-06 }, "databricks/databricks-gpt-5-3-codex": { "cache_creation_input_token_cost": 1.75e-06, @@ -20150,7 +22961,6 @@ "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -20160,22 +22970,28 @@ "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, "supports_prompt_caching": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "input_cost_per_token_priority": 3.5e-06, + "output_cost_per_token_priority": 2.8e-05, + "cache_read_input_token_cost_priority": 3.5e-07, + "cache_creation_input_token_cost_priority": 3.5e-06 }, "databricks/databricks-gpt-5-4": { "cache_creation_input_token_cost": 2.49998e-06, "cache_read_input_token_cost": 2.4997e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.0001e-07, "input_cost_per_token": 2.49998e-06, + "input_cost_per_token_above_272k_tokens": 5.00003e-06, "input_dbu_cost_per_token": 3.5714e-05, "litellm_provider": "databricks", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 1.5000020000000002e-05, + "output_cost_per_token": 1.500002e-05, + "output_cost_per_token_above_272k_tokens": 2.25e-05, "output_dbu_cost_per_token": 0.000214286, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ @@ -20189,7 +23005,14 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "input_cost_per_token_priority": 5.00003e-06, + "output_cost_per_token_priority": 2.999997e-05, + "cache_read_input_token_cost_priority": 5.0001e-07, + "cache_creation_input_token_cost_priority": 5.00003e-06, + "input_cost_per_token_above_272k_tokens_priority": 5.00003e-06, + "output_cost_per_token_above_272k_tokens_priority": 2.999997e-05, + "cache_read_input_token_cost_above_272k_tokens_priority": 5.0001e-07 }, "databricks/databricks-gpt-5-4-mini": { "cache_creation_input_token_cost": 7.4998e-07, @@ -20199,7 +23022,6 @@ "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -20218,7 +23040,14 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "input_cost_per_token_priority": 1.50003e-06, + "output_cost_per_token_priority": 8.99997e-06, + "cache_read_input_token_cost_priority": 1.5001e-07, + "cache_creation_input_token_cost_priority": 1.50003e-06 + }, + "databricks/gpt-mini-latest": { + "alias_of": "databricks/databricks-gpt-5-4-mini" }, "databricks/databricks-gpt-5-4-nano": { "cache_creation_input_token_cost": 1.9999e-07, @@ -20228,7 +23057,6 @@ "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -20251,18 +23079,21 @@ }, "databricks/databricks-gpt-5-6-sol": { "cache_creation_input_token_cost": 5.00003e-06, + "cache_creation_input_token_cost_above_272k_tokens": 9.99999e-06, "cache_read_input_token_cost": 3.9998e-07, + "cache_read_input_token_cost_above_272k_tokens": 8.0003e-07, "input_cost_per_token": 4.00001e-06, + "input_cost_per_token_above_272k_tokens": 8.00002e-06, "input_dbu_cost_per_token": 5.7143e-05, "litellm_provider": "databricks", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields. Rates reflect OpenAI's promotional pricing in effect through November 21, 2026; afterwards input, cache and Batch rates are 25% higher and output rates 50% higher." }, "mode": "chat", "output_cost_per_token": 1.999998e-05, + "output_cost_per_token_above_272k_tokens": 3e-05, "output_dbu_cost_per_token": 0.000285714, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ @@ -20276,23 +23107,34 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "input_cost_per_token_priority": 8.00002e-06, + "output_cost_per_token_priority": 4.000003e-05, + "cache_read_input_token_cost_priority": 8.0003e-07, + "cache_creation_input_token_cost_priority": 9.99999e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.599997e-05, + "output_cost_per_token_above_272k_tokens_priority": 6.000001e-05, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.59999e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1.999998e-05 }, "databricks/databricks-gpt-5-6-terra": { - "cache_creation_input_token_cost": 3.12501e-06, - "cache_read_input_token_cost": 2.4997e-07, - "input_cost_per_token": 2.49998e-06, - "input_dbu_cost_per_token": 3.5714e-05, + "cache_creation_input_token_cost": 2.49998e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5.00003e-06, + "cache_read_input_token_cost": 1.9999e-07, + "cache_read_input_token_cost_above_272k_tokens": 3.9998e-07, + "input_cost_per_token": 1.99997e-06, + "input_cost_per_token_above_272k_tokens": 4.00001e-06, + "input_dbu_cost_per_token": 2.8571e-05, "litellm_provider": "databricks", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", - "output_cost_per_token": 1.500002e-05, - "output_dbu_cost_per_token": 0.000214286, + "output_cost_per_token": 1.200003e-05, + "output_cost_per_token_above_272k_tokens": 1.8e-05, + "output_dbu_cost_per_token": 0.000171429, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", @@ -20305,23 +23147,34 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "input_cost_per_token_priority": 4.00001e-06, + "output_cost_per_token_priority": 2.399999e-05, + "cache_read_input_token_cost_priority": 3.9998e-07, + "cache_creation_input_token_cost_priority": 5.00003e-06, + "input_cost_per_token_above_272k_tokens_priority": 8.00002e-06, + "output_cost_per_token_above_272k_tokens_priority": 3.600002e-05, + "cache_read_input_token_cost_above_272k_tokens_priority": 8.0003e-07, + "cache_creation_input_token_cost_above_272k_tokens_priority": 9.99999e-06 }, "databricks/databricks-gpt-5-6-luna": { - "cache_creation_input_token_cost": 1.24999e-06, - "cache_read_input_token_cost": 1.0003e-07, - "input_cost_per_token": 1.00002e-06, - "input_dbu_cost_per_token": 1.4286e-05, + "cache_creation_input_token_cost": 2.4997e-07, + "cache_creation_input_token_cost_above_272k_tokens": 5.0001e-07, + "cache_read_input_token_cost": 2.002e-08, + "cache_read_input_token_cost_above_272k_tokens": 3.997e-08, + "input_cost_per_token": 1.9999e-07, + "input_cost_per_token_above_272k_tokens": 3.9998e-07, + "input_dbu_cost_per_token": 2.857e-06, "litellm_provider": "databricks", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", - "output_cost_per_token": 5.99998e-06, - "output_dbu_cost_per_token": 8.5714e-05, + "output_cost_per_token": 1.20001e-06, + "output_cost_per_token_above_272k_tokens": 1.79998e-06, + "output_dbu_cost_per_token": 1.7143e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", @@ -20334,22 +23187,32 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "input_cost_per_token_priority": 3.9998e-07, + "output_cost_per_token_priority": 2.40002e-06, + "cache_read_input_token_cost_priority": 3.997e-08, + "cache_creation_input_token_cost_priority": 5.0001e-07, + "input_cost_per_token_above_272k_tokens_priority": 8.0003e-07, + "output_cost_per_token_above_272k_tokens_priority": 3.60003e-06, + "cache_read_input_token_cost_above_272k_tokens_priority": 8.001e-08, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1.00002e-06 }, "databricks/databricks-gpt-5-5": { "cache_creation_input_token_cost": 5.00003e-06, "cache_read_input_token_cost": 5.0001e-07, + "cache_read_input_token_cost_above_272k_tokens": 1.00002e-06, "input_cost_per_token": 5.00003e-06, + "input_cost_per_token_above_272k_tokens": 9.99999e-06, "input_dbu_cost_per_token": 7.1429e-05, "litellm_provider": "databricks", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "responses", "output_cost_per_token": 2.999997e-05, + "output_cost_per_token_above_272k_tokens": 4.5e-05, "output_dbu_cost_per_token": 0.000428571, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ @@ -20363,23 +23226,31 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "input_cost_per_token_priority": 1.249997e-05, + "output_cost_per_token_priority": 7.50001e-05, + "cache_read_input_token_cost_priority": 1.24999e-06, + "cache_creation_input_token_cost_priority": 1.249997e-05, + "input_cost_per_token_above_272k_tokens_priority": 1.249997e-05, + "output_cost_per_token_above_272k_tokens_priority": 7.50001e-05, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.24999e-06 }, "databricks/databricks-gpt-5-5-pro": { "cache_creation_input_token_cost": 2.999997e-05, "cache_read_input_token_cost": 2.999997e-05, "input_cost_per_token": 2.999997e-05, - "input_dbu_cost_per_token": 0.000428571, + "input_cost_per_token_above_272k_tokens": 6e-05, + "input_dbu_cost_per_token": 0.00042857, "litellm_provider": "databricks", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "responses", - "output_cost_per_token": 0.00018000003, - "output_dbu_cost_per_token": 0.002571429, + "output_cost_per_token": 0.0001800001, + "output_cost_per_token_above_272k_tokens": 0.00027, + "output_dbu_cost_per_token": 0.0025714, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", @@ -20397,22 +23268,25 @@ "databricks/databricks-gpt-5-mini": { "cache_creation_input_token_cost": 2.4997e-07, "cache_read_input_token_cost": 2.499e-08, - "input_cost_per_token": 2.4997000000000006e-07, + "input_cost_per_token": 2.4997e-07, "input_dbu_cost_per_token": 3.571e-06, "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 1.9999700000000004e-06, + "output_cost_per_token": 1.99997e-06, "output_dbu_cost_per_token": 2.8571e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, "supports_prompt_caching": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "input_cost_per_token_priority": 4.5003e-07, + "output_cost_per_token_priority": 3.60003e-06, + "cache_read_input_token_cost_priority": 4.501e-08, + "cache_creation_input_token_cost_priority": 4.5003e-07 }, "databricks/databricks-gpt-5-nano": { "cache_creation_input_token_cost": 4.998e-08, @@ -20422,12 +23296,11 @@ "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 3.9998000000000007e-07, + "output_cost_per_token": 3.9998e-07, "output_dbu_cost_per_token": 5.714000000000001e-06, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, @@ -20437,12 +23310,11 @@ "databricks/databricks-gpt-oss-120b": { "cache_creation_input_token_cost": 1.5001e-07, "cache_read_input_token_cost": 1.5001e-07, - "input_cost_per_token": 1.5000999999999998e-07, + "input_cost_per_token": 1.5001e-07, "input_dbu_cost_per_token": 2.1429999999999996e-06, "litellm_provider": "databricks", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -20459,12 +23331,11 @@ "litellm_provider": "databricks", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 3.0001999999999996e-07, + "output_cost_per_token": 3.0002e-07, "output_dbu_cost_per_token": 4.285999999999999e-06, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, @@ -20497,11 +23368,10 @@ "databricks/databricks-gte-large-en": { "cache_creation_input_token_cost": 1.2999e-07, "cache_read_input_token_cost": 1.2999e-07, - "input_cost_per_token": 1.2999000000000001e-07, + "input_cost_per_token": 1.2999e-07, "input_dbu_cost_per_token": 1.857e-06, "litellm_provider": "databricks", "max_input_tokens": 8192, - "max_tokens": 8192, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -20514,6 +23384,8 @@ "databricks/databricks-inkling": { "cache_creation_input_token_cost": 1.00002e-06, "cache_read_input_token_cost": 1.7003e-07, + "deprecation_date": "2026-10-30", + "deprecation_source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "input_cost_per_token": 1.00002e-06, "input_dbu_cost_per_token": 1.4286e-05, "litellm_provider": "databricks", @@ -20524,7 +23396,8 @@ "mode": "chat", "output_cost_per_token": 4.04999e-06, "output_dbu_cost_per_token": 5.7857e-05, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", + "successor_model": "databricks/databricks-glm-5-3", "supported_modalities": [ "text", "image" @@ -20545,9 +23418,9 @@ "input_cost_per_token": 2.99999e-06, "input_dbu_cost_per_token": 4.2857e-05, "litellm_provider": "databricks", + "token_count_framing": 100, "max_input_tokens": 1000000, "max_output_tokens": 1048576, - "max_tokens": 1048576, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference." }, @@ -20566,7 +23439,19 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "input_cost_per_token_priority": 5.25e-06, + "output_cost_per_token_priority": 2.625e-05, + "cache_read_input_token_cost_priority": 5.25e-07, + "cache_creation_input_token_cost_priority": 5.25e-06 + }, + "databricks/kimi-latest": { + "alias_of": "databricks/databricks-kimi-k3" + }, + "databricks/system.ai.kimi-k3": { + "litellm_provider": "databricks", + "mode": "chat", + "token_count_framing": 100 }, "databricks/databricks-llama-4-maverick": { "cache_creation_input_token_cost": 5.0001e-07, @@ -20576,12 +23461,11 @@ "litellm_provider": "databricks", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Databricks documentation now provides both DBU costs (_dbu_cost_per_token) and dollar costs(_cost_per_token)." }, "mode": "chat", - "output_cost_per_token": 1.5000300000000002e-06, + "output_cost_per_token": 1.50003e-06, "output_dbu_cost_per_token": 2.1429e-05, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true @@ -20589,17 +23473,16 @@ "databricks/databricks-meta-llama-3-1-8b-instruct": { "cache_creation_input_token_cost": 1.5001e-07, "cache_read_input_token_cost": 1.5001e-07, - "input_cost_per_token": 1.5000999999999998e-07, + "input_cost_per_token": 1.5001e-07, "input_dbu_cost_per_token": 2.1429999999999996e-06, "litellm_provider": "databricks", - "max_input_tokens": 200000, + "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 4.5003000000000007e-07, + "output_cost_per_token": 4.5003e-07, "output_dbu_cost_per_token": 6.429000000000001e-06, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, @@ -20611,12 +23494,11 @@ "litellm_provider": "databricks", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 1.5000300000000002e-06, + "output_cost_per_token": 1.50003e-06, "output_dbu_cost_per_token": 2.1429e-05, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true @@ -20629,7 +23511,6 @@ "litellm_provider": "databricks", "max_input_tokens": 262144, "max_output_tokens": 25000, - "max_tokens": 25000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, @@ -20647,7 +23528,11 @@ "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false, - "thinking_always_on": true + "thinking_always_on": true, + "input_cost_per_token_priority": 3.85e-07, + "output_cost_per_token_priority": 3.85e-06, + "cache_read_input_token_cost_priority": 3.85e-07, + "cache_creation_input_token_cost_priority": 3.85e-07 }, "databricks/databricks-qwen3-next-80b-a3b-instruct": { "cache_creation_input_token_cost": 1.5001e-07, @@ -20679,7 +23564,6 @@ "input_dbu_cost_per_token": 2.86e-07, "litellm_provider": "databricks", "max_input_tokens": 32768, - "max_tokens": 32768, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, @@ -20689,6 +23573,51 @@ "output_vector_size": 1024, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, + "databricks/databricks-openjev-qwen35-4b": { + "cache_creation_input_token_cost": 4.2e-08, + "cache_read_input_token_cost": 4.2e-08, + "input_cost_per_token": 4.2e-08, + "input_dbu_cost_per_token": 6e-07, + "litellm_provider": "databricks", + "metadata": { + "notes": "Pay-per-token Foundation Model API decision endpoint (OpenJev, Qwen 3.5 4B) queried through the System One API. The serving-endpoints API lists it at 0.6 DBUs per 1M input tokens (input_price on the foundation_model entry, read 2026-10-27); input_cost_per_token is that dbu cost * $0.070, the same conversion as the other databricks rows. Output is free. Databricks publishes no cache rates for it, so cache tokens bill at the input rate." + }, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "output_dbu_cost_per_token": 0.0, + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models" + }, + "databricks/databricks-typesafeai-jev-1-14-0": { + "cache_creation_input_token_cost": 4.2e-08, + "cache_read_input_token_cost": 4.2e-08, + "input_cost_per_token": 4.2e-08, + "input_dbu_cost_per_token": 6e-07, + "litellm_provider": "databricks", + "metadata": { + "notes": "TypeSafe AI Jev 1.14.0, provider-hosted by TypeSafe AI and served through Unity Gateway, queried through the System One API. The proprietary pricing page lists 'Jev 1.14' at 0.600 DBU per 1M input tokens; input_cost_per_token is that times $0.070 per DBU. Output is free. No cache rates are published, so cache tokens bill at the input rate." + }, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "output_dbu_cost_per_token": 0.0, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supports_vision": true + }, + "databricks/ai_decide": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 0.0, + "input_cost_per_token": 0.0, + "litellm_provider": "databricks", + "metadata": { + "notes": "The ai_decide AI Function (Beta), called through POST /api/2.0/ai-functions/ai-decide. Its response carries no token usage, so LiteLLM records no spend for it." + }, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.databricks.com/api/ai-functions/v1/ai-decide" + }, "dataforseo/search": { "input_cost_per_query": 0.003, "litellm_provider": "dataforseo", @@ -20696,17 +23625,36 @@ }, "davinci-002": { "deprecation_date": "2026-09-28", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 2e-06, "output_cost_per_token_batches": 1e-06, "source": "https://developers.openai.com/api/docs/pricing" }, + "deepgram/aura": { + "input_cost_per_character": 1.5e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0150/1000 characters = $0.000015 per character", + "note": "Aura-1 text-to-speech voices (aura--), pay as you go" + }, + "source": "https://deepgram.com/pricing" + }, + "deepgram/aura-2": { + "input_cost_per_character": 3e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.030/1000 characters = $0.00003 per character", + "note": "Aura-2 text-to-speech voices (aura-2--), pay as you go" + }, + "source": "https://deepgram.com/pricing" + }, "deepgram/base": { "input_cost_per_second": 0.00020833, "litellm_provider": "deepgram", @@ -21128,12 +24076,12 @@ ] }, "deepgram/streaming/nova-3": { - "input_cost_per_second": 8e-05, + "input_cost_per_second": 0.00012833, "litellm_provider": "deepgram", "metadata": { - "calculation": "$0.0048/60 seconds = $0.00008000 per second", + "calculation": "$0.0077/60 seconds = $0.00012833 per second", "note": "Nova-3 monolingual streaming, pay as you go", - "original_pricing_per_minute": 0.0048 + "original_pricing_per_minute": 0.0077 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, @@ -21142,13 +24090,28 @@ "/v1/listen" ] }, + "deepgram/streaming/nova-3-medical": { + "input_cost_per_second": 0.00012833, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0077/60 seconds = $0.00012833 per second", + "note": "Nova-3 Medical streaming, launch price from Deepgram's 2025-03-03 announcement. deepgram.com/pricing does not list Nova-3 Medical, and this matches its current Nova-3 monolingual streaming pay as you go rate", + "original_pricing_per_minute": 0.0077 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://www.businesswire.com/news/home/20250303470439/en", + "supported_endpoints": [ + "/v1/listen" + ] + }, "deepgram/streaming/nova-3-multilingual": { - "input_cost_per_second": 9.667e-05, + "input_cost_per_second": 0.00015333, "litellm_provider": "deepgram", "metadata": { - "calculation": "$0.0058/60 seconds = $0.00009667 per second", + "calculation": "$0.0092/60 seconds = $0.00015333 per second", "note": "Nova-3 multilingual (language=multi) streaming, pay as you go", - "original_pricing_per_minute": 0.0058 + "original_pricing_per_minute": 0.0092 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, @@ -21296,7 +24259,6 @@ ] }, "deepinfra/Gryphe/MythoMax-L2-13b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 4e-07, @@ -21308,7 +24270,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/NousResearch/Hermes-3-Llama-3.1-405B": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-06, @@ -21319,7 +24280,6 @@ "supports_function_calling": true }, "deepinfra/NousResearch/Hermes-3-Llama-3.1-70B": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 7e-07, @@ -21330,7 +24290,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/QwQ-32B": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.5e-07, @@ -21341,7 +24300,6 @@ "supports_function_calling": true }, "deepinfra/Qwen/Qwen2.5-72B-Instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 3.6e-07, @@ -21353,7 +24311,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen2.5-7B-Instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 4e-08, @@ -21363,7 +24320,6 @@ "supports_tool_choice": false }, "deepinfra/Qwen/Qwen2.5-VL-32B-Instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-07, @@ -21375,7 +24331,6 @@ "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-14B": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1.2e-07, @@ -21387,7 +24342,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-235B-A22B": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1.8e-07, @@ -21398,7 +24352,6 @@ "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9e-08, @@ -21410,7 +24363,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 3e-07, @@ -21421,7 +24373,6 @@ "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-30B-A3B": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1.2e-07, @@ -21433,7 +24384,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-32B": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 8e-08, @@ -21445,7 +24395,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 4e-07, @@ -21456,7 +24405,6 @@ "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 3e-07, @@ -21470,7 +24418,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9e-08, @@ -21482,7 +24429,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.4e-07, @@ -21493,7 +24439,6 @@ "supports_function_calling": true }, "deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 4e-08, @@ -21503,7 +24448,6 @@ "supports_tool_choice": false }, "deepinfra/Sao10K/L3.1-70B-Euryale-v2.2": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 8.5e-07, @@ -21514,7 +24458,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Sao10K/L3.3-70B-Euryale-v2.3": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 6.5e-07, @@ -21524,7 +24467,6 @@ "supports_tool_choice": false }, "deepinfra/allenai/olmOCR-7B-0725-FP8": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2.7e-07, @@ -21534,7 +24476,6 @@ "supports_tool_choice": false }, "deepinfra/anthropic/claude-3-7-sonnet-latest": { - "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 3.3e-06, @@ -21546,7 +24487,6 @@ "supports_function_calling": true }, "deepinfra/anthropic/claude-4-opus": { - "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 1.65e-05, @@ -21557,7 +24497,6 @@ "supports_function_calling": true }, "deepinfra/anthropic/claude-4-sonnet": { - "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 3.3e-06, @@ -21568,7 +24507,6 @@ "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 7e-07, @@ -21579,19 +24517,17 @@ "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1-0528": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 5e-07, "output_cost_per_token": 2.15e-06, - "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost": 3.5e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-06, @@ -21602,7 +24538,6 @@ "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -21612,7 +24547,6 @@ "supports_tool_choice": false }, "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2.7e-07, @@ -21623,7 +24557,6 @@ "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1-Turbo": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1e-06, @@ -21634,7 +24567,6 @@ "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-V3": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 3.2e-07, @@ -21646,7 +24578,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V3-0324": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 2.4e-07, @@ -21660,12 +24591,11 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V3.1": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 9.5e-07, - "cache_read_input_token_cost": 2.16e-07, + "cache_read_input_token_cost": 1.3e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, @@ -21674,7 +24604,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 2.7e-07, @@ -21686,7 +24615,6 @@ "supports_function_calling": true }, "deepinfra/google/gemini-2.5-flash": { - "max_tokens": 1000000, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "input_cost_per_token": 3e-07, @@ -21702,7 +24630,6 @@ "supports_audio_input": true }, "deepinfra/google/gemini-2.5-pro": { - "max_tokens": 1000000, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "input_cost_per_token": 1.25e-06, @@ -21717,7 +24644,6 @@ "supports_audio_input": true }, "deepinfra/google/gemma-3-12b-it": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5e-08, @@ -21729,7 +24655,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-3-27b-it": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 8e-08, @@ -21741,7 +24666,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-3-4b-it": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5e-08, @@ -21753,7 +24677,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 4.9e-08, @@ -21763,7 +24686,6 @@ "supports_tool_choice": false }, "deepinfra/meta-llama/Llama-3.2-3B-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-08, @@ -21774,7 +24696,6 @@ "supports_function_calling": true }, "deepinfra/meta-llama/Llama-3.3-70B-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2.3e-07, @@ -21785,7 +24706,6 @@ "supports_function_calling": true }, "deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -21797,7 +24717,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 2e-07, @@ -21809,7 +24728,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct": { - "max_tokens": 327680, "max_input_tokens": 327680, "max_output_tokens": 327680, "input_cost_per_token": 1e-07, @@ -21821,7 +24739,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-Guard-3-8B": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5.5e-08, @@ -21831,7 +24748,6 @@ "supports_tool_choice": false }, "deepinfra/meta-llama/Llama-Guard-4-12B": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 1.8e-07, @@ -21841,7 +24757,6 @@ "supports_tool_choice": false }, "deepinfra/meta-llama/Meta-Llama-3-8B-Instruct": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 3e-08, @@ -21852,7 +24767,6 @@ "supports_function_calling": true }, "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 4e-07, @@ -21863,7 +24777,6 @@ "supports_function_calling": true }, "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 4e-07, @@ -21875,7 +24788,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3e-08, @@ -21886,7 +24798,6 @@ "supports_function_calling": true }, "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-08, @@ -21898,7 +24809,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/microsoft/WizardLM-2-8x22B": { - "max_tokens": 65536, "max_input_tokens": 65536, "max_output_tokens": 65536, "input_cost_per_token": 4.8e-07, @@ -21908,7 +24818,6 @@ "supports_tool_choice": false }, "deepinfra/microsoft/phi-4": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 7e-08, @@ -21919,10 +24828,9 @@ "supports_function_calling": true }, "deepinfra/mistralai/Mistral-Nemo-Instruct-2407": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 1.9e-08, + "input_cost_per_token": 2.9e-08, "output_cost_per_token": 3e-08, "litellm_provider": "deepinfra", "mode": "chat", @@ -21931,7 +24839,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/mistralai/Mistral-Small-24B-Instruct-2501": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-08, @@ -21942,7 +24849,6 @@ "supports_function_calling": true }, "deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 7.5e-08, @@ -21953,7 +24859,6 @@ "supports_function_calling": true }, "deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 4e-07, @@ -21964,7 +24869,6 @@ "supports_function_calling": true }, "deepinfra/moonshotai/Kimi-K2-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5e-07, @@ -21975,7 +24879,6 @@ "supports_function_calling": true }, "deepinfra/moonshotai/Kimi-K2-Instruct-0905": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 5e-07, @@ -21987,7 +24890,6 @@ "supports_function_calling": true }, "deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 6e-07, @@ -21998,7 +24900,6 @@ "supports_function_calling": true }, "deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -22010,8 +24911,8 @@ }, "deepinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning": { "max_input_tokens": 262144, - "input_cost_per_token": 8e-08, - "output_cost_per_token": 2e-07, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 1.6e-07, "litellm_provider": "deepinfra", "mode": "chat", "source": "https://deepinfra.com/pricing", @@ -22022,7 +24923,6 @@ "supports_prompt_caching": true }, "deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 4e-08, @@ -22033,7 +24933,6 @@ "supports_function_calling": true }, "deepinfra/openai/gpt-oss-120b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3.7e-08, @@ -22045,7 +24944,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/openai/gpt-oss-20b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3e-08, @@ -22057,7 +24955,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-4.5": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 4e-07, @@ -22070,12 +24967,13 @@ "deepseek/deepseek-chat": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 2.8e-08, + "deprecation_date": "2026-07-24", + "deprecation_source": "https://api-docs.deepseek.com/updates", "input_cost_per_token": 2.8e-07, "input_cost_per_token_cache_hit": 2.8e-08, "litellm_provider": "deepseek", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.2e-07, "source": "https://api-docs.deepseek.com/quick_start/pricing", @@ -22098,7 +24996,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-07, "supports_assistant_prefill": true, @@ -22113,7 +25010,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 65536, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.19e-06, "supports_assistant_prefill": true, @@ -22124,12 +25020,13 @@ }, "deepseek/deepseek-reasoner": { "cache_read_input_token_cost": 2.8e-08, + "deprecation_date": "2026-07-24", + "deprecation_source": "https://api-docs.deepseek.com/updates", "input_cost_per_token": 2.8e-07, "input_cost_per_token_cache_hit": 2.8e-08, "litellm_provider": "deepseek", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.2e-07, "source": "https://api-docs.deepseek.com/quick_start/pricing", @@ -22154,7 +25051,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 65536, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.1e-06, "supports_assistant_prefill": true, @@ -22169,7 +25065,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 4e-07, "supports_assistant_prefill": true, @@ -22179,14 +25074,15 @@ "supports_tool_choice": true }, "deepseek.v3-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-1.html", "input_cost_per_token": 5.8e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 163840, - "max_output_tokens": 81920, - "max_tokens": 81920, + "max_input_tokens": 128000, + "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.68e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-1.html", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -22194,17 +25090,22 @@ }, "deepseek.v3.2": { "input_cost_per_token": 6.2e-07, + "input_cost_per_token_batches": 3.1e-07, + "input_cost_per_token_flex": 3.1e-07, + "input_cost_per_token_priority": 1.085e-06, "litellm_provider": "bedrock_converse", - "max_input_tokens": 164000, + "max_input_tokens": 156000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.85e-06, + "output_cost_per_token_batches": 9.25e-07, + "output_cost_per_token_flex": 9.25e-07, + "output_cost_per_token_priority": 3.2375e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.md", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false @@ -22214,7 +25115,6 @@ "litellm_provider": "nlp_cloud", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "completion", "output_cost_per_token": 5e-07 }, @@ -22223,7 +25123,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 98304, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0, "supports_assistant_prefill": true, @@ -22237,7 +25136,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0, "supports_assistant_prefill": true, @@ -22251,7 +25149,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 229376, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0, "supports_assistant_prefill": true, @@ -22264,7 +25161,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 4096, - "max_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - standard version with 2560 dimensions" }, @@ -22276,7 +25172,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 4096, - "max_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - large version with 2048 dimensions" }, @@ -22288,7 +25183,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 4096, - "max_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - text-240915 version with 4096 dimensions" }, @@ -22300,7 +25194,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 4096, - "max_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - text-250515 version with 2048 dimensions" }, @@ -22312,7 +25205,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 4096, - "max_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - text-240715 version with 2560 dimensions" }, @@ -22419,13 +25311,17 @@ "notes": "Firecrawl search pricing: $83 for 100,000 credits, 2 credits per 10 results. Cost = ceiling(limit/10) * 2 * $0.00083" } }, + "webiq/search": { + "input_cost_per_query": 0.007, + "litellm_provider": "webiq", + "mode": "search" + }, "perplexity/search": { "input_cost_per_query": 0.005, "litellm_provider": "perplexity", "mode": "search" }, "sail/moonshotai/Kimi-K3": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 2.5e-06, @@ -22447,7 +25343,6 @@ "source": "https://docs.sailresearch.com/models" }, "sail/zai-org/GLM-5.3": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 9.8e-07, @@ -22469,7 +25364,6 @@ "source": "https://docs.sailresearch.com/models" }, "sail/zai-org/GLM-5.3-Flash": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 1.1e-07, @@ -22491,7 +25385,6 @@ "source": "https://docs.sailresearch.com/models" }, "sail/deepseek-ai/DeepSeek-V4-Pro-0813": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 9.2e-07, @@ -22513,7 +25406,6 @@ "source": "https://docs.sailresearch.com/models" }, "sail/deepseek-ai/DeepSeek-V4-Flash-0731": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 9e-08, @@ -22535,17 +25427,16 @@ "source": "https://docs.sailresearch.com/models" }, "sail/deepseek-ai/DeepSeek-V4.1-Flash": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 3e-07, "cache_read_input_token_cost": 6e-09, - "input_cost_per_token_balanced": 1.2e-07, - "output_cost_per_token_balanced": 4.8e-07, + "input_cost_per_token_balanced": 7e-08, + "output_cost_per_token_balanced": 2.2e-07, "cache_read_input_token_cost_balanced": 5e-09, - "input_cost_per_token_flex": 8e-08, - "output_cost_per_token_flex": 3e-07, + "input_cost_per_token_flex": 5e-08, + "output_cost_per_token_flex": 1.5e-07, "cache_read_input_token_cost_flex": 4e-09, "litellm_provider": "sail", "mode": "chat", @@ -22557,7 +25448,6 @@ "source": "https://docs.sailresearch.com/models" }, "sail/moonshotai/Kimi-K2.6": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1e-06, @@ -22580,7 +25470,6 @@ "source": "https://docs.sailresearch.com/models" }, "sail/google/gemma-4-31B-it": { - "max_tokens": 256000, "max_input_tokens": 256000, "max_output_tokens": 256000, "input_cost_per_token": 4e-07, @@ -22603,7 +25492,6 @@ "source": "https://docs.sailresearch.com/models" }, "sail/nvidia/Gemma-4-31B-IT-NVFP4": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.4e-07, @@ -22626,7 +25514,6 @@ "source": "https://docs.sailresearch.com/models" }, "sail/google/gemma-4-12B-it": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 3e-07, @@ -22648,7 +25535,6 @@ "source": "https://docs.sailresearch.com/models" }, "sail/openai/gpt-oss-120b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 6e-08, @@ -22664,7 +25550,6 @@ "source": "https://docs.sailresearch.com/models" }, "sail/Qwen/Qwen3.6-35B-A3B": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 5e-08, @@ -22716,7 +25601,7 @@ } }, "agentcore/search": { - "input_cost_per_query": 0.0, + "input_cost_per_query": 0.007, "litellm_provider": "agentcore", "mode": "search", "metadata": { @@ -22731,6 +25616,11 @@ "notes": "Grounding with Bing Search (G1 SKU): $14 per 1,000 transactions. Tokens for the Foundry model deployment that runs the grounded search are billed separately on that deployment." } }, + "deepseek/search": { + "input_cost_per_query": 0.00075, + "litellm_provider": "deepseek", + "mode": "search" + }, "tinyfish/search": { "input_cost_per_query": 0.0, "litellm_provider": "tinyfish", @@ -22778,27 +25668,118 @@ ] }, "elevenlabs/eleven_v3": { - "input_cost_per_character": 0.00018, + "input_cost_per_character": 8e-05, "litellm_provider": "elevenlabs", "metadata": { - "calculation": "$0.18/1000 characters (Scale plan pricing, 1 credit per character)", + "calculation": "$0.08/1000 characters (API usage pricing, billed in USD per character)", "notes": "ElevenLabs Eleven v3 - most expressive TTS model with 70+ languages and audio tags support" }, "mode": "audio_speech", - "source": "https://elevenlabs.io/pricing", + "source": "https://elevenlabs.io/pricing/api", "supported_endpoints": [ "/v1/audio/speech" ] }, "elevenlabs/eleven_multilingual_v2": { - "input_cost_per_character": 0.00018, + "input_cost_per_character": 8e-05, "litellm_provider": "elevenlabs", "metadata": { - "calculation": "$0.18/1000 characters (Scale plan pricing, 1 credit per character)", + "calculation": "$0.08/1000 characters (API usage pricing, billed in USD per character)", "notes": "ElevenLabs Eleven Multilingual v2 - default TTS model with 29 languages support" }, "mode": "audio_speech", - "source": "https://elevenlabs.io/pricing", + "source": "https://elevenlabs.io/pricing/api", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "elevenlabs/eleven_v4": { + "input_cost_per_character": 8e-05, + "litellm_provider": "elevenlabs", + "metadata": { + "calculation": "$0.08/1000 characters (API usage pricing, billed in USD per character)", + "notes": "ElevenLabs Eleven v4 - most emotive TTS model with audio tags and 90+ languages" + }, + "mode": "audio_speech", + "source": "https://elevenlabs.io/pricing/api", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "elevenlabs/eleven_v4_turbo": { + "input_cost_per_character": 4e-05, + "litellm_provider": "elevenlabs", + "metadata": { + "calculation": "$0.04/1000 characters (API usage pricing, billed in USD per character)", + "notes": "ElevenLabs Eleven v4 Turbo - low-latency v4 tuned for real-time and agents" + }, + "mode": "audio_speech", + "source": "https://elevenlabs.io/pricing/api", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "elevenlabs/eleven_v3_conversational": { + "input_cost_per_character": 4e-05, + "litellm_provider": "elevenlabs", + "metadata": { + "calculation": "$0.04/1000 characters (API usage pricing, billed in USD per character)", + "notes": "ElevenLabs Eleven v3 Conversational - low-latency v3 tuned for realtime conversation" + }, + "mode": "audio_speech", + "source": "https://elevenlabs.io/pricing/api", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "elevenlabs/eleven_flash_v2_5": { + "input_cost_per_character": 4e-05, + "litellm_provider": "elevenlabs", + "metadata": { + "calculation": "$0.04/1000 characters (API usage pricing, billed in USD per character)", + "notes": "ElevenLabs Eleven Flash v2.5 - low-latency multilingual TTS model" + }, + "mode": "audio_speech", + "source": "https://elevenlabs.io/pricing/api", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "elevenlabs/eleven_flash_v2": { + "input_cost_per_character": 4e-05, + "litellm_provider": "elevenlabs", + "metadata": { + "calculation": "$0.04/1000 characters (API usage pricing, billed in USD per character)", + "notes": "ElevenLabs Eleven Flash v2 - low-latency English-only TTS model" + }, + "mode": "audio_speech", + "source": "https://elevenlabs.io/pricing/api", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "elevenlabs/eleven_turbo_v2_5": { + "input_cost_per_character": 4e-05, + "litellm_provider": "elevenlabs", + "metadata": { + "calculation": "$0.04/1000 characters (API usage pricing, billed in USD per character)", + "notes": "ElevenLabs Eleven Turbo v2.5 - multilingual TTS model" + }, + "mode": "audio_speech", + "source": "https://elevenlabs.io/pricing/api", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "elevenlabs/eleven_turbo_v2": { + "input_cost_per_character": 4e-05, + "litellm_provider": "elevenlabs", + "metadata": { + "calculation": "$0.04/1000 characters (API usage pricing, billed in USD per character)", + "notes": "ElevenLabs Eleven Turbo v2 - English-only TTS model" + }, + "mode": "audio_speech", + "source": "https://elevenlabs.io/pricing/api", "supported_endpoints": [ "/v1/audio/speech" ] @@ -22807,7 +25788,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "cohere", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -22816,7 +25796,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "cohere", "max_input_tokens": 512, - "max_tokens": 512, "metadata": { "notes": "'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead." }, @@ -22829,7 +25808,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "cohere", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "supports_embedding_image_input": true @@ -22838,7 +25816,6 @@ "input_cost_per_token": 0.0001, "litellm_provider": "cohere", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "supports_embedding_image_input": true @@ -22849,7 +25826,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.12e-07, "supports_function_calling": true, @@ -22865,7 +25841,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.84e-07, "supports_function_calling": true, @@ -22875,13 +25850,15 @@ }, "eu.amazon.nova-pro-v1:0": { "cache_read_input_token_cost": 2.625e-07, + "cache_read_input_token_cost_flex": 1.3125e-07, "input_cost_per_token": 1.05e-06, + "input_cost_per_token_flex": 5.25e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 4.2e-06, + "output_cost_per_token_flex": 2.1e-06, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_pdf_input": true, @@ -22895,7 +25872,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-06, "supports_assistant_prefill": true, @@ -22914,11 +25890,11 @@ "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token": 1.1e-06, "deprecation_date": "2026-10-15", + "successor_model": "eu.anthropic.claude-haiku-5-5", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -22935,14 +25911,17 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5.5e-07, - "output_cost_per_token_batches": 2.75e-06 + "output_cost_per_token_batches": 2.75e-06, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "eu.anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -22958,7 +25937,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -22977,7 +25955,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -22997,7 +25974,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_function_calling": true, @@ -23014,7 +25990,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { @@ -23032,7 +26007,12 @@ "supports_tool_choice": true, "supports_vision": true, "prompt_cache_min_tokens": 1024, - "deprecation_date": "2027-01-08" + "deprecation_date": "2027-01-08", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "token_count_model": { + "model": "anthropic.claude-opus-4-1-20250805-v1:0", + "litellm_provider": "bedrock" + } }, "eu.anthropic.claude-opus-4-20250514-v1:0": { "cache_creation_input_token_cost": 1.875e-05, @@ -23041,7 +26021,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { @@ -23064,15 +26043,16 @@ "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2026-10-14", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "eu.anthropic.claude-sonnet-5", "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -23091,7 +26071,11 @@ "supports_vision": true, "bedrock_converse_supports_strict_tools": false, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-20250514-v1:0", + "litellm_provider": "bedrock" + } }, "eu.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.125e-06, @@ -23103,11 +26087,13 @@ "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05, "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, + "deprecation_date": "2027-04-08", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "eu.anthropic.claude-sonnet-5-5", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -23129,27 +26115,35 @@ "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.65e-06, "output_cost_per_token_batches": 8.25e-06, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "eu.meta.llama3-2-1b-instruct-v1:0": { + "deprecation_date": "2026-07-07", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.md", "input_cost_per_token": 1.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.3e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.md", "supports_function_calling": true, "supports_tool_choice": false }, "eu.meta.llama3-2-3b-instruct-v1:0": { + "deprecation_date": "2026-07-07", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.md", "input_cost_per_token": 1.9e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.9e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.md", "supports_function_calling": true, "supports_tool_choice": false }, @@ -23157,10 +26151,10 @@ "input_cost_per_token": 2e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-pixtral-large.md", "supports_function_calling": true, "supports_tool_choice": false }, @@ -23174,8 +26168,11 @@ }, "fal_ai/fal-ai/flux-pro/v1.1": { "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-pro/v1.1 at $0.04 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.04, + "output_cost_per_pixel": 3.814697265625e-08, + "source": "https://fal.ai/models/fal-ai/flux-pro/v1.1", "supported_endpoints": [ "/v1/images/generations" ] @@ -23184,14 +26181,18 @@ "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.06, + "source": "https://fal.ai/models/fal-ai/flux-pro/v1.1-ultra", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux/schnell": { "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux/schnell at $0.003 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.003, + "output_cost_per_pixel": 2.86102294921875e-09, + "source": "https://fal.ai/models/fal-ai/flux/schnell", "supported_endpoints": [ "/v1/images/generations" ] @@ -23267,6 +26268,7 @@ }, "fal_ai/minimax/h3/text-to-video": { "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 2k rate"}, "mode": "video_generation", "output_cost_per_second": 0.13, "output_cost_per_second_480p": 0.05, @@ -23376,6 +26378,7 @@ "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.06, + "source": "https://fal.ai/models/fal-ai/ideogram/v3", "supported_endpoints": [ "/v1/images/generations" ] @@ -23414,8 +26417,11 @@ }, "fal_ai/fal-ai/stable-diffusion-v35-medium": { "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/stable-diffusion-v35-medium at $0.02 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", - "output_cost_per_image": 0.0398, + "output_cost_per_image": 0.02, + "output_cost_per_pixel": 1.9073486328125e-08, + "source": "https://fal.ai/models/fal-ai/stable-diffusion-v35-medium", "supported_endpoints": [ "/v1/images/generations" ] @@ -23423,7 +26429,8 @@ "fal_ai/fal-ai/nano-banana": { "litellm_provider": "fal_ai", "mode": "image_generation", - "output_cost_per_image": 0.039, + "output_cost_per_image": 0.0398, + "source": "https://fal.ai/models/fal-ai/nano-banana", "supported_endpoints": [ "/v1/images/generations" ] @@ -23431,7 +26438,8 @@ "fal_ai/fal-ai/gemini-25-flash-image": { "litellm_provider": "fal_ai", "mode": "image_generation", - "output_cost_per_image": 0.039, + "output_cost_per_image": 0.0398, + "source": "https://fal.ai/models/fal-ai/gemini-25-flash-image", "supported_endpoints": [ "/v1/images/generations" ] @@ -25362,9 +28370,7 @@ }, "fal_ai/fal-ai/flux/dev": { "litellm_provider": "fal_ai", - "metadata": { - "notes": "fal bills FLUX.1 [dev] at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price is the fallback when dimensions are unavailable" - }, + "metadata": {"notes":"fal bills fal-ai/flux/dev at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.025, "output_cost_per_pixel": 2.384185791015625e-08, @@ -25396,16 +28402,16 @@ }, "fal_ai/fal-ai/flux-lora-depth": { "litellm_provider": "fal_ai", - "metadata": { - "notes": "fal bills fal-ai/flux-lora-depth at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries" - }, + "metadata": {"notes":"fal bills fal-ai/flux-lora-depth at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/flux-lora-depth", "supported_endpoints": [ - "/v1/images/edits" - ] + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true }, "fal_ai/fal-ai/moondream3-preview/query": { "input_cost_per_token": 4e-07, @@ -25423,14 +28429,12 @@ "litellm_provider": "featherless_ai", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat" }, "featherless_ai/featherless-ai/Qwerky-QwQ-32B": { "litellm_provider": "featherless_ai", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat" }, "fireworks-ai-4.1b-to-16b": { @@ -25478,7 +28482,6 @@ "input_cost_per_token": 1.6e-08, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://fireworks.ai/pricing" @@ -25488,7 +28491,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 65536, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://fireworks.ai/pricing", @@ -25499,9 +28501,8 @@ "fireworks_ai/accounts/fireworks/models/deepseek-r1": { "input_cost_per_token": 3e-06, "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, + "max_input_tokens": 163840, "max_output_tokens": 20480, - "max_tokens": 20480, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://fireworks.ai/pricing", @@ -25511,9 +28512,8 @@ "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528": { "input_cost_per_token": 3e-06, "litellm_provider": "fireworks_ai", - "max_input_tokens": 160000, + "max_input_tokens": 163840, "max_output_tokens": 160000, - "max_tokens": 160000, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://fireworks.ai/pricing", @@ -25523,9 +28523,8 @@ "fireworks_ai/accounts/fireworks/models/deepseek-r1-basic": { "input_cost_per_token": 5.5e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, + "max_input_tokens": 163840, "max_output_tokens": 20480, - "max_tokens": 20480, "mode": "chat", "output_cost_per_token": 2.19e-06, "source": "https://fireworks.ai/pricing", @@ -25535,9 +28534,8 @@ "fireworks_ai/accounts/fireworks/models/deepseek-v3": { "input_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, + "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://fireworks.ai/pricing", @@ -25549,7 +28547,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://fireworks.ai/models/fireworks/deepseek-v3-0324", @@ -25561,7 +28558,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.68e-06, "source": "https://fireworks.ai/pricing", @@ -25574,7 +28570,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.68e-06, "source": "https://fireworks.ai/pricing", @@ -25587,7 +28582,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.68e-06, "source": "https://fireworks.ai/models/fireworks/deepseek-v3p2", @@ -25598,14 +28592,16 @@ }, "fireworks_ai/accounts/fireworks/models/deepseek-v4-flash": { "cache_read_input_token_cost": 2.8e-08, + "deprecation_date": "2026-08-14", + "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md", "input_cost_per_token": 1.4e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://docs.fireworks.ai/serverless/pricing", + "successor_model": "fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -25621,7 +28617,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.96e-06, "output_cost_per_token_priority": 4.95e-06, @@ -25641,7 +28636,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.96e-06, "output_cost_per_token_priority": 4.95e-06, @@ -25657,7 +28651,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://fireworks.ai/pricing", @@ -25668,9 +28661,8 @@ "fireworks_ai/accounts/fireworks/models/glm-4p5": { "input_cost_per_token": 5.5e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, + "max_input_tokens": 131072, "max_output_tokens": 96000, - "max_tokens": 96000, "mode": "chat", "output_cost_per_token": 2.19e-06, "source": "https://fireworks.ai/models/fireworks/glm-4p5", @@ -25682,9 +28674,8 @@ "fireworks_ai/accounts/fireworks/models/glm-4p5-air": { "input_cost_per_token": 2.2e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, + "max_input_tokens": 131072, "max_output_tokens": 96000, - "max_tokens": 96000, "mode": "chat", "output_cost_per_token": 8.8e-07, "source": "https://artificialanalysis.ai/models/glm-4-5-air", @@ -25697,9 +28688,8 @@ "input_cost_per_token": 5.5e-07, "output_cost_per_token": 2.19e-06, "litellm_provider": "fireworks_ai", - "max_input_tokens": 202800, + "max_input_tokens": 202752, "max_output_tokens": 202800, - "max_tokens": 202800, "mode": "chat", "source": "https://fireworks.ai/pricing", "supports_function_calling": true, @@ -25711,9 +28701,8 @@ "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 6e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 202800, + "max_input_tokens": 202752, "max_output_tokens": 202800, - "max_tokens": 202800, "mode": "chat", "output_cost_per_token": 2.2e-06, "source": "https://fireworks.ai/models/fireworks/glm-4p7", @@ -25726,9 +28715,8 @@ "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "fireworks_ai", - "max_input_tokens": 202800, + "max_input_tokens": 202752, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -25742,12 +28730,12 @@ "cache_read_input_token_cost": 1.4e-07, "cache_read_input_token_cost_priority": 1.75e-07, "deprecation_date": "2026-09-25", + "successor_model": "fireworks_ai/accounts/fireworks/models/glm-5p3", "input_cost_per_token": 1.4e-06, "input_cost_per_token_priority": 1.75e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_priority": 5.5e-06, @@ -25761,16 +28749,17 @@ "fireworks_ai/accounts/fireworks/models/gpt-oss-120b": { "cache_read_input_token_cost": 1.5e-08, "cache_read_input_token_cost_priority": 1.8e-08, + "deprecation_date": "2026-11-07", + "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md", "input_cost_per_token": 1.5e-07, "input_cost_per_token_priority": 1.8e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_priority": 7.2e-07, - "source": "https://api.fireworks.ai/v1/serverless/models", + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -25783,7 +28772,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -25798,7 +28786,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://fireworks.ai/models/fireworks/kimi-k2-instruct", @@ -25811,7 +28798,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://app.fireworks.ai/models/fireworks/kimi-k2-instruct-0905", @@ -25824,7 +28810,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://fireworks.ai/pricing", @@ -25839,7 +28824,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://fireworks.ai/pricing", @@ -25856,7 +28840,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "output_cost_per_token_priority": 6e-06, @@ -25876,7 +28859,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "output_cost_per_token_priority": 6e-06, @@ -25890,9 +28872,8 @@ "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct": { "input_cost_per_token": 3e-06, "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, + "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://fireworks.ai/pricing", @@ -25903,9 +28884,8 @@ "fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct": { "input_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 16384, + "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://fireworks.ai/pricing", @@ -25916,9 +28896,8 @@ "fireworks_ai/accounts/fireworks/models/llama-v3p2-11b-vision-instruct": { "input_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 16384, + "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://fireworks.ai/pricing", @@ -25930,9 +28909,8 @@ "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct": { "input_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 16384, + "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://fireworks.ai/pricing", @@ -25943,9 +28921,8 @@ "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b-instruct": { "input_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 16384, + "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://fireworks.ai/pricing", @@ -25956,9 +28933,8 @@ "fireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instruct": { "input_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 16384, + "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://fireworks.ai/pricing", @@ -25971,7 +28947,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8.8e-07, "source": "https://fireworks.ai/pricing", @@ -25983,7 +28958,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://fireworks.ai/pricing", @@ -25994,9 +28968,8 @@ "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 3e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 204800, + "max_input_tokens": 196608, "max_output_tokens": 204800, - "max_tokens": 204800, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://fireworks.ai/models/fireworks/minimax-m2p1", @@ -26012,23 +28985,42 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 512000, "max_output_tokens": 512000, - "max_tokens": 512000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_priority": 1.8e-06, - "source": "https://api.fireworks.ai/v1/serverless/models", + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/routers/minimax-latest": { + "cache_read_input_token_cost": 6e-08, + "cache_read_input_token_cost_priority": 9e-08, + "input_cost_per_token": 3e-07, + "input_cost_per_token_priority": 4.5e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 512000, + "max_output_tokens": 512000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_priority": 1.8e-06, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/minimax-latest": { + "alias_of": "fireworks_ai/accounts/fireworks/models/minimax-m3" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf": { "input_cost_per_token": 1.2e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 65536, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://fireworks.ai/pricing", @@ -26041,7 +29033,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://fireworks.ai/pricing", @@ -26054,7 +29045,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://fireworks.ai/pricing", @@ -26067,7 +29057,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://fireworks.ai/pricing", @@ -26077,14 +29066,16 @@ }, "fireworks_ai/deepseek-v4-flash": { "cache_read_input_token_cost": 2.8e-08, + "deprecation_date": "2026-08-14", + "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md", "input_cost_per_token": 1.4e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://docs.fireworks.ai/serverless/pricing", + "successor_model": "fireworks_ai/deepseek-v4-flash-0731", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -26095,9 +29086,8 @@ "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 6e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 202800, + "max_input_tokens": 202752, "max_output_tokens": 202800, - "max_tokens": 202800, "mode": "chat", "output_cost_per_token": 2.2e-06, "source": "https://fireworks.ai/models/fireworks/glm-4p7", @@ -26110,9 +29100,8 @@ "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "fireworks_ai", - "max_input_tokens": 202800, + "max_input_tokens": 202752, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -26128,7 +29117,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 202800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8.8e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -26142,12 +29130,12 @@ "cache_read_input_token_cost": 1.4e-07, "cache_read_input_token_cost_priority": 1.75e-07, "deprecation_date": "2026-09-25", + "successor_model": "fireworks_ai/glm-5p3", "input_cost_per_token": 1.4e-06, "input_cost_per_token_priority": 1.75e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_priority": 5.5e-06, @@ -26161,16 +29149,17 @@ "fireworks_ai/gpt-oss-120b": { "cache_read_input_token_cost": 1.5e-08, "cache_read_input_token_cost_priority": 1.8e-08, + "deprecation_date": "2026-11-07", + "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md", "input_cost_per_token": 1.5e-07, "input_cost_per_token_priority": 1.8e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_priority": 7.2e-07, - "source": "https://api.fireworks.ai/v1/serverless/models", + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -26183,7 +29172,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -26199,7 +29187,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://fireworks.ai/pricing", @@ -26216,7 +29203,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "output_cost_per_token_priority": 6e-06, @@ -26230,14 +29216,15 @@ "fireworks_ai/kimi-k2p6-fast": { "cache_read_input_token_cost": 3e-07, "deprecation_date": "2026-08-27", + "deprecation_source": "https://docs.fireworks.ai/changelog.md", "input_cost_per_token": 2e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://docs.fireworks.ai/changelog.md", + "successor_model": "fireworks_ai/kimi-k2p6", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -26253,7 +29240,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "output_cost_per_token_priority": 6e-06, @@ -26267,14 +29253,15 @@ "fireworks_ai/kimi-k2p7-code-fast": { "cache_read_input_token_cost": 3.8e-07, "deprecation_date": "2026-08-27", + "deprecation_source": "https://docs.fireworks.ai/changelog.md", "input_cost_per_token": 1.9e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://docs.fireworks.ai/changelog.md", + "successor_model": "fireworks_ai/kimi-k2p7-code", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -26285,9 +29272,8 @@ "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 3e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 204800, + "max_input_tokens": 196608, "max_output_tokens": 204800, - "max_tokens": 204800, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://fireworks.ai/models/fireworks/minimax-m2p1", @@ -26303,7 +29289,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 512000, "max_output_tokens": 512000, - "max_tokens": 512000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_priority": 1.8e-06, @@ -26312,7 +29297,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true }, "fireworks_ai/qwen3p7-plus": { "cache_read_input_token_cost": 8e-08, @@ -26320,7 +29305,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://api.fireworks.ai/v1/serverless/models", @@ -26334,7 +29318,6 @@ "input_cost_per_token": 8e-09, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://fireworks.ai/pricing" @@ -26343,7 +29326,6 @@ "input_cost_per_token": 8e-09, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://fireworks.ai/pricing" @@ -26352,7 +29334,6 @@ "input_cost_per_token": 8e-09, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://fireworks.ai/pricing" @@ -26361,7 +29342,6 @@ "input_cost_per_token": 1.6e-08, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://fireworks.ai/pricing" @@ -26370,7 +29350,6 @@ "litellm_provider": "friendliai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 5e-07, "cache_read_input_token_cost": 3e-08, @@ -26398,7 +29377,6 @@ "litellm_provider": "friendliai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "input_cost_per_token": 1.26e-06, "output_cost_per_token": 3.96e-06, "cache_read_input_token_cost": 2.34e-07, @@ -26426,7 +29404,6 @@ "litellm_provider": "friendliai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "input_cost_per_token": 1.4e-07, "output_cost_per_token": 4e-07, "supports_prompt_caching": false, @@ -26449,7 +29426,6 @@ "litellm_provider": "friendliai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "input_cost_per_token": 1.4e-06, "output_cost_per_token": 4.4e-06, "cache_read_input_token_cost": 2.6e-07, @@ -26472,59 +29448,10 @@ "comment": "Open flagship GLM for long-horizon coding agents and million-token context work", "source": "https://api.friendli.ai/serverless/v1/models" }, - "friendliai/deepseek-ai/DeepSeek-V3.2": { - "litellm_provider": "friendliai", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "cache_read_input_token_cost": 2.5e-07, - "supports_prompt_caching": true, - "supports_reasoning": true, - "reasoning_effort_levels": [], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_native_structured_output": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_image_input": false, - "supports_video_input": false, - "mode": "chat", - "comment": "DeepSeek chat model for instruction following, coding, and analysis", - "source": "https://api.friendli.ai/serverless/v1/models" - }, - "friendliai/MiniMaxAI/MiniMax-M2.5": { - "litellm_provider": "friendliai", - "max_input_tokens": 196608, - "max_output_tokens": 196608, - "max_tokens": 196608, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "cache_read_input_token_cost": 6e-08, - "supports_prompt_caching": true, - "supports_reasoning": true, - "reasoning_effort_levels": [], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_native_structured_output": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_image_input": false, - "supports_video_input": false, - "mode": "chat", - "comment": "Prior MiniMax coding model for agent workflows, office edits, and automation", - "source": "https://api.friendli.ai/serverless/v1/models" - }, "friendliai/zai-org/GLM-5.1": { "litellm_provider": "friendliai", "max_input_tokens": 202752, "max_output_tokens": 202752, - "max_tokens": 202752, "input_cost_per_token": 1.4e-06, "output_cost_per_token": 4.4e-06, "cache_read_input_token_cost": 2.6e-07, @@ -26542,29 +29469,32 @@ "supports_video_input": false, "mode": "chat", "comment": "Strong GLM coding model for agentic engineering, terminals, and repository generation", - "source": "https://api.friendli.ai/serverless/v1/models" + "source": "https://api.friendli.ai/serverless/v1/models", + "deprecation_date": "2026-11-20" }, "ft:babbage-002": { - "deprecation_date": "2026-10-23", + "deprecation_date": "2026-09-28", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 1.6e-06, "input_cost_per_token_batches": 8e-07, "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 9e-07, "source": "https://developers.openai.com/api/docs/pricing" }, "ft:davinci-002": { - "deprecation_date": "2026-10-23", + "deprecation_date": "2026-09-28", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 1.2e-05, "input_cost_per_token_batches": 6e-06, "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 1.2e-05, "output_cost_per_token_batches": 6e-06, @@ -26572,14 +29502,16 @@ }, "ft:gpt-3.5-turbo": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 3e-06, "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-06, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 3e-06, "source": "https://developers.openai.com/api/docs/pricing", "supports_system_messages": true, @@ -26587,49 +29519,57 @@ }, "ft:gpt-3.5-turbo-0125": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 3e-06, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-06, + "fedramp_uplift_multiplier": 1.1, "supports_system_messages": true, "supports_tool_choice": true }, "ft:gpt-3.5-turbo-0613": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "ft:gpt-3.5-turbo", "input_cost_per_token": 3e-06, "litellm_provider": "openai", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-06, + "fedramp_uplift_multiplier": 1.1, "supports_system_messages": true, "supports_tool_choice": true }, "ft:gpt-3.5-turbo-1106": { - "deprecation_date": "2026-10-23", + "deprecation_date": "2026-09-28", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 3e-06, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-06, + "fedramp_uplift_multiplier": 1.1, "supports_system_messages": true, "supports_tool_choice": true }, "ft:gpt-4-0613": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 3e-05, "litellm_provider": "openai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-05, + "fedramp_uplift_multiplier": 1.1, "source": "OpenAI needs to add pricing for this ft model, will be updated when added by OpenAI. Defaulting to base model pricing", "supports_function_calling": true, "supports_system_messages": true, @@ -26638,14 +29578,17 @@ "ft:gpt-4o-2024-08-06": { "cache_read_input_token_cost": 1.875e-06, "cache_read_input_token_cost_batches": 9e-07, + "deprecation_date": "2027-01-14", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna", "input_cost_per_token": 3.75e-06, "input_cost_per_token_batches": 2.225e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 1.25e-05, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, @@ -26659,13 +29602,16 @@ }, "ft:gpt-4o-2024-11-20": { "cache_creation_input_token_cost": 1.875e-06, + "deprecation_date": "2027-01-14", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna", "input_cost_per_token": 3.75e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-05, + "fedramp_uplift_multiplier": 1.1, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -26677,14 +29623,17 @@ "ft:gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 1.5e-07, "cache_read_input_token_cost_batches": 7.5e-08, + "deprecation_date": "2027-01-14", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna", "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 6e-07, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, @@ -26698,14 +29647,17 @@ "ft:gpt-4.1-2025-04-14": { "cache_read_input_token_cost": 7.5e-07, "cache_read_input_token_cost_batches": 5e-07, + "deprecation_date": "2027-01-14", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna", "input_cost_per_token": 3e-06, "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.2e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 6e-06, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, @@ -26718,14 +29670,17 @@ "ft:gpt-4.1-mini-2025-04-14": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1e-07, + "deprecation_date": "2027-01-14", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna", "input_cost_per_token": 8e-07, "input_cost_per_token_batches": 4e-07, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3.2e-06, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 1.6e-06, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, @@ -26739,14 +29694,16 @@ "cache_read_input_token_cost": 5e-08, "cache_read_input_token_cost_batches": 2.5e-08, "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-luna", "input_cost_per_token": 2e-07, "input_cost_per_token_batches": 1e-07, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-07, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 4e-07, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, @@ -26760,14 +29717,16 @@ "cache_read_input_token_cost": 1e-06, "cache_read_input_token_cost_batches": 5e-07, "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 4e-06, "input_cost_per_token_batches": 2e-06, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 1.6e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 8e-06, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, @@ -26779,20 +29738,38 @@ }, "gemini-2.5-flash": { "cache_read_input_audio_token_cost": 1e-07, - "deprecation_date": "2026-10-20", + "cache_read_input_audio_token_cost_priority": 1.8e-07, "cache_read_input_token_cost": 3e-08, "cache_read_input_token_cost_flex": 3e-08, "cache_read_input_token_cost_priority": 5.4e-08, + "deprecation_date": "2026-10-20", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token": 1e-06, + "input_cost_per_audio_token_above_200k_tokens": 3e-07, + "input_cost_per_audio_token_above_200k_tokens_batches": 5e-07, + "input_cost_per_audio_token_above_200k_tokens_flex": 5e-07, + "input_cost_per_audio_token_above_200k_tokens_priority": 1.8e-06, + "input_cost_per_audio_token_batches": 5e-07, + "input_cost_per_audio_token_flex": 5e-07, + "input_cost_per_audio_token_priority": 1.8e-06, "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.4e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_priority": 4.5e-06, + "search_context_cost_per_query": {"search_context_size_low":0.035,"search_context_size_medium":0.035,"search_context_size_high":0.035}, + "search_free_requests": {"count":1500,"period":"day","shared_group":"gemini-2-flash"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "successor_model": "gemini-3.8-flash", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -26809,6 +29786,7 @@ ], "supports_audio_output": false, "supports_function_calling": true, + "supports_image_size": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -26818,25 +29796,12 @@ "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - }, - "google_maps_grounding_cost_per_query": 0.025, - "input_cost_per_audio_token_batches": 5e-07, - "input_cost_per_token_batches": 1.5e-07, - "input_cost_per_token_flex": 1.5e-07, - "input_cost_per_token_priority": 5.4e-07, - "input_cost_per_audio_token_priority": 1.8e-06, - "output_cost_per_token_batches": 1.25e-06, - "output_cost_per_token_flex": 1.25e-06, - "output_cost_per_token_priority": 4.5e-06, - "supports_image_size": false + "supports_web_search": true }, "gemini-2.5-flash-image": { "deprecation_date": "2027-03-15", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "successor_model": "gemini-3.1-flash-lite-image", "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, @@ -26844,10 +29809,10 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.039, "output_cost_per_image_token": 3e-05, + "output_cost_per_image_token_batches": 1.5e-05, "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 1.25e-06, @@ -26856,7 +29821,8 @@ "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", + "/v1/images/generations", + "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ @@ -26890,7 +29856,6 @@ "cache_read_input_token_cost_batches": 1e-07, "cache_read_input_token_cost_flex": 1e-07, "cache_read_input_token_cost_priority": 3.6e-07, - "deprecation_date": "2027-05-28", "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, @@ -26901,20 +29866,24 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, + "output_cost_per_image_token_batches": 6e-05, + "output_cost_per_image_token_priority": 0.000216, "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "output_cost_per_token_batches": 6e-06, "output_cost_per_token_flex": 6e-06, "output_cost_per_token_priority": 2.16e-05, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", + "/v1/images/generations", + "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ @@ -26931,11 +29900,6 @@ "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, "web_search_billing_unit": "per_query" }, "gemini-3-pro-image-preview": { @@ -26953,19 +29917,21 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, + "output_cost_per_image_token_batches": 6e-05, + "output_cost_per_image_token_priority": 0.000216, "output_cost_per_token": 1.2e-05, "output_cost_per_token_priority": 2.16e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "output_cost_per_token_batches": 6e-06, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", + "/v1/images/generations", + "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ @@ -26987,31 +29953,38 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-image": { "cache_read_input_token_cost": 5e-08, "cache_read_input_token_cost_batches": 2.5e-08, "cache_read_input_token_cost_flex": 2.5e-08, - "deprecation_date": "2027-05-28", + "cache_read_input_token_cost_priority": 9e-08, "input_cost_per_image": 0.00056, "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "input_cost_per_token_flex": 2.5e-07, + "input_cost_per_token_priority": 9e-07, "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 65536, + "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.0672, "output_cost_per_image_token": 6e-05, + "output_cost_per_image_token_batches": 3e-05, + "output_cost_per_image_token_priority": 0.000108, "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, + "output_cost_per_token_priority": 5.4e-06, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", + "/v1/images/generations", + "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ @@ -27028,11 +30001,6 @@ "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-image-preview": { @@ -27044,16 +30012,18 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.0672, "output_cost_per_image_token": 6e-05, + "output_cost_per_image_token_batches": 3e-05, + "output_cost_per_image_token_priority": 0.000108, "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", + "/v1/images/generations", + "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ @@ -27075,30 +30045,36 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-lite-image": { "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, + "cache_read_input_token_cost_priority": 4.5e-08, "input_cost_per_image": 0.00028, "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_flex": 1.25e-07, + "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "image_generation", "output_cost_per_image": 0.0336, "output_cost_per_image_token": 3e-05, + "output_cost_per_image_token_batches": 1.5e-05, + "output_cost_per_image_token_priority": 5.4e-05, "output_cost_per_token": 1.5e-06, "output_cost_per_token_batches": 7.5e-07, "output_cost_per_token_flex": 7.5e-07, + "output_cost_per_token_priority": 2.7e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", + "/v1/images/generations", + "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ @@ -27126,7 +30102,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 1.5e-06, "output_cost_per_token": 1.5e-06, @@ -27165,33 +30140,45 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, "gemini-3.1-flash-lite": { "cache_read_input_audio_token_cost": 5e-08, - "deprecation_date": "2027-05-07", + "cache_read_input_audio_token_cost_batches": 2.5e-08, + "cache_read_input_audio_token_cost_flex": 2.5e-08, + "cache_read_input_audio_token_cost_priority": 9e-08, "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 5e-07, + "input_cost_per_audio_token_above_200k_tokens": 5e-07, + "input_cost_per_audio_token_above_200k_tokens_batches": 2.5e-07, + "input_cost_per_audio_token_above_200k_tokens_flex": 2.5e-07, + "input_cost_per_audio_token_above_200k_tokens_priority": 9e-07, + "input_cost_per_audio_token_batches": 2.5e-07, + "input_cost_per_audio_token_flex": 2.5e-07, + "input_cost_per_audio_token_priority": 9e-07, "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_flex": 1.25e-07, "input_cost_per_token_priority": 4.5e-07, - "input_cost_per_audio_token_priority": 9e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 1.5e-06, "output_cost_per_token": 1.5e-06, "output_cost_per_token_batches": 7.5e-07, "output_cost_per_token_flex": 7.5e-07, "output_cost_per_token_priority": 2.7e-06, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "successor_model": "gemini-3.5-flash-lite", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -27209,6 +30196,7 @@ "supports_audio_input": true, "supports_audio_output": false, "supports_function_calling": true, + "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -27220,22 +30208,14 @@ "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_audio_token_batches": 2.5e-07 + "web_search_billing_unit": "per_query" }, "gemini-3.5-flash-lite": { - "deprecation_date": "2027-07-21", "cache_read_input_token_cost": 3e-08, "cache_read_input_token_cost_batches": 1.5e-08, "cache_read_input_token_cost_flex": 1.5e-08, "cache_read_input_token_cost_priority": 5.4e-08, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, @@ -27243,13 +30223,14 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 1.25e-06, "output_cost_per_token_flex": 1.25e-06, "output_cost_per_token_priority": 4.5e-06, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -27267,26 +30248,22 @@ ], "supports_audio_input": true, "supports_audio_output": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "web_search_billing_unit": "per_query" }, "deep-research-pro-preview-12-2025": { "cache_read_input_token_cost": 2e-07, @@ -27297,8 +30274,7 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "image_generation", + "mode": "chat", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_token": 1.2e-05, @@ -27326,20 +30302,38 @@ }, "gemini-2.5-flash-lite": { "cache_read_input_audio_token_cost": 3e-08, - "deprecation_date": "2026-10-20", + "cache_read_input_audio_token_cost_priority": 5.4e-08, "cache_read_input_token_cost": 1e-08, "cache_read_input_token_cost_flex": 1e-08, "cache_read_input_token_cost_priority": 1.8e-08, + "deprecation_date": "2026-10-20", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token": 3e-07, + "input_cost_per_audio_token_above_200k_tokens": 3e-07, + "input_cost_per_audio_token_above_200k_tokens_batches": 5e-08, + "input_cost_per_audio_token_above_200k_tokens_flex": 5e-08, + "input_cost_per_audio_token_above_200k_tokens_priority": 5.4e-07, + "input_cost_per_audio_token_batches": 5e-08, + "input_cost_per_audio_token_flex": 5e-08, + "input_cost_per_audio_token_priority": 5.4e-07, "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "input_cost_per_token_flex": 5e-08, + "input_cost_per_token_priority": 1.8e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 4e-07, "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07, + "output_cost_per_token_flex": 2e-07, + "output_cost_per_token_priority": 7.2e-07, + "search_context_cost_per_query": {"search_context_size_low":0.035,"search_context_size_medium":0.035,"search_context_size_high":0.035}, + "search_free_requests": {"count":1500,"period":"day","shared_group":"gemini-2-flash"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "successor_model": "gemini-3.8-flash", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -27356,6 +30350,7 @@ ], "supports_audio_output": false, "supports_function_calling": true, + "supports_image_size": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -27365,22 +30360,7 @@ "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - }, - "google_maps_grounding_cost_per_query": 0.025, - "input_cost_per_audio_token_batches": 5e-08, - "input_cost_per_token_batches": 5e-08, - "input_cost_per_token_flex": 5e-08, - "input_cost_per_token_priority": 1.8e-07, - "input_cost_per_audio_token_priority": 5.4e-07, - "output_cost_per_token_batches": 2e-07, - "output_cost_per_token_flex": 2e-07, - "output_cost_per_token_priority": 7.2e-07, - "supports_image_size": false + "supports_web_search": true }, "gemini-2.5-flash-lite-preview-09-2025": { "cache_read_input_token_cost": 1e-08, @@ -27389,7 +30369,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_reasoning_token": 4e-07, "output_cost_per_token": 4e-07, @@ -27425,6 +30404,7 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false }, @@ -27435,7 +30415,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -27471,17 +30450,19 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false }, "gemini-live-2.5-flash-native-audio": { "deprecation_date": "2026-12-13", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "successor_model": "gemini-3.8-live", "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -27527,7 +30508,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -27571,7 +30551,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -27611,23 +30590,39 @@ "gemini_native_audio": true }, "gemini-2.5-pro": { - "deprecation_date": "2026-10-20", "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 4.5e-07, "cache_read_input_token_cost_flex": 1.25e-07, "cache_read_input_token_cost_priority": 2.25e-07, + "deprecation_date": "2026-10-20", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 1.25e-06, + "input_cost_per_token_above_200k_tokens_flex": 1.25e-06, + "input_cost_per_token_above_200k_tokens_priority": 4.5e-06, + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_flex": 6.25e-07, + "input_cost_per_token_priority": 2.25e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, + "output_cost_per_token_above_200k_tokens_batches": 7.5e-06, + "output_cost_per_token_above_200k_tokens_flex": 7.5e-06, + "output_cost_per_token_above_200k_tokens_priority": 2.7e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_flex": 5e-06, + "output_cost_per_token_priority": 1.8e-05, + "prompt_cache_min_tokens": 2048.0, + "search_context_cost_per_query": {"search_context_size_low":0.035,"search_context_size_medium":0.035,"search_context_size_high":0.035}, + "search_free_requests": {"count":10000,"period":"day","shared_group":"gemini-2.5-pro"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "successor_model": "gemini-3.8-flash", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" @@ -27645,46 +30640,44 @@ "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, - "prompt_cache_min_tokens": 2048, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - }, - "google_maps_grounding_cost_per_query": 0.025, - "input_cost_per_token_above_200k_tokens_priority": 4.5e-06, - "input_cost_per_token_batches": 6.25e-07, - "input_cost_per_token_flex": 6.25e-07, - "input_cost_per_token_priority": 2.25e-06, - "output_cost_per_token_above_200k_tokens_priority": 2.7e-05, - "output_cost_per_token_batches": 5e-06, - "output_cost_per_token_flex": 5e-06, - "output_cost_per_token_priority": 1.8e-05 + "supports_web_search": true }, "gemini-3.1-pro-preview": { - "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_priority": 3.6e-07, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "input_cost_per_token_above_200k_tokens_flex": 2e-06, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.6e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", + "output_cost_per_image": 0.00012, "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, + "output_cost_per_token_above_200k_tokens_batches": 9e-06, + "output_cost_per_token_above_200k_tokens_flex": 9e-06, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "output_cost_per_token_batches": 6e-06, - "output_cost_per_image": 0.00012, + "output_cost_per_token_flex": 6e-06, + "output_cost_per_token_priority": 2.16e-05, + "prompt_cache_min_tokens": 4096.0, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -27702,46 +30695,29 @@ ], "supports_audio_input": true, "supports_function_calling": true, + "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_url_context": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 3.6e-06, - "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, - "output_cost_per_token_priority": 2.16e-05, - "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, - "cache_read_input_token_cost_priority": 3.6e-07, - "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, - "cache_read_input_token_cost_flex": 2e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_token_flex": 1e-06, - "output_cost_per_token_flex": 6e-06 + "web_search_billing_unit": "per_query" }, "gemini-3.1-pro-preview-customtools": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, @@ -27780,20 +30756,19 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, "vertex_ai/gemini-3-pro-preview": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, @@ -27836,20 +30811,37 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-3-flash-preview": { "cache_read_input_audio_token_cost": 1e-07, + "cache_read_input_audio_token_cost_priority": 1.8e-07, "cache_read_input_token_cost": 5e-08, - "cache_read_input_token_cost_flex": 5e-08, - "input_cost_per_token": 5e-07, + "cache_read_input_token_cost_priority": 9e-08, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 1e-06, + "input_cost_per_audio_token_above_200k_tokens": 1e-06, + "input_cost_per_audio_token_above_200k_tokens_batches": 5e-07, + "input_cost_per_audio_token_above_200k_tokens_flex": 5e-07, + "input_cost_per_audio_token_above_200k_tokens_priority": 1.8e-06, + "input_cost_per_audio_token_batches": 5e-07, + "input_cost_per_audio_token_flex": 5e-07, + "input_cost_per_audio_token_priority": 1.8e-06, + "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "input_cost_per_token_flex": 2.5e-07, + "input_cost_per_token_priority": 9e-07, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-06, + "output_cost_per_token_batches": 1.5e-06, + "output_cost_per_token_flex": 1.5e-06, + "output_cost_per_token_priority": 5.4e-06, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -27866,7 +30858,9 @@ "text" ], "supports_audio_input": true, + "supports_computer_use": true, "supports_function_calling": true, + "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -27876,40 +30870,35 @@ "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 9e-07, - "input_cost_per_audio_token_priority": 1.8e-06, - "output_cost_per_token_priority": 5.4e-06, - "cache_read_input_token_cost_priority": 9e-08, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_audio_token_batches": 5e-07, - "input_cost_per_token_batches": 2.5e-07, - "input_cost_per_token_flex": 2.5e-07, - "output_cost_per_token_batches": 1.5e-06, - "output_cost_per_token_flex": 1.5e-06 + "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-3.5-flash": { - "prompt_cache_min_tokens": 4096, - "deprecation_date": "2027-05-19", "cache_read_input_token_cost": 1.5e-07, "cache_read_input_token_cost_batches": 7.5e-08, - "input_cost_per_token": 1.5e-06, + "cache_read_input_token_cost_flex": 7.5e-08, + "cache_read_input_token_cost_priority": 2.7e-07, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 1.5e-06, + "input_cost_per_audio_token_priority": 2.7e-06, + "input_cost_per_token": 1.5e-06, + "input_cost_per_token_batches": 7.5e-07, + "input_cost_per_token_flex": 7.5e-07, + "input_cost_per_token_priority": 2.7e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, + "output_cost_per_token_batches": 4.5e-06, + "output_cost_per_token_flex": 4.5e-06, + "output_cost_per_token_priority": 1.62e-05, + "prompt_cache_min_tokens": 4096.0, "regional_endpoint_uplift_multiplier": 1.1, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "successor_model": "vertex_ai/gemini-3.8-flash", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -27925,7 +30914,9 @@ "text" ], "supports_audio_input": true, + "supports_computer_use": true, "supports_function_calling": true, + "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -27937,23 +30928,7 @@ "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 2.7e-06, - "input_cost_per_audio_token_priority": 2.7e-06, - "output_cost_per_token_priority": 1.62e-05, - "cache_read_input_token_cost_priority": 2.7e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_token_batches": 7.5e-07, - "output_cost_per_token_batches": 4.5e-06, - "input_cost_per_token_flex": 7.5e-07, - "output_cost_per_token_flex": 4.5e-06, - "cache_read_input_token_cost_flex": 7.5e-08 + "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-3.6-flash": { "prompt_cache_min_tokens": 4096, @@ -27966,7 +30941,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -27989,12 +30963,14 @@ "text" ], "supports_audio_input": true, + "supports_computer_use": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -28005,11 +30981,15 @@ "input_cost_per_token_priority": 1.35e-06, "output_cost_per_token_priority": 6.75e-06, "cache_read_input_token_cost_priority": 1.35e-07, + "deprecation_date": "2026-11-19", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "successor_model": "vertex_ai/gemini-3.8-flash", "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -28024,7 +31004,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -28047,6 +31026,7 @@ "text" ], "supports_audio_input": true, + "supports_computer_use": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -28054,6 +31034,7 @@ "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -28064,32 +31045,41 @@ "input_cost_per_token_priority": 1.35e-06, "output_cost_per_token_priority": 6.75e-06, "cache_read_input_token_cost_priority": 1.35e-07, + "deprecation_date": "2027-01-28", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "successor_model": "vertex_ai/gemini-3.8-flash", "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, "vertex_ai/gemini-3.8-flash": { - "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, + "cache_read_input_token_cost_priority": 1.35e-07, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token": 7.5e-07, "input_cost_per_token_batches": 3.75e-07, "input_cost_per_token_flex": 3.75e-07, + "input_cost_per_token_priority": 1.35e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, "output_cost_per_token_batches": 1.875e-06, "output_cost_per_token_flex": 1.875e-06, + "output_cost_per_token_priority": 6.75e-06, + "prompt_cache_min_tokens": 4096.0, "regional_endpoint_uplift_multiplier": 1.1, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -28106,30 +31096,23 @@ "text" ], "supports_audio_input": true, + "supports_computer_use": true, "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 1.35e-06, - "output_cost_per_token_priority": 6.75e-06, - "cache_read_input_token_cost_priority": 1.35e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-3.8-flash-cyber": { "cache_read_input_token_cost": 1.5e-07, @@ -28143,7 +31126,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 7.5e-06, "output_cost_per_token": 7.5e-06, @@ -28172,6 +31154,7 @@ "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": false, "supports_url_context": false, @@ -28181,6 +31164,7 @@ "supports_native_streaming": true }, "vertex_ai/gemini-3.8-live": { + "gemini_audio_only_live": true, "input_cost_per_audio_token": 3e-06, "input_cost_per_image_token": 1e-06, "input_cost_per_token": 7.5e-07, @@ -28189,10 +31173,10 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, + "output_cost_per_video_token": 1e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/vertex_ai/live", @@ -28213,27 +31197,38 @@ "supports_function_calling": true, "supports_response_schema": false, "supports_vision": true, - "supports_web_search": true, - "gemini_audio_only_live": true, - "output_cost_per_video_token": 1e-06 + "supports_web_search": true }, "vertex_ai/gemini-3.1-pro-preview": { - "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_priority": 3.6e-07, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "input_cost_per_token_above_200k_tokens_flex": 2e-06, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.6e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", + "output_cost_per_image": 0.00012, "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, + "output_cost_per_token_above_200k_tokens_batches": 9e-06, + "output_cost_per_token_above_200k_tokens_flex": 9e-06, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "output_cost_per_token_batches": 6e-06, - "output_cost_per_image": 0.00012, + "output_cost_per_token_flex": 6e-06, + "output_cost_per_token_priority": 2.16e-05, + "prompt_cache_min_tokens": 4096.0, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -28251,46 +31246,29 @@ ], "supports_audio_input": true, "supports_function_calling": true, + "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_url_context": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 3.6e-06, - "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, - "output_cost_per_token_priority": 2.16e-05, - "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, - "cache_read_input_token_cost_priority": 3.6e-07, - "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, - "cache_read_input_token_cost_flex": 2e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_token_flex": 1e-06, - "output_cost_per_token_flex": 6e-06 + "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-3.1-pro-preview-customtools": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, @@ -28335,6 +31313,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -28346,7 +31325,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2e-05, @@ -28379,7 +31357,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_reasoning_token": 2.5e-06, @@ -28417,7 +31394,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 5e-06, "output_cost_per_token": 5e-06, @@ -28464,7 +31440,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, @@ -28484,11 +31459,12 @@ }, "gemini-embedding-001": { "deprecation_date": "2028-05-20", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "successor_model": "gemini-embedding-2", "input_cost_per_token": 1.5e-07, "input_cost_per_token_batches": 1.2e-07, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, - "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, @@ -28505,11 +31481,11 @@ "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supports_embedding_image_input": true, "uses_embed_content": true }, "gemini-embedding-2": { @@ -28523,11 +31499,11 @@ "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supports_embedding_image_input": true, "supports_multimodal": true, "uses_embed_content": true }, @@ -28542,11 +31518,11 @@ "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supports_embedding_image_input": true, "supports_multimodal": true, "uses_embed_content": true }, @@ -28561,11 +31537,11 @@ "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supports_embedding_image_input": true, "supports_multimodal": true, "uses_embed_content": true }, @@ -28575,7 +31551,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1000000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, @@ -28584,16 +31559,18 @@ }, "gemini/gemini-embedding-001": { "deprecation_date": "2028-05-14", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-embedding-2", "input_cost_per_token": 1.5e-07, "litellm_provider": "gemini", "max_input_tokens": 2048, - "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "rpm": 10000, - "source": "https://ai.google.dev/gemini-api/docs/embeddings#model-versions", - "tpm": 10000000 + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "tpm": 10000000, + "input_cost_per_token_batches": 7.5e-08 }, "gemini/gemini-embedding-2": { "input_cost_per_audio_token": 6.5e-06, @@ -28606,19 +31583,21 @@ "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "gemini", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "rpm": 10000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supports_audio_input": true, + "supports_embedding_image_input": true, "supports_multimodal": true, "supports_vision": true, "tpm": 10000000 }, "gemini/gemini-3-pro-image-preview": { "deprecation_date": "2026-06-25", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-3-pro-image", "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, @@ -28627,7 +31606,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, @@ -28640,8 +31618,8 @@ "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", - "/v1/batch" + "/v1/images/generations", + "/v1/images/edits" ], "supported_modalities": [ "text", @@ -28662,17 +31640,19 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "supports_reasoning": false }, "gemini/gemini-3.1-flash-image-preview": { "deprecation_date": "2026-06-25", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-nano-banana-2.1", "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "gemini", "max_input_tokens": 65536, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "image_generation", "output_cost_per_image": 0.045, "output_cost_per_image_token": 6e-05, @@ -28683,8 +31663,8 @@ "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", - "/v1/batch" + "/v1/images/generations", + "/v1/images/edits" ], "supported_modalities": [ "text", @@ -28706,6 +31686,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "gemini/gemini-3.1-flash-lite-preview": { @@ -28715,6 +31696,8 @@ "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, "deprecation_date": "2026-05-25", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-3.1-flash-lite", "input_cost_per_audio_token": 5e-07, "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, @@ -28723,7 +31706,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 1.5e-06, "output_cost_per_token": 1.5e-06, @@ -28767,11 +31749,14 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 2.5e-07 }, "gemini/gemini-embedding-2-preview": { + "deprecation_date": "2026-11-06", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", "input_cost_per_audio_token": 6.5e-06, "input_cost_per_audio_token_batches": 3.25e-06, "input_cost_per_image_token": 4.5e-07, @@ -28782,13 +31767,14 @@ "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "gemini", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "rpm": 10000, "source": "https://ai.google.dev/gemini-api/docs/pricing", + "successor_model": "gemini/gemini-embedding-2", "supports_audio_input": true, + "supports_embedding_image_input": true, "supports_multimodal": true, "supports_vision": true, "tpm": 10000000 @@ -28797,9 +31783,8 @@ "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "gemini", - "max_input_tokens": 131072, + "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "rpm": 1000, @@ -28834,9 +31819,8 @@ "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "gemini", - "max_input_tokens": 131072, + "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "rpm": 1000, @@ -28869,16 +31853,22 @@ }, "gemini/gemini-2.5-flash": { "cache_read_input_audio_token_cost": 1e-07, + "cache_read_input_audio_token_cost_batches": 1e-07, + "cache_read_input_audio_token_cost_flex": 1e-07, + "cache_read_input_audio_token_cost_priority": 1.8e-07, "cache_read_input_token_cost": 3e-08, "cache_read_input_token_cost_batches": 3e-08, "cache_read_input_token_cost_flex": 3e-08, "cache_read_input_token_cost_priority": 5.4e-08, + "deprecation_date": "2026-12-01", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-3.5-flash-lite", "input_cost_per_audio_token": 1e-06, + "input_cost_per_audio_token_flex": 5e-07, "input_cost_per_token": 3e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -28916,8 +31906,10 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 5e-07, + "input_cost_per_audio_token_priority": 1.8e-06, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, "input_cost_per_token_priority": 5.4e-07, @@ -28929,7 +31921,9 @@ }, "gemini/gemini-2.5-flash-image": { "cache_read_input_token_cost": 3e-08, - "deprecation_date": "2026-10-02", + "deprecation_date": "2027-03-15", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-3.1-flash-lite-image", "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, @@ -28939,18 +31933,22 @@ "supports_reasoning": false, "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.039, "output_cost_per_image_token": 3e-05, + "output_cost_per_image_token_batches": 1.5e-05, + "output_cost_per_image_token_priority": 5.4e-05, "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_priority": 4.5e-06, "rpm": 100000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", - "/v1/batch" + "/v1/images/generations", + "/v1/images/edits" ], "supported_modalities": [ "text", @@ -28991,10 +31989,10 @@ "litellm_provider": "gemini", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, + "output_cost_per_image_token_batches": 6e-05, "output_cost_per_token": 1.2e-05, "rpm": 1000, "tpm": 4000000, @@ -29004,8 +32002,8 @@ "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", - "/v1/batch" + "/v1/images/generations", + "/v1/images/edits" ], "supported_modalities": [ "text", @@ -29026,6 +32024,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "supports_reasoning": true }, @@ -29038,7 +32037,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, @@ -29051,8 +32049,7 @@ "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", - "/v1/batch" + "/v1/images/edits" ], "supported_modalities": [ "text", @@ -29082,19 +32079,21 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.045, "output_cost_per_image_token": 6e-05, + "output_cost_per_image_token_batches": 3e-05, "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, - "rpm": 1000, - "tpm": 4000000, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "rpm": 1000.0, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-nano-banana-2.1", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", - "/v1/batch" + "/v1/images/generations", + "/v1/images/edits" ], "supported_modalities": [ "text", @@ -29105,19 +32104,15 @@ "image" ], "supports_function_calling": false, + "supports_pdf_input": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "supports_pdf_input": true + "tpm": 4000000.0, + "web_search_billing_unit": "per_query" }, "gemini/gemini-3.1-flash-lite-image": { "input_cost_per_image": 0.00028, @@ -29126,18 +32121,18 @@ "litellm_provider": "gemini", "max_input_tokens": 65536, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "image_generation", "output_cost_per_image": 0.0336, "output_cost_per_image_token": 3e-05, + "output_cost_per_image_token_batches": 1.5e-05, "output_cost_per_token": 1.5e-06, "output_cost_per_token_batches": 7.5e-07, "rpm": 1000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", - "/v1/batch" + "/v1/images/generations", + "/v1/images/edits" ], "supported_modalities": [ "text", @@ -29158,18 +32153,20 @@ "tpm": 4000000 }, "gemini/deep-research-pro-preview-12-2025": { + "deprecation_date": "2026-10-23", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/deep-research-preview-04-2026", "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, - "rpm": 1000, - "tpm": 4000000, "output_cost_per_token_batches": 6e-06, + "rpm": 1000.0, + "search_context_cost_per_query": {"search_context_size_low":0.035,"search_context_size_medium":0.035,"search_context_size_high":0.035}, "source": "https://ai.google.dev/gemini-api/docs/models/deep-research-pro-preview-12-2025", "supported_endpoints": [ "/v1/chat/completions", @@ -29186,30 +32183,29 @@ "text" ], "supports_function_calling": false, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - }, - "supports_pdf_input": true + "tpm": 4000000.0 }, "gemini/gemini-2.5-flash-lite": { "cache_read_input_audio_token_cost": 3e-08, + "cache_read_input_audio_token_cost_batches": 3e-08, + "cache_read_input_audio_token_cost_flex": 3e-08, + "cache_read_input_audio_token_cost_priority": 5.4e-08, "cache_read_input_token_cost": 1e-08, "cache_read_input_token_cost_batches": 1e-08, "cache_read_input_token_cost_flex": 1e-08, "cache_read_input_token_cost_priority": 1.8e-08, "input_cost_per_audio_token": 3e-07, + "input_cost_per_audio_token_flex": 1.5e-07, "input_cost_per_token": 1e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 4e-07, "output_cost_per_token": 4e-07, @@ -29247,8 +32243,10 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 1.5e-07, + "input_cost_per_audio_token_priority": 5.4e-07, "input_cost_per_token_batches": 5e-08, "input_cost_per_token_flex": 5e-08, "input_cost_per_token_priority": 1.8e-07, @@ -29260,11 +32258,11 @@ }, "gemini/gemini-flash-latest": { "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_batches": 3.75e-08, "input_cost_per_token": 7.5e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -29319,11 +32317,11 @@ }, "gemini/gemini-flash-lite-latest": { "cache_read_input_token_cost": 3e-08, + "cache_read_input_token_cost_batches": 1.5e-08, "input_cost_per_token": 3e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -29376,12 +32374,14 @@ "web_search_billing_unit": "per_query" }, "gemini/gemini-2.5-flash-preview-tts": { + "deprecation_date": "2026-11-17", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-3.8-flash-tts", "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "gemini", "max_input_tokens": 8192, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "audio_speech", "output_cost_per_audio_token": 1e-05, "output_cost_per_token": 1e-05, @@ -29411,7 +32411,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, @@ -29450,19 +32449,32 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 10000, "period": "day", "shared_group": "gemini-2.5-pro"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_token_batches": 6.25e-07, "input_cost_per_token_flex": 6.25e-07, "output_cost_per_token_batches": 5e-06, - "output_cost_per_token_flex": 5e-06 + "output_cost_per_token_flex": 5e-06, + "supports_url_context": true, + "cache_read_input_token_cost_above_200k_tokens_batches": 2.5e-07, + "cache_read_input_token_cost_above_200k_tokens_flex": 2.5e-07, + "deprecation_date": "2026-12-01", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-3.8-flash", + "input_cost_per_token_above_200k_tokens_batches": 1.25e-06, + "input_cost_per_token_above_200k_tokens_flex": 1.25e-06, + "output_cost_per_token_above_200k_tokens_batches": 7.5e-06, + "output_cost_per_token_above_200k_tokens_flex": 7.5e-06 }, "gemini/gemini-2.5-computer-use-preview-10-2025": { + "deprecation_date": "2026-07-28", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-3.8-flash", "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, "litellm_provider": "gemini", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, @@ -29488,12 +32500,18 @@ }, "gemini/gemini-3.1-flash-lite": { "cache_read_input_audio_token_cost": 5e-08, + "cache_read_input_audio_token_cost_batches": 2.5e-08, + "cache_read_input_audio_token_cost_flex": 2.5e-08, + "cache_read_input_audio_token_cost_priority": 9e-08, "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, "deprecation_date": "2027-05-07", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-3.5-flash-lite", "input_cost_per_audio_token": 5e-07, + "input_cost_per_audio_token_flex": 2.5e-07, "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_flex": 1.25e-07, @@ -29501,7 +32519,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 1.5e-06, "output_cost_per_token": 1.5e-06, @@ -29545,13 +32562,15 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_audio_token_batches": 2.5e-07 + "input_cost_per_audio_token_batches": 2.5e-07, + "input_cost_per_audio_token_priority": 9e-07 }, "gemini/gemini-3.5-flash-lite": { "cache_read_input_token_cost": 3e-08, - "cache_read_input_token_cost_batches": 2e-08, + "cache_read_input_token_cost_batches": 1.5e-08, "cache_read_input_token_cost_flex": 2e-08, "cache_read_input_token_cost_priority": 5e-08, "input_cost_per_token": 3e-07, @@ -29561,7 +32580,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -29592,6 +32610,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -29605,25 +32624,30 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "supports_computer_use": true }, "gemini/gemini-3-flash-preview": { "cache_read_input_audio_token_cost": 1e-07, + "cache_read_input_audio_token_cost_batches": 1e-07, + "cache_read_input_audio_token_cost_flex": 1e-07, + "cache_read_input_audio_token_cost_priority": 1.8e-07, "cache_read_input_token_cost": 5e-08, "cache_read_input_token_cost_batches": 5e-08, "cache_read_input_token_cost_flex": 5e-08, "input_cost_per_audio_token": 1e-06, + "input_cost_per_audio_token_flex": 5e-07, "input_cost_per_token": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3e-06, "output_cost_per_token": 3e-06, "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -29661,6 +32685,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 5e-07, @@ -29668,7 +32693,9 @@ "input_cost_per_token_flex": 2.5e-07, "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, - "supports_audio_input": true + "successor_model": "gemini/gemini-3.6-flash", + "supports_audio_input": true, + "supports_computer_use": true }, "gemini/gemini-3.5-flash": { "prompt_cache_min_tokens": 4096, @@ -29679,12 +32706,11 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -29724,13 +32750,15 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_batches": 7.5e-07, "output_cost_per_token_batches": 4.5e-06, "input_cost_per_token_flex": 7.5e-07, "output_cost_per_token_flex": 4.5e-06, - "cache_read_input_token_cost_flex": 8e-08 + "cache_read_input_token_cost_flex": 8e-08, + "successor_model": "gemini/gemini-3.6-flash" }, "gemini/gemini-3.6-flash": { "prompt_cache_min_tokens": 4096, @@ -29743,7 +32771,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -29773,6 +32800,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -29789,6 +32817,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -29803,14 +32832,13 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, "output_cost_per_token_batches": 1.875e-06, "output_cost_per_token_flex": 1.875e-06, "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -29834,6 +32862,7 @@ "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -29850,8 +32879,10 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "successor_model": "gemini/gemini-3.8-flash" }, "gemini/gemini-3.8-flash": { "prompt_cache_min_tokens": 4096, @@ -29864,7 +32895,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -29895,6 +32925,7 @@ "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -29911,8 +32942,10 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "supports_computer_use": true }, "gemini/gemini-omni-flash-preview": { "input_cost_per_audio_token": 1.5e-06, @@ -29920,13 +32953,12 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, "output_cost_per_video_token": 1.75e-05, "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_endpoints": [ "/v1beta/interactions" ], @@ -29946,7 +32978,9 @@ "supports_video_input": true, "supports_vision": true, "tpm": 800000, - "deprecation_date": "2026-09-30" + "deprecation_date": "2026-10-22", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-omni-1.2-flash" }, "gemini/gemini-3.1-pro-preview": { "prompt_cache_min_tokens": 4096, @@ -29958,7 +32992,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, @@ -30006,10 +33039,17 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_flex": 1e-06, - "output_cost_per_token_flex": 6e-06 + "output_cost_per_token_flex": 6e-06, + "cache_read_input_token_cost_above_200k_tokens_batches": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_flex": 4e-07, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "input_cost_per_token_above_200k_tokens_flex": 2e-06, + "output_cost_per_token_above_200k_tokens_batches": 9e-06, + "output_cost_per_token_above_200k_tokens_flex": 9e-06 }, "gemini/gemini-3.1-pro-preview-customtools": { "prompt_cache_min_tokens": 4096, @@ -30021,7 +33061,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, @@ -30069,24 +33108,47 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_flex": 1e-06, - "output_cost_per_token_flex": 6e-06 + "output_cost_per_token_flex": 6e-06, + "cache_read_input_token_cost_above_200k_tokens_batches": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_flex": 4e-07, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "input_cost_per_token_above_200k_tokens_flex": 2e-06, + "output_cost_per_token_above_200k_tokens_batches": 9e-06, + "output_cost_per_token_above_200k_tokens_flex": 9e-06 }, "gemini-3-flash-preview": { "cache_read_input_audio_token_cost": 1e-07, + "cache_read_input_audio_token_cost_priority": 1.8e-07, "cache_read_input_token_cost": 5e-08, - "cache_read_input_token_cost_flex": 5e-08, + "cache_read_input_token_cost_priority": 9e-08, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 1e-06, + "input_cost_per_audio_token_above_200k_tokens": 1e-06, + "input_cost_per_audio_token_above_200k_tokens_batches": 5e-07, + "input_cost_per_audio_token_above_200k_tokens_flex": 5e-07, + "input_cost_per_audio_token_above_200k_tokens_priority": 1.8e-06, + "input_cost_per_audio_token_batches": 5e-07, + "input_cost_per_audio_token_flex": 5e-07, + "input_cost_per_audio_token_priority": 1.8e-06, "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "input_cost_per_token_flex": 2.5e-07, + "input_cost_per_token_priority": 9e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3e-06, "output_cost_per_token": 3e-06, + "output_cost_per_token_batches": 1.5e-06, + "output_cost_per_token_flex": 1.5e-06, + "output_cost_per_token_priority": 5.4e-06, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -30103,7 +33165,9 @@ "text" ], "supports_audio_output": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -30114,36 +33178,19 @@ "supports_url_context": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 9e-07, - "input_cost_per_audio_token_priority": 1.8e-06, - "output_cost_per_token_priority": 5.4e-06, - "cache_read_input_token_cost_priority": 9e-08, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_audio_token_batches": 5e-07, - "input_cost_per_token_batches": 2.5e-07, - "input_cost_per_token_flex": 2.5e-07, - "output_cost_per_token_batches": 1.5e-06, - "output_cost_per_token_flex": 1.5e-06 + "web_search_billing_unit": "per_query" }, "gemini-omni-flash-preview": { "input_cost_per_audio_token": 1.5e-06, "input_cost_per_token": 1.5e-06, "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_input_tokens": 131072, + "max_output_tokens": 57920, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, "output_cost_per_video_token": 1.75e-05, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/omni-flash-preview", "supported_endpoints": [ "/v1/chat/completions" ], @@ -30161,23 +33208,35 @@ "supports_reasoning": true, "supports_system_messages": true, "supports_video_input": true, - "supports_vision": true + "supports_vision": true, + "deprecation_date": "2026-11-06" }, "gemini-3.5-flash": { - "prompt_cache_min_tokens": 4096, - "deprecation_date": "2027-05-19", "cache_read_input_token_cost": 1.5e-07, "cache_read_input_token_cost_batches": 7.5e-08, + "cache_read_input_token_cost_flex": 7.5e-08, + "cache_read_input_token_cost_priority": 2.7e-07, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 1.5e-06, + "input_cost_per_audio_token_priority": 2.7e-06, "input_cost_per_token": 1.5e-06, + "input_cost_per_token_batches": 7.5e-07, + "input_cost_per_token_flex": 7.5e-07, + "input_cost_per_token_priority": 2.7e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, + "output_cost_per_token_batches": 4.5e-06, + "output_cost_per_token_flex": 4.5e-06, + "output_cost_per_token_priority": 1.62e-05, + "prompt_cache_min_tokens": 4096.0, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "successor_model": "gemini-3.8-flash", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -30192,9 +33251,11 @@ "supported_output_modalities": [ "text" ], - "supports_audio_output": false, "supports_audio_input": true, + "supports_audio_output": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -30206,23 +33267,7 @@ "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 2.7e-06, - "input_cost_per_audio_token_priority": 2.7e-06, - "output_cost_per_token_priority": 1.62e-05, - "cache_read_input_token_cost_priority": 2.7e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_token_batches": 7.5e-07, - "output_cost_per_token_batches": 4.5e-06, - "input_cost_per_token_flex": 7.5e-07, - "output_cost_per_token_flex": 4.5e-06, - "cache_read_input_token_cost_flex": 7.5e-08 + "web_search_billing_unit": "per_query" }, "gemini-3.6-flash": { "prompt_cache_min_tokens": 4096, @@ -30235,7 +33280,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -30258,12 +33302,14 @@ ], "supports_audio_output": false, "supports_audio_input": true, + "supports_computer_use": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -30274,11 +33320,15 @@ "input_cost_per_token_priority": 1.35e-06, "output_cost_per_token_priority": 6.75e-06, "cache_read_input_token_cost_priority": 1.35e-07, + "deprecation_date": "2026-11-19", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "successor_model": "gemini-3.8-flash", "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -30293,7 +33343,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -30316,6 +33365,7 @@ ], "supports_audio_output": false, "supports_audio_input": true, + "supports_computer_use": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -30323,6 +33373,7 @@ "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -30333,31 +33384,40 @@ "input_cost_per_token_priority": 1.35e-06, "output_cost_per_token_priority": 6.75e-06, "cache_read_input_token_cost_priority": 1.35e-07, + "deprecation_date": "2027-01-28", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "successor_model": "gemini-3.8-flash", "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, "gemini-3.8-flash": { - "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, + "cache_read_input_token_cost_priority": 1.35e-07, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token": 7.5e-07, "input_cost_per_token_batches": 3.75e-07, "input_cost_per_token_flex": 3.75e-07, + "input_cost_per_token_priority": 1.35e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, "output_cost_per_token_batches": 1.875e-06, "output_cost_per_token_flex": 1.875e-06, + "output_cost_per_token_priority": 6.75e-06, + "prompt_cache_min_tokens": 4096.0, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -30373,32 +33433,25 @@ "supported_output_modalities": [ "text" ], - "supports_audio_output": false, "supports_audio_input": true, + "supports_audio_output": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 1.35e-06, - "output_cost_per_token_priority": 6.75e-06, - "cache_read_input_token_cost_priority": 1.35e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "web_search_billing_unit": "per_query" }, "gemini-3.8-flash-cyber": { "cache_read_input_token_cost": 1.5e-07, @@ -30412,7 +33465,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 7.5e-06, "output_cost_per_token": 7.5e-06, @@ -30441,6 +33493,7 @@ "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": false, "supports_url_context": false, @@ -30451,13 +33504,15 @@ }, "gemini/gemini-2.5-pro-preview-tts": { "cache_read_input_token_cost": 1.25e-07, + "deprecation_date": "2026-11-17", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-3.8-flash-tts", "input_cost_per_audio_token": 7e-07, "input_cost_per_token": 1e-06, "input_cost_per_token_batches": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 8192, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2e-05, @@ -30492,7 +33547,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 8192, - "max_tokens": 8192, "metadata": { "notes": "Rate limits not documented for gemini-exp-1114. Assuming same as gemini-1.5-pro.", "supports_tool_choice": true @@ -30515,7 +33569,6 @@ "litellm_provider": "gemini", "max_input_tokens": 2097152, "max_output_tokens": 8192, - "max_tokens": 8192, "metadata": { "notes": "Rate limits not documented for gemini-exp-1206. Assuming same as gemini-1.5-pro.", "supports_tool_choice": true @@ -30536,7 +33589,7 @@ "input_cost_per_token": 3.5e-07, "litellm_provider": "gemini", "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.05e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", @@ -30550,7 +33603,7 @@ "input_cost_per_token": 3.5e-07, "litellm_provider": "gemini", "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.05e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", @@ -30574,7 +33627,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_character": 0, "output_cost_per_character_above_128k_tokens": 0, @@ -30594,7 +33646,6 @@ "litellm_provider": "gemini", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, @@ -30610,7 +33661,6 @@ "litellm_provider": "gemini", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, @@ -30646,7 +33696,6 @@ "litellm_provider": "gemini", "max_input_tokens": 32767, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_character": 0, "output_cost_per_character_above_128k_tokens": 0, @@ -30665,7 +33714,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_image": 0.04, "output_cost_per_token": 0, @@ -30690,10 +33738,9 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_modalities": [ "text" ], @@ -30708,17 +33755,20 @@ "supports_system_messages": false, "supports_vision": false, "supports_web_search": false, - "output_cost_per_image": 0.08 + "output_cost_per_image": 0.08, + "successor_model": "gemini/lyria-3.5" }, "gemini/veo-3.1-fast-generate-preview": { + "deprecation_date": "2026-10-22", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-omni-1.2-flash", "litellm_provider": "gemini", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.12, "output_cost_per_second_4k": 0.3, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_modalities": [ "text" ], @@ -30727,13 +33777,15 @@ ] }, "gemini/veo-3.1-generate-preview": { + "deprecation_date": "2026-10-22", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-omni-1.2-flash", "litellm_provider": "gemini", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, "output_cost_per_second_4k": 0.6, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_modalities": [ "text" ], @@ -30742,13 +33794,15 @@ ] }, "gemini/veo-3.1-lite-generate-preview": { + "deprecation_date": "2026-10-22", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-omni-1.2-flash", "litellm_provider": "gemini", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.05, "output_cost_per_second_1080p": 0.08, - "source": "https://ai.google.dev/gemini-api/docs/video", + "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_modalities": [ "text" ], @@ -30759,7 +33813,6 @@ "gemini/veo-3.1-fast-generate-001": { "litellm_provider": "gemini", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.12, @@ -30775,7 +33828,6 @@ "gemini/veo-3.1-generate-001": { "litellm_provider": "gemini", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, "output_cost_per_second_4k": 0.6, @@ -30787,6 +33839,53 @@ "video" ] }, + "github_copilot/claude-fable-5": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_read_input_token_cost": 1e-06, + "input_cost_per_token": 1e-05, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/messages" + ], + "supports_adaptive_thinking": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "thinking_always_on": true + }, + "github_copilot/claude-fable-5.1": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 1e-05, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/messages" + ], + "supports_adaptive_thinking": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "thinking_always_on": true + }, + "github_copilot/claude-fable-latest": { + "alias_of": "github_copilot/claude-fable-5.2" + }, "github_copilot/claude-haiku-4.5": { "cache_creation_input_token_cost": 1.25e-06, "cache_read_input_token_cost": 1e-07, @@ -30794,7 +33893,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 5e-06, "supported_endpoints": [ @@ -30802,83 +33900,216 @@ ], "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_reasoning": true, "supports_vision": true }, - "github_copilot/claude-opus-4.5": { + "github_copilot/claude-haiku-5.5": { + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_above_100k_tokens": 5e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_100k_tokens": 5e-07, "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ - "/v1/chat/completions" + "/v1/chat/completions", + "/v1/messages" ], + "supports_adaptive_thinking": true, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_vision": true, - "supports_output_config": true + "thinking_always_on": false + }, + "github_copilot/claude-haiku-latest": { + "alias_of": "github_copilot/claude-haiku-5.5" }, - "github_copilot/claude-opus-4.6-fast": { + "github_copilot/claude-opus-4.8": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_read_input_token_cost": 5e-07, + "deprecation_date": "2026-11-16", + "input_cost_per_token": 5e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/messages" + ], "supports_adaptive_thinking": true, - "supports_legacy_thinking": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/claude-opus-4.8-fast": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_read_input_token_cost": 1e-06, + "deprecation_date": "2026-11-16", + "input_cost_per_token": 1e-05, "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 16000, - "max_tokens": 16000, + "max_input_tokens": 200000, + "max_output_tokens": 64000, "mode": "chat", + "output_cost_per_token": 5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ - "/v1/chat/completions" + "/v1/chat/completions", + "/v1/messages" ], + "supports_adaptive_thinking": true, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_vision": true }, - "github_copilot/claude-opus-41": { + "github_copilot/claude-opus-5": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_read_input_token_cost": 5e-07, + "deprecation_date": "2026-11-16", + "input_cost_per_token": 5e-06, "litellm_provider": "github_copilot", - "max_input_tokens": 80000, - "max_output_tokens": 16000, - "max_tokens": 16000, + "max_input_tokens": 200000, + "max_output_tokens": 64000, "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ - "/v1/chat/completions" + "/v1/chat/completions", + "/v1/messages" ], + "supports_adaptive_thinking": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_vision": true }, - "github_copilot/claude-sonnet-4": { - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, + "github_copilot/claude-opus-5.5": { + "cache_creation_input_token_cost": 5e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 4e-06, "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 16000, - "max_tokens": 16000, + "max_input_tokens": 200000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.5e-05, + "output_cost_per_token": 2e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/messages" + ], + "supports_adaptive_thinking": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "thinking_always_on": true + }, + "github_copilot/claude-opus-latest": { + "alias_of": "github_copilot/claude-opus-5.5" + }, + "github_copilot/claude-sonnet-5": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/messages" + ], + "supports_adaptive_thinking": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/claude-sonnet-5.5": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/messages" + ], + "supports_adaptive_thinking": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "thinking_always_on": true + }, + "github_copilot/claude-sonnet-latest": { + "alias_of": "github_copilot/claude-sonnet-5.5" + }, + "github_copilot/gemini-3.7-flash": { + "cache_read_input_token_cost": 7.5e-08, + "deprecation_date": "2026-10-19", + "input_cost_per_token": 7.5e-07, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 3.75e-06, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_sampling_params": false, "supports_vision": true }, - "github_copilot/claude-sonnet-4.5": { + "github_copilot/gemini-3.8-flash": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 16000, - "max_tokens": 16000, + "max_input_tokens": 200000, + "max_output_tokens": 65536, "mode": "chat", + "output_cost_per_token": 3.75e-06, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_sampling_params": false, "supports_vision": true }, "github_copilot/gpt-3.5-turbo": { "litellm_provider": "github_copilot", "max_input_tokens": 16384, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true }, @@ -30886,7 +34117,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 16384, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true }, @@ -30894,7 +34124,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true }, @@ -30902,7 +34131,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true }, @@ -30910,28 +34138,31 @@ "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true }, "github_copilot/gpt-4.1": { + "deprecation_date": "2026-06-01", + "deprecation_source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/model-deprecation-history.yml", "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/model-deprecation-history.yml", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/gpt-4.1-2025-04-14": { + "deprecation_date": "2026-06-01", + "deprecation_source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/model-deprecation-history.yml", "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/model-deprecation-history.yml", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -30945,7 +34176,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -30955,7 +34185,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -30965,7 +34194,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true @@ -30974,7 +34202,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -30984,7 +34211,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true @@ -30993,157 +34219,416 @@ "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true }, - "github_copilot/gpt-5": { + "github_copilot/gpt-5-mini": { + "cache_read_input_token_cost": 2.5e-08, + "deprecation_date": "2026-10-19", + "input_cost_per_token": 2.5e-07, + "litellm_provider": "github_copilot", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://github.blog/changelog/2026-10-19-github-copilot-models-deprecated-on-october-19-2026", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-5.3-codex": { + "cache_read_input_token_cost": 1.75e-07, + "input_cost_per_token": 1.75e-06, "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1.4e-05, + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-5.4": { + "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 5e-07, + "deprecation_date": "2026-10-19", + "deprecation_source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/model-deprecation-history.yml", + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_above_272k_tokens": 5e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 272000, + "max_output_tokens": 128000, "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_above_272k_tokens": 2.25e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, - "github_copilot/gpt-5-mini": { - "cache_read_input_token_cost": 2.5e-08, - "input_cost_per_token": 2.5e-07, + "github_copilot/gpt-5.4-mini": { + "cache_read_input_token_cost": 7.5e-08, + "deprecation_date": "2026-10-19", + "input_cost_per_token": 7.5e-07, "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 2e-06, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 4.5e-06, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/responses" + ], "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, - "github_copilot/gpt-5.1": { + "github_copilot/gpt-5.5": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "deprecation_date": "2026-10-19", + "deprecation_source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/model-deprecation-history.yml", + "input_cost_per_token": 5e-06, + "input_cost_per_token_above_272k_tokens": 1e-05, "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 3e-05, + "output_cost_per_token_above_272k_tokens": 4.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ - "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, - "github_copilot/gpt-5.1-codex-max": { + "github_copilot/gpt-5.6-luna": { + "cache_creation_input_token_cost": 2.5e-07, + "cache_creation_input_token_cost_above_200k_tokens": 5e-07, + "cache_read_input_token_cost": 2e-08, + "cache_read_input_token_cost_above_200k_tokens": 4e-08, + "input_cost_per_token": 2e-07, + "input_cost_per_token_above_200k_tokens": 4e-07, "litellm_provider": "github_copilot", - "max_input_tokens": 128000, + "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_above_200k_tokens": 1.8e-06, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, - "github_copilot/gpt-5.2": { + "github_copilot/gpt-5.6-sol": { + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1e-05, + "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "input_cost_per_token": 4e-06, + "input_cost_per_token_above_272k_tokens": 8e-06, "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 2e-05, + "output_cost_per_token_above_272k_tokens": 3e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ - "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, - "github_copilot/gpt-5.3-codex": { - "cache_read_input_token_cost": 1.75e-07, - "input_cost_per_token": 1.75e-06, + "github_copilot/gpt-5.6-terra": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "deprecation_date": "2026-11-16", + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, "litellm_provider": "github_copilot", - "max_input_tokens": 128000, + "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", - "output_cost_per_token": 1.4e-05, + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_272k_tokens": 1.8e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, - "github_copilot/mai-code-1-flash": { - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_token": 7.5e-07, + "github_copilot/gpt-6-astra": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, + "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_above_272k_tokens": 2e-06, + "input_cost_per_token": 1e-05, + "input_cost_per_token_above_272k_tokens": 2e-05, "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 5e-05, + "output_cost_per_token_above_272k_tokens": 7.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-astra-latest": { + "alias_of": "github_copilot/gpt-6-astra" + }, + "github_copilot/gpt-6-luna": { + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_272k_tokens": 2e-07, + "litellm_provider": "github_copilot", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 5e-07, + "output_cost_per_token_above_272k_tokens": 7.5e-07, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-luna-latest": { + "alias_of": "github_copilot/gpt-6-luna" + }, + "github_copilot/gpt-6-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-sol-latest": { + "alias_of": "github_copilot/gpt-6.1-sol" + }, + "github_copilot/kimi-k3": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 917504, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 4.5e-06, + "output_cost_per_token": 1.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_response_schema": true + "supports_response_schema": true, + "supports_vision": true }, - "github_copilot/mai-code-1-flash-internal": { - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_token": 7.5e-07, + "github_copilot/kimi-latest": { + "alias_of": "github_copilot/kimi-k3" + }, + "github_copilot/mai-code-1.1-flash": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 2e-07, "litellm_provider": "github_copilot", "max_input_tokens": 128000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 4.5e-06, + "max_output_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1.2e-06, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ - "/v1/chat/completions" + "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_response_schema": true + "supports_response_schema": true, + "supports_vision": true }, "github_copilot/text-embedding-3-small": { "litellm_provider": "github_copilot", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding" }, "github_copilot/text-embedding-3-small-inference": { "litellm_provider": "github_copilot", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding" }, "github_copilot/text-embedding-ada-002": { "litellm_provider": "github_copilot", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding" }, + "chatgpt/gpt-6-sol": { + "litellm_provider": "chatgpt", + "mode": "responses", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "source": "https://developers.openai.com/api/docs/pricing", + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "chatgpt/gpt-6-luna": { + "litellm_provider": "chatgpt", + "mode": "responses", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "source": "https://developers.openai.com/api/docs/pricing", + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "chatgpt/gpt-6-astra": { + "litellm_provider": "chatgpt", + "mode": "responses", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "source": "https://developers.openai.com/api/docs/pricing", + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "chatgpt/gpt-6.1-sol": { + "litellm_provider": "chatgpt", + "mode": "responses", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "source": "https://developers.openai.com/api/docs/pricing", + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, "chatgpt/gpt-5.5": { "litellm_provider": "chatgpt", "source": "https://platform.openai.com/docs/models/gpt-5.5", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -31163,7 +34648,6 @@ "source": "https://platform.openai.com/docs/models/gpt-5.6-luna", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -31183,7 +34667,6 @@ "source": "https://platform.openai.com/docs/models/gpt-5.6-sol", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -31203,7 +34686,6 @@ "source": "https://platform.openai.com/docs/models/gpt-5.6-terra", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -31222,7 +34704,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -31242,7 +34723,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" @@ -31260,7 +34740,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" @@ -31270,15 +34749,14 @@ "supports_response_schema": true, "supports_vision": true, "supports_reasoning": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false }, "chatgpt/gpt-5.3-codex-spark": { "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" @@ -31292,7 +34770,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -31307,7 +34784,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -31323,7 +34799,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" @@ -31338,7 +34813,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -31358,7 +34832,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" @@ -31373,7 +34846,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "responses", "supported_endpoints": [ "/v1/responses" @@ -31389,7 +34861,6 @@ "litellm_provider": "gigachat", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true, @@ -31400,7 +34871,6 @@ "litellm_provider": "gigachat", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true, @@ -31412,7 +34882,6 @@ "litellm_provider": "gigachat", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true, @@ -31423,7 +34892,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "gigachat", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024 @@ -31432,7 +34900,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "gigachat", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024 @@ -31441,7 +34908,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "gigachat", "max_input_tokens": 4096, - "max_tokens": 4096, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 2560 @@ -31450,7 +34916,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "gigachat", "max_input_tokens": 4096, - "max_tokens": 4096, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 2048 @@ -31460,7 +34925,6 @@ "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.5e-05, "supports_function_calling": true, @@ -31472,7 +34936,6 @@ "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -31483,7 +34946,6 @@ "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -31494,7 +34956,6 @@ "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_function_calling": true, @@ -31505,7 +34966,6 @@ "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.4e-05, "supports_function_calling": true @@ -31515,7 +34975,6 @@ "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true @@ -31525,7 +34984,6 @@ "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true @@ -31535,7 +34993,6 @@ "litellm_provider": "gmi", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, @@ -31546,7 +35003,6 @@ "litellm_provider": "gmi", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -31557,7 +35013,6 @@ "litellm_provider": "gmi", "max_input_tokens": 163840, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 4e-07, "supports_function_calling": true @@ -31567,7 +35022,6 @@ "litellm_provider": "gmi", "max_input_tokens": 163840, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 8.8e-07, "supports_function_calling": true @@ -31577,7 +35031,6 @@ "litellm_provider": "gmi", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-06, "supports_function_calling": true, @@ -31589,7 +35042,6 @@ "litellm_provider": "gmi", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06 }, @@ -31598,35 +35050,37 @@ "litellm_provider": "gmi", "max_input_tokens": 196608, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06 }, "baseten/MiniMaxAI/MiniMax-M2.5": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 3e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 1.2e-06 }, "baseten/nvidia/Nemotron-120B-A12B": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 3e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 7.5e-07 }, "baseten/zai-org/GLM-5": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 9.5e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 3.15e-06 }, "baseten/zai-org/GLM-4.7": { + "deprecation_date": "2026-10-16", "cache_read_input_token_cost": 1.2e-07, "input_cost_per_token": 6e-07, "litellm_provider": "baseten", "max_input_tokens": 200000, "max_output_tokens": 200000, - "max_tokens": 200000, "mode": "chat", "output_cost_per_token": 2.2e-06, "source": "https://inference.baseten.co/v1/models", @@ -31638,24 +35092,28 @@ "supports_vision": false }, "baseten/zai-org/GLM-4.6": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 6e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 2.2e-06 }, "baseten/moonshotai/Kimi-K2.5": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 6e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 3e-06 }, "baseten/moonshotai/Kimi-K2-Thinking": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 6e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 2.5e-06 }, "baseten/moonshotai/Kimi-K2-Instruct-0905": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 6e-07, "litellm_provider": "baseten", "mode": "chat", @@ -31667,7 +35125,6 @@ "litellm_provider": "baseten", "max_input_tokens": 128072, "max_output_tokens": 128072, - "max_tokens": 128072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inference.baseten.co/v1/models", @@ -31679,12 +35136,14 @@ "supports_vision": false }, "baseten/deepseek-ai/DeepSeek-V3.1": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 5e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 1.5e-06 }, "baseten/deepseek-ai/DeepSeek-V3-0324": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 7.7e-07, "litellm_provider": "baseten", "mode": "chat", @@ -31695,7 +35154,6 @@ "litellm_provider": "gmi", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.4e-06, "supports_vision": true @@ -31705,19 +35163,25 @@ "litellm_provider": "gmi", "max_input_tokens": 202752, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2e-06 }, "google.gemma-3-12b-it": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 9e-08, + "input_cost_per_token_batches": 5e-08, + "input_cost_per_token_flex": 5e-08, + "input_cost_per_token_priority": 1.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.9e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 1.5e-07, + "output_cost_per_token_flex": 1.5e-07, + "output_cost_per_token_priority": 5.1e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, @@ -31725,14 +35189,21 @@ "supports_vision": true }, "google.gemma-3-27b-it": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 2.3e-07, + "input_cost_per_token_batches": 1.2e-07, + "input_cost_per_token_flex": 1.2e-07, + "input_cost_per_token_priority": 4e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 3.8e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 1.9e-07, + "output_cost_per_token_flex": 1.9e-07, + "output_cost_per_token_priority": 6.7e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, @@ -31740,14 +35211,21 @@ "supports_vision": true }, "google.gemma-3-4b-it": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 4e-08, + "input_cost_per_token_batches": 2e-08, + "input_cost_per_token_flex": 2e-08, + "input_cost_per_token_priority": 7e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 8e-08, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 4e-08, + "output_cost_per_token_flex": 4e-08, + "output_cost_per_token_priority": 1.4e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, @@ -31768,11 +35246,13 @@ "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "deprecation_date": "2027-04-08", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "global.anthropic.claude-sonnet-5-5", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -31794,21 +35274,26 @@ "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.5e-06, "output_cost_per_token_batches": 7.5e-06, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "global.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2026-10-14", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "global.anthropic.claude-sonnet-5", "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -31827,7 +35312,11 @@ "supports_vision": true, "bedrock_converse_supports_strict_tools": false, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-20250514-v1:0", + "litellm_provider": "bedrock" + } }, "global.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.25e-06, @@ -31838,7 +35327,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -31855,17 +35343,26 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5e-07, - "output_cost_per_token_batches": 2.5e-06 + "output_cost_per_token_batches": 2.5e-06, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "global.amazon.nova-2-lite-v1:0": { "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_priority": 1.3125e-07, "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_priority": 4.375e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -31877,13 +35374,15 @@ }, "gpt-3.5-turbo": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 5e-07, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-06, + "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_prompt_caching": true, @@ -31892,14 +35391,16 @@ }, "gpt-3.5-turbo-0125": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-06, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 7.5e-07, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, @@ -31910,14 +35411,16 @@ }, "gpt-3.5-turbo-1106": { "deprecation_date": "2026-09-28", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 1e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-06, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 2e-06, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, @@ -31928,24 +35431,26 @@ }, "gpt-3.5-turbo-16k": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "input_cost_per_token": 3e-06, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 4e-06, + "fedramp_uplift_multiplier": 1.1, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true }, "gpt-3.5-turbo-instruct": { "deprecation_date": "2026-09-28", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 1.5e-06, "litellm_provider": "text-completion-openai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 2e-06, "source": "https://developers.openai.com/api/docs/pricing" @@ -31955,19 +35460,20 @@ "litellm_provider": "text-completion-openai", "max_input_tokens": 8192, "max_output_tokens": 4097, - "max_tokens": 4097, "mode": "completion", "output_cost_per_token": 2e-06 }, "gpt-4": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 3e-05, "litellm_provider": "openai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-05, + "fedramp_uplift_multiplier": 1.1, "supports_function_calling": true, "supports_prompt_caching": true, "supports_system_messages": true, @@ -31975,14 +35481,16 @@ }, "gpt-4-0613": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 3e-05, "input_cost_per_token_batches": 1.5e-05, "litellm_provider": "openai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 3e-05, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, @@ -31992,13 +35500,15 @@ }, "gpt-4-1106-preview": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1e-05, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-05, + "fedramp_uplift_multiplier": 1.1, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -32007,13 +35517,15 @@ }, "gpt-4-turbo": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1e-05, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-05, + "fedramp_uplift_multiplier": 1.1, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -32024,14 +35536,16 @@ }, "gpt-4-turbo-2024-04-09": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1e-05, "input_cost_per_token_batches": 5e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 1.5e-05, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, @@ -32045,15 +35559,18 @@ "gpt-4.1": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_priority": 8.75e-07, + "deprecation_date": "2027-01-14", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna", "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 4e-06, "output_cost_per_token_priority": 1.4e-05, "search_context_cost_per_query": { @@ -32088,15 +35605,18 @@ "gpt-4.1-2025-04-14": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_priority": 8.75e-07, + "deprecation_date": "2027-01-14", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna", "input_cost_per_token": 2e-06, "input_cost_per_token_priority": 3.5e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 1.4e-05, "output_cost_per_token_batches": 4e-06, "search_context_cost_per_query": { @@ -32131,15 +35651,18 @@ "gpt-4.1-mini": { "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_priority": 1.75e-07, + "deprecation_date": "2027-01-14", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna", "input_cost_per_token": 4e-07, "input_cost_per_token_batches": 2e-07, "input_cost_per_token_priority": 7e-07, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 8e-07, "output_cost_per_token_priority": 2.8e-06, "search_context_cost_per_query": { @@ -32174,15 +35697,18 @@ "gpt-4.1-mini-2025-04-14": { "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_priority": 1.75e-07, + "deprecation_date": "2027-01-14", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna", "input_cost_per_token": 4e-07, "input_cost_per_token_priority": 7e-07, "input_cost_per_token_batches": 2e-07, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 2.8e-06, "output_cost_per_token_batches": 8e-07, "search_context_cost_per_query": { @@ -32218,15 +35744,17 @@ "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_priority": 5e-08, "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-luna", "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, "input_cost_per_token_priority": 2e-07, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 2e-07, "output_cost_per_token_priority": 8e-07, "source": "https://developers.openai.com/api/docs/pricing", @@ -32256,15 +35784,17 @@ "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_priority": 5e-08, "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-luna", "input_cost_per_token": 1e-07, "input_cost_per_token_priority": 2e-07, "input_cost_per_token_batches": 5e-08, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 8e-07, "output_cost_per_token_batches": 2e-07, "source": "https://developers.openai.com/api/docs/pricing", @@ -32293,15 +35823,18 @@ "gpt-4o": { "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_priority": 2.125e-06, + "deprecation_date": "2027-01-14", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna", "input_cost_per_token": 2.5e-06, "input_cost_per_token_batches": 1.25e-06, "input_cost_per_token_priority": 4.25e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 1.7e-05, "source": "https://developers.openai.com/api/docs/pricing", @@ -32316,15 +35849,17 @@ }, "gpt-4o-2024-05-13": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "input_cost_per_token_priority": 8.75e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 7.5e-06, "output_cost_per_token_priority": 2.625e-05, "source": "https://developers.openai.com/api/docs/pricing", @@ -32339,15 +35874,18 @@ "gpt-4o-2024-08-06": { "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_priority": 2.125e-06, + "deprecation_date": "2027-01-14", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna", "input_cost_per_token": 2.5e-06, "input_cost_per_token_priority": 4.25e-06, "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 1.7e-05, "output_cost_per_token_batches": 5e-06, "source": "https://developers.openai.com/api/docs/pricing", @@ -32363,15 +35901,18 @@ "gpt-4o-2024-11-20": { "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_priority": 2.125e-06, + "deprecation_date": "2027-01-14", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna", "input_cost_per_token": 2.5e-06, "input_cost_per_token_priority": 4.25e-06, "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 1.7e-05, "output_cost_per_token_batches": 5e-06, "source": "https://developers.openai.com/api/docs/pricing", @@ -32386,12 +35927,13 @@ }, "gpt-4o-audio-preview-2024-12-17": { "deprecation_date": "2027-01-20", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-audio-1.5", "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 1e-05, @@ -32404,12 +35946,13 @@ }, "gpt-4o-audio-preview-2025-06-03": { "deprecation_date": "2027-01-20", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-audio-1.5", "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 1e-05, @@ -32422,12 +35965,13 @@ }, "gpt-audio": { "deprecation_date": "2027-01-20", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-audio-1.5", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, @@ -32464,7 +36008,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, @@ -32494,12 +36037,13 @@ }, "gpt-audio-2025-08-28": { "deprecation_date": "2027-01-20", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-audio-1.5", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, @@ -32532,12 +36076,13 @@ }, "gpt-audio-mini": { "deprecation_date": "2027-01-20", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-audio-1.5", "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 6e-07, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -32568,13 +36113,51 @@ "supports_tool_choice": true, "supports_vision": false }, + "gpt-audio-mini-2025-10-06": { + "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-audio-1.5", + "input_cost_per_audio_token": 1e-05, + "input_cost_per_token": 6e-07, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 2.4e-06, + "source": "https://developers.openai.com/api/docs/models/gpt-audio-mini", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/realtime", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, "gpt-audio-mini-2025-12-15": { "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 6e-07, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -32604,20 +36187,25 @@ "supports_tool_choice": true, "supports_vision": false, "deprecation_date": "2027-01-20", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-audio-1.5", "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-4o-mini": { "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_priority": 1.25e-07, + "deprecation_date": "2027-01-14", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna", "input_cost_per_token": 1.5e-07, "input_cost_per_token_batches": 7.5e-08, "input_cost_per_token_priority": 2.5e-07, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 3e-07, "output_cost_per_token_priority": 1e-06, "supports_function_calling": true, @@ -32638,15 +36226,18 @@ "gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_priority": 1.25e-07, + "deprecation_date": "2027-01-14", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna", "input_cost_per_token": 1.5e-07, "input_cost_per_token_priority": 2.5e-07, "input_cost_per_token_batches": 7.5e-08, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 1e-06, "output_cost_per_token_batches": 3e-07, "search_context_cost_per_query": { @@ -32666,12 +36257,12 @@ }, "gpt-4o-mini-audio-preview-2024-12-17": { "deprecation_date": "2027-01-20", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 1.5e-07, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 6e-07, @@ -32686,12 +36277,12 @@ "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2027-01-20", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 6e-07, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -32709,9 +36300,9 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 3e-07, "search_context_cost_per_query": { "search_context_size_high": 0.025, @@ -32728,6 +36319,36 @@ "supports_vision": true, "supports_web_search": true }, + "gpt-4o-mini-search-preview-2025-03-11": { + "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6e-07, + "fedramp_uplift_multiplier": 1.1, + "output_cost_per_token_batches": 3e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.025, + "search_context_size_low": 0.025, + "search_context_size_medium": 0.025 + }, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "source": "https://developers.openai.com/api/docs/models/gpt-4o-mini-search-preview" + }, "gpt-4o-mini-transcribe": { "input_cost_per_audio_token": 1.25e-06, "input_cost_per_token": 1.25e-06, @@ -32740,10 +36361,15 @@ "/v1/audio/transcriptions" ], "deprecation_date": "2027-02-26", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-live-transcribe", "input_cost_per_second": 5e-05, "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-4o-mini-tts": { + "deprecation_date": "2027-01-06", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-realtime-2.1-mini", "input_cost_per_token": 6e-07, "litellm_provider": "openai", "mode": "audio_speech", @@ -32763,6 +36389,9 @@ ] }, "gpt-4o-mini-tts-2025-03-20": { + "deprecation_date": "2027-01-06", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-realtime-2.1-mini", "input_cost_per_token": 6e-07, "litellm_provider": "openai", "mode": "audio_speech", @@ -32788,9 +36417,9 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.025, @@ -32807,6 +36436,36 @@ "supports_vision": true, "supports_web_search": true }, + "gpt-4o-search-preview-2025-03-11": { + "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, + "output_cost_per_token_batches": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.025, + "search_context_size_low": 0.025, + "search_context_size_medium": 0.025 + }, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "source": "https://developers.openai.com/api/docs/models/gpt-4o-search-preview" + }, "gpt-4o-transcribe": { "input_cost_per_audio_token": 2.5e-06, "input_cost_per_token": 2.5e-06, @@ -32819,14 +36478,19 @@ "/v1/audio/transcriptions" ], "deprecation_date": "2027-02-26", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-live-transcribe", "input_cost_per_second": 0.0001, "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-image-1.5": { "cache_read_input_image_token_cost": 2e-06, + "cache_read_input_image_token_cost_batches": 1e-06, "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_batches": 6.3e-07, "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", @@ -32835,6 +36499,7 @@ "input_cost_per_image_token_batches": 4e-06, "input_cost_per_token_batches": 2.5e-06, "output_cost_per_image_token": 3.2e-05, + "output_cost_per_image_token_batches": 1.6e-05, "output_cost_per_token_batches": 5e-06, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ @@ -32848,6 +36513,8 @@ "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_batches": 6.3e-07, "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", @@ -32856,6 +36523,7 @@ "input_cost_per_image_token_batches": 4e-06, "input_cost_per_token_batches": 2.5e-06, "output_cost_per_image_token": 3.2e-05, + "output_cost_per_image_token_batches": 1.6e-05, "output_cost_per_token_batches": 5e-06, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ @@ -32866,8 +36534,11 @@ }, "gpt-image-2": { "cache_read_input_image_token_cost": 2e-06, + "cache_read_input_image_token_cost_batches": 1e-06, "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_batches": 6.25e-07, + "deprecation_date": "2027-02-10", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", @@ -32875,7 +36546,9 @@ "input_cost_per_image_token_batches": 4e-06, "input_cost_per_token_batches": 2.5e-06, "output_cost_per_image_token": 3e-05, + "output_cost_per_image_token_batches": 1.5e-05, "source": "https://developers.openai.com/api/docs/pricing", + "successor_model": "gpt-image-2.6-sunburst", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -32886,12 +36559,15 @@ "gpt-image-2-2026-04-21": { "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, + "deprecation_date": "2027-02-10", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", "input_cost_per_image_token": 8e-06, "output_cost_per_image_token": 3e-05, "source": "https://developers.openai.com/api/docs/pricing", + "successor_model": "gpt-image-2.6-sunburst", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -32901,12 +36577,17 @@ }, "gpt-image-2.5-flare": { "cache_read_input_image_token_cost": 2e-06, + "cache_read_input_image_token_cost_batches": 1e-06, "cache_read_input_token_cost": 1.25e-06, + "cache_read_input_token_cost_batches": 6.25e-07, "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", "input_cost_per_image_token": 8e-06, + "input_cost_per_image_token_batches": 4e-06, + "input_cost_per_token_batches": 2.5e-06, "output_cost_per_image_token": 3e-05, + "output_cost_per_image_token_batches": 1.5e-05, "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -32933,12 +36614,17 @@ }, "gpt-image-2.5-sunburst": { "cache_read_input_image_token_cost": 2e-06, + "cache_read_input_image_token_cost_batches": 1e-06, "cache_read_input_token_cost": 1.25e-06, + "cache_read_input_token_cost_batches": 6.25e-07, "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", "input_cost_per_image_token": 8e-06, + "input_cost_per_image_token_batches": 4e-06, + "input_cost_per_token_batches": 2.5e-06, "output_cost_per_image_token": 3e-05, + "output_cost_per_image_token_batches": 1.5e-05, "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -32965,6 +36651,8 @@ }, "low/1024-x-1024/gpt-image-1.5": { "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.009, "litellm_provider": "openai", "mode": "image_generation", @@ -32977,6 +36665,8 @@ }, "low/1024-x-1536/gpt-image-1.5": { "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", @@ -32989,6 +36679,8 @@ }, "low/1536-x-1024/gpt-image-1.5": { "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", @@ -33001,6 +36693,8 @@ }, "medium/1024-x-1024/gpt-image-1.5": { "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.034, "litellm_provider": "openai", "mode": "image_generation", @@ -33013,6 +36707,8 @@ }, "medium/1024-x-1536/gpt-image-1.5": { "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.05, "litellm_provider": "openai", "mode": "image_generation", @@ -33025,6 +36721,8 @@ }, "medium/1536-x-1024/gpt-image-1.5": { "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.05, "litellm_provider": "openai", "mode": "image_generation", @@ -33037,6 +36735,8 @@ }, "high/1024-x-1024/gpt-image-1.5": { "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.133, "litellm_provider": "openai", "mode": "image_generation", @@ -33049,6 +36749,8 @@ }, "high/1024-x-1536/gpt-image-1.5": { "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.2, "litellm_provider": "openai", "mode": "image_generation", @@ -33061,6 +36763,8 @@ }, "high/1536-x-1024/gpt-image-1.5": { "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.2, "litellm_provider": "openai", "mode": "image_generation", @@ -33073,6 +36777,8 @@ }, "standard/1024-x-1024/gpt-image-1.5": { "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.009, "litellm_provider": "openai", "mode": "image_generation", @@ -33085,6 +36791,8 @@ }, "standard/1024-x-1536/gpt-image-1.5": { "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", @@ -33097,6 +36805,8 @@ }, "standard/1536-x-1024/gpt-image-1.5": { "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", @@ -33109,6 +36819,8 @@ }, "1024-x-1024/gpt-image-1.5": { "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.009, "litellm_provider": "openai", "mode": "image_generation", @@ -33121,6 +36833,8 @@ }, "1024-x-1536/gpt-image-1.5": { "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", @@ -33133,6 +36847,8 @@ }, "1536-x-1024/gpt-image-1.5": { "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", @@ -33153,7 +36869,9 @@ ], "supports_vision": true, "supports_pdf_input": true, - "deprecation_date": "2026-12-01" + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst" }, "low/1024-x-1536/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.013, @@ -33165,7 +36883,9 @@ ], "supports_vision": true, "supports_pdf_input": true, - "deprecation_date": "2026-12-01" + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst" }, "low/1536-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.013, @@ -33177,7 +36897,9 @@ ], "supports_vision": true, "supports_pdf_input": true, - "deprecation_date": "2026-12-01" + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst" }, "medium/1024-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.034, @@ -33189,7 +36911,9 @@ ], "supports_vision": true, "supports_pdf_input": true, - "deprecation_date": "2026-12-01" + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst" }, "medium/1024-x-1536/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.05, @@ -33201,7 +36925,9 @@ ], "supports_vision": true, "supports_pdf_input": true, - "deprecation_date": "2026-12-01" + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst" }, "medium/1536-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.05, @@ -33213,7 +36939,9 @@ ], "supports_vision": true, "supports_pdf_input": true, - "deprecation_date": "2026-12-01" + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst" }, "high/1024-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.133, @@ -33225,7 +36953,9 @@ ], "supports_vision": true, "supports_pdf_input": true, - "deprecation_date": "2026-12-01" + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst" }, "high/1024-x-1536/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.2, @@ -33237,7 +36967,9 @@ ], "supports_vision": true, "supports_pdf_input": true, - "deprecation_date": "2026-12-01" + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst" }, "high/1536-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.2, @@ -33249,7 +36981,9 @@ ], "supports_vision": true, "supports_pdf_input": true, - "deprecation_date": "2026-12-01" + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst" }, "standard/1024-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.009, @@ -33261,7 +36995,9 @@ ], "supports_vision": true, "supports_pdf_input": true, - "deprecation_date": "2026-12-01" + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst" }, "standard/1024-x-1536/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.013, @@ -33273,7 +37009,9 @@ ], "supports_vision": true, "supports_pdf_input": true, - "deprecation_date": "2026-12-01" + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst" }, "standard/1536-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.013, @@ -33285,7 +37023,9 @@ ], "supports_vision": true, "supports_pdf_input": true, - "deprecation_date": "2026-12-01" + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst" }, "1024-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.009, @@ -33297,7 +37037,9 @@ ], "supports_vision": true, "supports_pdf_input": true, - "deprecation_date": "2026-12-01" + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst" }, "1024-x-1536/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.013, @@ -33309,7 +37051,9 @@ ], "supports_vision": true, "supports_pdf_input": true, - "deprecation_date": "2026-12-01" + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst" }, "1536-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.013, @@ -33321,13 +37065,18 @@ ], "supports_vision": true, "supports_pdf_input": true, - "deprecation_date": "2026-12-01" + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst" }, "gpt-5": { "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_batches": 6.25e-08, "cache_read_input_token_cost_flex": 6.25e-08, "cache_read_input_token_cost_priority": 2.5e-07, + "deprecation_date": "2026-12-11", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.25e-06, "input_cost_per_token_batches": 6.25e-07, "input_cost_per_token_flex": 6.25e-07, @@ -33335,12 +37084,19 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_flex": 5e-06, "output_cost_per_token_priority": 2e-05, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "standard" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -33377,13 +37133,15 @@ "gpt-5-codex": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/gpt-5-codex", "supported_endpoints": [ "/v1/responses" @@ -33416,10 +37174,17 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 2e-05, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "standard" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -33456,18 +37221,23 @@ "output_cost_per_token_flex": 5e-06, "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": false + "supports_minimal_reasoning_effort": false, + "deprecation_date": "2027-04-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-sol" }, "gpt-5.1-codex-mini": { "cache_read_input_token_cost": 2.5e-08, "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 2.5e-07, "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, + "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/gpt-5.1-codex-mini", "supported_endpoints": [ "/v1/responses" @@ -33492,13 +37262,15 @@ "gpt-5.1-codex-max": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/gpt-5.1-codex-max", "supported_endpoints": [ "/v1/responses" @@ -33524,13 +37296,15 @@ "gpt-5.1-codex": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/gpt-5.1-codex", "supported_endpoints": [ "/v1/responses" @@ -33556,13 +37330,15 @@ "gpt-5.1-chat-latest": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/gpt-5.1-chat-latest", "supported_endpoints": [ "/v1/chat/completions", @@ -33590,15 +37366,25 @@ "cache_read_input_token_cost_batches": 6.25e-08, "cache_read_input_token_cost_flex": 6.25e-08, "cache_read_input_token_cost_priority": 2.5e-07, + "deprecation_date": "2027-04-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-sol", "input_cost_per_token": 1.25e-06, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 2e-05, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "standard" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -33647,10 +37433,17 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 2.8e-05, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "standard" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -33678,6 +37471,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, @@ -33693,13 +37487,15 @@ "gpt-5.2-codex": { "cache_read_input_token_cost": 1.75e-07, "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.75e-06, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, + "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/gpt-5.2-codex", "supported_endpoints": [ "/v1/responses" @@ -33725,13 +37521,15 @@ "gpt-5.2-chat-latest": { "cache_read_input_token_cost": 1.75e-07, "deprecation_date": "2026-08-10", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.75e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.4e-05, + "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/gpt-5.2-chat-latest", "supported_endpoints": [ "/v1/chat/completions", @@ -33764,10 +37562,17 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 2.8e-05, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "standard" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -33795,6 +37600,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, @@ -33813,10 +37619,17 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 8.4e-05, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "pro" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -33855,10 +37668,17 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 8.4e-05, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "pro" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -33893,6 +37713,16 @@ }, "gpt-6-astra": { "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_12hr": 2.5e-05, + "cache_creation_input_token_cost_above_12hr_ultrafast": 0.00015, + "cache_creation_input_token_cost_above_12hr_batches": 1.25e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 5e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 2.5e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 2.5e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 0.0001, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_ultrafast": 0.0003, + "cache_creation_input_token_cost_above_12hr_flex": 1.25e-05, + "cache_creation_input_token_cost_above_12hr_priority": 5e-05, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-05, "cache_creation_input_token_cost_above_272k_tokens_priority": 5e-05, @@ -33925,7 +37755,6 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_above_272k_tokens": 7.5e-05, @@ -33937,8 +37766,18 @@ "output_cost_per_token_flex": 2.5e-05, "output_cost_per_token_priority": 0.0001, "output_cost_per_token_ultrafast": 0.0003, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard", + "pro" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -33971,12 +37810,24 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "gpt-astra-latest": { + "alias_of": "gpt-6-astra" + }, "gpt-6-sol": { "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_12hr": 5e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 1e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 5e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 5e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 2e-05, + "cache_creation_input_token_cost_above_12hr_batches": 2.5e-06, + "cache_creation_input_token_cost_above_12hr_flex": 2.5e-06, + "cache_creation_input_token_cost_above_12hr_priority": 1e-05, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, @@ -34003,7 +37854,6 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, @@ -34013,8 +37863,18 @@ "output_cost_per_token_above_272k_tokens_batches": 7.5e-06, "output_cost_per_token_flex": 5e-06, "output_cost_per_token_priority": 2e-05, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard", + "pro" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -34047,19 +37907,32 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "gpt-6-luna": { "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_12hr": 2.5e-07, + "cache_creation_input_token_cost_above_12hr_batches": 1.25e-07, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 5e-07, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 2.5e-07, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 2.5e-07, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 1e-06, + "cache_creation_input_token_cost_above_12hr_flex": 1.25e-07, + "cache_creation_input_token_cost_above_12hr_priority": 5e-07, + "cache_creation_input_token_cost_decisions": 1.25e-07, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, + "cache_creation_input_token_cost_above_272k_tokens_decisions": 2.5e-07, "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-07, "cache_creation_input_token_cost_above_272k_tokens_priority": 5e-07, "cache_creation_input_token_cost_flex": 6.25e-08, "cache_creation_input_token_cost_priority": 2.5e-07, "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_decisions": 1e-08, "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "cache_read_input_token_cost_above_272k_tokens_decisions": 2e-08, "cache_read_input_token_cost_above_272k_tokens_flex": 1e-08, "cache_read_input_token_cost_above_272k_tokens_priority": 4e-08, "cache_read_input_token_cost_batches": 5e-09, @@ -34069,7 +37942,9 @@ "cache_read_input_token_cost_flex": 5e-09, "cache_read_input_token_cost_priority": 2e-08, "input_cost_per_token": 1e-07, + "input_cost_per_token_decisions": 1e-07, "input_cost_per_token_above_272k_tokens": 2e-07, + "input_cost_per_token_above_272k_tokens_decisions": 2e-07, "input_cost_per_token_above_272k_tokens_flex": 1e-07, "input_cost_per_token_above_272k_tokens_priority": 4e-07, "input_cost_per_token_batches": 5e-08, @@ -34079,18 +37954,29 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, + "output_cost_per_token_decisions": 0.0, "output_cost_per_token_above_272k_tokens": 7.5e-07, + "output_cost_per_token_above_272k_tokens_decisions": 0.0, "output_cost_per_token_above_272k_tokens_flex": 3.75e-07, "output_cost_per_token_above_272k_tokens_priority": 1.5e-06, "output_cost_per_token_batches": 2.5e-07, "output_cost_per_token_above_272k_tokens_batches": 3.75e-07, "output_cost_per_token_flex": 2.5e-07, "output_cost_per_token_priority": 1e-06, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard", + "pro" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -34100,7 +37986,8 @@ "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", - "/v1/responses" + "/v1/responses", + "/v1/decisions" ], "supported_modalities": [ "text", @@ -34123,12 +38010,22 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "gpt-luna-latest": { + "alias_of": "gpt-6-luna" + }, "gpt-5.6": { "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_12hr": 1e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 2e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 1e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 4e-05, + "cache_creation_input_token_cost_above_12hr_flex": 5e-06, + "cache_creation_input_token_cost_above_12hr_priority": 2e-05, "cache_creation_input_token_cost_above_272k_tokens": 1e-05, "cache_creation_input_token_cost_above_272k_tokens_flex": 5e-06, "cache_creation_input_token_cost_above_272k_tokens_priority": 2e-05, @@ -34155,7 +38052,6 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, @@ -34165,8 +38061,18 @@ "output_cost_per_token_above_272k_tokens_batches": 1.5e-05, "output_cost_per_token_flex": 1e-05, "output_cost_per_token_priority": 4e-05, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard", + "pro" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -34196,12 +38102,21 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "gpt-5.6-sol": { "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_12hr": 1e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 2e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 1e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 1e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 4e-05, + "cache_creation_input_token_cost_above_12hr_batches": 5e-06, + "cache_creation_input_token_cost_above_12hr_flex": 5e-06, + "cache_creation_input_token_cost_above_12hr_priority": 2e-05, "cache_creation_input_token_cost_above_272k_tokens": 1e-05, "cache_creation_input_token_cost_above_272k_tokens_flex": 5e-06, "cache_creation_input_token_cost_above_272k_tokens_priority": 2e-05, @@ -34228,7 +38143,6 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, @@ -34238,8 +38152,18 @@ "output_cost_per_token_above_272k_tokens_batches": 1.5e-05, "output_cost_per_token_flex": 1e-05, "output_cost_per_token_priority": 4e-05, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard", + "pro" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -34271,12 +38195,21 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "gpt-5.6-terra": { "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_12hr": 5e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 1e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 5e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 5e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 2e-05, + "cache_creation_input_token_cost_above_12hr_batches": 2.5e-06, + "cache_creation_input_token_cost_above_12hr_flex": 2.5e-06, + "cache_creation_input_token_cost_above_12hr_priority": 1e-05, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, @@ -34303,7 +38236,6 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, @@ -34313,8 +38245,18 @@ "output_cost_per_token_above_272k_tokens_batches": 9e-06, "output_cost_per_token_flex": 6e-06, "output_cost_per_token_priority": 2.4e-05, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard", + "pro" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -34345,12 +38287,21 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "gpt-5.6-luna": { "cache_creation_input_token_cost": 2.5e-07, + "cache_creation_input_token_cost_above_12hr": 5e-07, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 1e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 5e-07, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 5e-07, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 2e-06, + "cache_creation_input_token_cost_above_12hr_batches": 2.5e-07, + "cache_creation_input_token_cost_above_12hr_flex": 2.5e-07, + "cache_creation_input_token_cost_above_12hr_priority": 1e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-07, "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-07, "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-06, @@ -34377,7 +38328,6 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_above_272k_tokens": 1.8e-06, @@ -34387,8 +38337,18 @@ "output_cost_per_token_above_272k_tokens_batches": 9e-07, "output_cost_per_token_flex": 6e-07, "output_cost_per_token_priority": 2.4e-06, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard", + "pro" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -34419,23 +38379,25 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "gpt-5.6-cyber": { "cache_creation_input_token_cost": 1.5625e-05, + "cache_creation_input_token_cost_above_12hr": 3.125e-05, "cache_creation_input_token_cost_above_272k_tokens": 3.125e-05, "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_above_272k_tokens": 2.5e-06, "input_cost_per_token": 1.25e-05, "input_cost_per_token_above_272k_tokens": 2.5e-05, "litellm_provider": "openai", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 7.5e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_above_272k_tokens": 0.0001125, "supported_endpoints": [ "/v1/chat/completions", @@ -34470,11 +38432,11 @@ "input_cost_per_token": 1.25e-05, "input_cost_per_token_above_272k_tokens": 2.5e-05, "litellm_provider": "openai", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 7.5e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_above_272k_tokens": 0.0001125, "supported_endpoints": [ "/v1/chat/completions", @@ -34509,11 +38471,11 @@ "input_cost_per_token": 1.25e-05, "input_cost_per_token_above_272k_tokens": 2.5e-05, "litellm_provider": "openai", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 7.5e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_above_272k_tokens": 0.0001125, "supported_endpoints": [ "/v1/responses" @@ -34549,9 +38511,9 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_above_272k_tokens": 3e-05, "supported_endpoints": [ "/v1/chat/completions", @@ -34588,9 +38550,9 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_above_272k_tokens": 3e-05, "supported_endpoints": [ "/v1/responses" @@ -34622,12 +38584,20 @@ "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, + "fedramp_uplift_multiplier": 1.1, "reasoning_effort_levels": [ "medium" ], + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard" + ], "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -34668,7 +38638,6 @@ "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, @@ -34676,8 +38645,17 @@ "output_cost_per_token_batches": 1.5e-05, "output_cost_per_token_above_272k_tokens_batches": 2.25e-05, "output_cost_per_token_priority": 7.5e-05, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -34704,6 +38682,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, @@ -34730,7 +38709,6 @@ "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, @@ -34738,8 +38716,17 @@ "output_cost_per_token_batches": 1.5e-05, "output_cost_per_token_above_272k_tokens_batches": 2.25e-05, "output_cost_per_token_priority": 7.5e-05, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -34766,6 +38753,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, @@ -34785,15 +38773,23 @@ "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 9e-05, "output_cost_per_token_batches": 9e-05, "output_cost_per_token_above_272k_tokens_batches": 0.000135, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "pro" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -34820,6 +38816,7 @@ "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, @@ -34836,15 +38833,23 @@ "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 9e-05, "output_cost_per_token_batches": 9e-05, "output_cost_per_token_above_272k_tokens_batches": 0.000135, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "pro" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -34871,6 +38876,7 @@ "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, @@ -34894,7 +38900,6 @@ "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_above_272k_tokens": 2.25e-05, @@ -34902,8 +38907,17 @@ "output_cost_per_token_batches": 7.5e-06, "output_cost_per_token_above_272k_tokens_batches": 1.125e-05, "output_cost_per_token_priority": 3e-05, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -34925,6 +38939,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", @@ -34951,7 +38966,6 @@ "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_above_272k_tokens": 2.25e-05, @@ -34959,8 +38973,17 @@ "output_cost_per_token_batches": 7.5e-06, "output_cost_per_token_above_272k_tokens_batches": 1.125e-05, "output_cost_per_token_priority": 3e-05, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -34982,6 +39005,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", @@ -35001,15 +39025,23 @@ "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 9e-05, "output_cost_per_token_batches": 9e-05, "output_cost_per_token_above_272k_tokens_batches": 0.000135, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "pro" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -35035,6 +39067,7 @@ "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, @@ -35053,15 +39086,23 @@ "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 9e-05, "output_cost_per_token_batches": 9e-05, "output_cost_per_token_above_272k_tokens_batches": 0.000135, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "pro" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -35087,6 +39128,7 @@ "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, @@ -35108,14 +39150,22 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "output_cost_per_token_flex": 2.25e-06, "output_cost_per_token_batches": 2.25e-06, "output_cost_per_token_priority": 9e-06, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -35142,6 +39192,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, @@ -35150,6 +39201,9 @@ "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, + "gpt-mini-latest": { + "alias_of": "gpt-5.4-mini" + }, "gpt-5.4-mini-2026-03-17": { "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, @@ -35162,14 +39216,22 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "output_cost_per_token_flex": 2.25e-06, "output_cost_per_token_batches": 2.25e-06, "output_cost_per_token_priority": 9e-06, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -35196,6 +39258,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, @@ -35214,13 +39277,21 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "output_cost_per_token_flex": 6.25e-07, "output_cost_per_token_batches": 6.25e-07, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -35253,25 +39324,39 @@ "default_reasoning_effort": "none", "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": false + "supports_minimal_reasoning_effort": false, + "deprecation_date": "2027-04-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna" }, "gpt-5.4-nano-2026-03-17": { "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_batches": 1e-08, "cache_read_input_token_cost_flex": 1e-08, + "deprecation_date": "2027-04-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna", "input_cost_per_token": 2e-07, "input_cost_per_token_flex": 1e-07, "input_cost_per_token_batches": 1e-07, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "output_cost_per_token_flex": 6.25e-07, "output_cost_per_token_batches": 6.25e-07, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -35307,15 +39392,25 @@ "supports_minimal_reasoning_effort": false }, "gpt-5-pro": { + "deprecation_date": "2026-12-11", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.5e-05, "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 272000, - "max_tokens": 272000, "mode": "responses", "output_cost_per_token": 0.00012, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 6e-05, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "pro" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -35350,15 +39445,24 @@ }, "gpt-5-pro-2025-10-06": { "deprecation_date": "2026-12-11", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.5e-05, "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 272000, - "max_tokens": 272000, "mode": "responses", "output_cost_per_token": 0.00012, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 6e-05, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "pro" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -35397,6 +39501,8 @@ "cache_read_input_token_cost_flex": 6.25e-08, "cache_read_input_token_cost_priority": 2.5e-07, "deprecation_date": "2026-12-11", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.25e-06, "input_cost_per_token_batches": 6.25e-07, "input_cost_per_token_flex": 6.25e-07, @@ -35404,12 +39510,19 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_flex": 5e-06, "output_cost_per_token_priority": 2e-05, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "standard" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -35446,13 +39559,15 @@ "gpt-5-chat": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.2-chat-latest", "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -35482,13 +39597,15 @@ "gpt-5-chat-latest": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/gpt-5-chat-latest", "supported_endpoints": [ "/v1/chat/completions", @@ -35519,10 +39636,17 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 2.8e-05, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "standard" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -35548,22 +39672,28 @@ "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "deprecation_date": "2027-04-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-sol" }, "gpt-5.3-chat-latest": { "cache_read_input_token_cost": 1.75e-07, "deprecation_date": "2026-08-10", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.75e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.4e-05, + "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/gpt-5.3-chat-latest", "supported_endpoints": [ "/v1/chat/completions", @@ -35591,6 +39721,9 @@ "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, + "deprecation_date": "2026-12-11", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_flex": 1.25e-07, @@ -35598,12 +39731,19 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 1e-06, "output_cost_per_token_flex": 1e-06, "output_cost_per_token_priority": 3.6e-06, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "standard" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -35643,6 +39783,8 @@ "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, "deprecation_date": "2026-12-11", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_flex": 1.25e-07, @@ -35650,12 +39792,19 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 1e-06, "output_cost_per_token_flex": 1e-06, "output_cost_per_token_priority": 3.6e-06, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "standard" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -35693,18 +39842,27 @@ "cache_read_input_token_cost": 5e-09, "cache_read_input_token_cost_batches": 2.5e-09, "cache_read_input_token_cost_flex": 2.5e-09, + "deprecation_date": "2026-12-11", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-luna", "input_cost_per_token": 5e-08, "input_cost_per_token_batches": 2.5e-08, "input_cost_per_token_flex": 2.5e-08, - "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 2e-07, "output_cost_per_token_flex": 2e-07, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "standard" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -35743,18 +39901,26 @@ "cache_read_input_token_cost_batches": 2.5e-09, "cache_read_input_token_cost_flex": 2.5e-09, "deprecation_date": "2026-12-11", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-luna", "input_cost_per_token": 5e-08, "input_cost_per_token_batches": 2.5e-08, - "input_cost_per_token_priority": 2.5e-06, "input_cost_per_token_flex": 2.5e-08, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 2e-07, "output_cost_per_token_flex": 2e-07, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "standard" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -35793,6 +39959,8 @@ "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_batches": 6.3e-07, "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image_token": 1e-05, "input_cost_per_image_token_batches": 5e-06, "input_cost_per_token": 5e-06, @@ -35808,9 +39976,12 @@ }, "gpt-image-1-mini": { "cache_read_input_image_token_cost": 2.5e-07, + "cache_read_input_image_token_cost_batches": 1.3e-07, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1e-07, "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image_token": 2.5e-06, "input_cost_per_image_token_batches": 1.25e-06, "input_cost_per_token": 2e-06, @@ -35818,6 +39989,7 @@ "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_image_token": 8e-06, + "output_cost_per_image_token_batches": 4e-06, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/images/generations", @@ -35830,13 +40002,14 @@ "cache_read_input_image_token_cost": 5e-07, "cache_read_input_token_cost": 4e-07, "deprecation_date": "2027-01-20", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-realtime-2.1", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, @@ -35871,7 +40044,6 @@ "litellm_provider": "openai", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, @@ -35906,8 +40078,10 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "realtime", + "provider_specific_entry": { + "realtime_ga_only": 1 + }, "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 2.4e-05, "source": "https://developers.openai.com/api/docs/pricing", @@ -35941,7 +40115,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 2.4e-05, @@ -35964,6 +40137,8 @@ "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true }, @@ -35978,7 +40153,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -36001,6 +40175,8 @@ "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true }, @@ -36010,13 +40186,14 @@ "cache_read_input_image_token_cost": 8e-08, "cache_read_input_token_cost": 6e-08, "deprecation_date": "2027-01-20", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-realtime-2.1-mini", "input_cost_per_audio_token": 1e-05, "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "openai", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -36046,13 +40223,14 @@ "cache_read_input_image_token_cost": 5e-07, "cache_read_input_token_cost": 4e-07, "deprecation_date": "2027-01-20", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-realtime-2.1", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, @@ -36078,7 +40256,6 @@ }, "gradient_ai/alibaba-qwen3-32b": { "litellm_provider": "gradient_ai", - "max_tokens": 40960, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" @@ -36093,7 +40270,6 @@ "gradient_ai/anthropic-claude-3-opus": { "input_cost_per_token": 1.5e-05, "litellm_provider": "gradient_ai", - "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 7.5e-05, "supported_endpoints": [ @@ -36109,7 +40285,6 @@ "gradient_ai/anthropic-claude-3.5-haiku": { "input_cost_per_token": 8e-07, "litellm_provider": "gradient_ai", - "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 4e-06, "supported_endpoints": [ @@ -36125,7 +40300,6 @@ "gradient_ai/anthropic-claude-3.5-sonnet": { "input_cost_per_token": 3e-06, "litellm_provider": "gradient_ai", - "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 1.5e-05, "supported_endpoints": [ @@ -36141,7 +40315,6 @@ "gradient_ai/anthropic-claude-3.7-sonnet": { "input_cost_per_token": 3e-06, "litellm_provider": "gradient_ai", - "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 1.5e-05, "supported_endpoints": [ @@ -36157,7 +40330,6 @@ "gradient_ai/deepseek-r1-distill-llama-70b": { "input_cost_per_token": 9.9e-07, "litellm_provider": "gradient_ai", - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 9.9e-07, "supported_endpoints": [ @@ -36173,7 +40345,6 @@ "gradient_ai/llama3-8b-instruct": { "input_cost_per_token": 2e-07, "litellm_provider": "gradient_ai", - "max_tokens": 512, "mode": "chat", "output_cost_per_token": 2e-07, "supported_endpoints": [ @@ -36189,7 +40360,6 @@ "gradient_ai/llama3.3-70b-instruct": { "input_cost_per_token": 6.5e-07, "litellm_provider": "gradient_ai", - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 6.5e-07, "supported_endpoints": [ @@ -36205,7 +40375,6 @@ "gradient_ai/mistral-nemo-instruct-2407": { "input_cost_per_token": 3e-07, "litellm_provider": "gradient_ai", - "max_tokens": 512, "mode": "chat", "output_cost_per_token": 3e-07, "supported_endpoints": [ @@ -36220,7 +40389,6 @@ }, "gradient_ai/openai-gpt-4o": { "litellm_provider": "gradient_ai", - "max_tokens": 16384, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" @@ -36234,7 +40402,6 @@ }, "gradient_ai/openai-gpt-4o-mini": { "litellm_provider": "gradient_ai", - "max_tokens": 16384, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" @@ -36249,7 +40416,6 @@ "gradient_ai/openai-o3": { "input_cost_per_token": 2e-06, "litellm_provider": "gradient_ai", - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, "supported_endpoints": [ @@ -36265,7 +40431,6 @@ "gradient_ai/openai-o3-mini": { "input_cost_per_token": 1.1e-06, "litellm_provider": "gradient_ai", - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "supported_endpoints": [ @@ -36281,7 +40446,6 @@ "lemonade/Qwen3-Coder-30B-A3B-Instruct-GGUF": { "input_cost_per_token": 0, "litellm_provider": "lemonade", - "max_tokens": 32768, "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", @@ -36293,7 +40457,6 @@ "lemonade/gpt-oss-20b-mxfp4-GGUF": { "input_cost_per_token": 0, "litellm_provider": "lemonade", - "max_tokens": 32768, "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", @@ -36305,7 +40468,6 @@ "lemonade/gpt-oss-120b-mxfp-GGUF": { "input_cost_per_token": 0, "litellm_provider": "lemonade", - "max_tokens": 32768, "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", @@ -36317,7 +40479,6 @@ "lemonade/Gemma-3-4b-it-GGUF": { "input_cost_per_token": 0, "litellm_provider": "lemonade", - "max_tokens": 8192, "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", @@ -36329,7 +40490,6 @@ "lemonade/Qwen3-4B-Instruct-2507-GGUF": { "input_cost_per_token": 0, "litellm_provider": "lemonade", - "max_tokens": 32768, "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", @@ -36343,7 +40503,6 @@ "litellm_provider": "amazon_nova", "max_input_tokens": 128000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.4e-07, "supports_function_calling": true, @@ -36355,7 +40514,6 @@ "litellm_provider": "amazon_nova", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 2.4e-07, "supports_function_calling": true, @@ -36369,7 +40527,6 @@ "litellm_provider": "amazon_nova", "max_input_tokens": 1000000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.25e-05, "supports_function_calling": true, @@ -36383,7 +40540,6 @@ "litellm_provider": "amazon_nova", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.2e-06, "supports_function_calling": true, @@ -36392,22 +40548,11 @@ "supports_response_schema": true, "supports_vision": true }, - "groq/llama-guard-3-8b": { - "deprecation_date": "2025-06-06", - "input_cost_per_token": 2e-07, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://console.groq.com/docs/model/llama-guard-3-8b" - }, "groq/meta-llama/llama-prompt-guard-2-22m": { "input_cost_per_token": 3e-08, "litellm_provider": "groq", "max_input_tokens": 512, "max_output_tokens": 512, - "max_tokens": 512, "mode": "chat", "output_cost_per_token": 3e-08, "source": "https://console.groq.com/docs/models" @@ -36417,7 +40562,6 @@ "litellm_provider": "groq", "max_input_tokens": 512, "max_output_tokens": 512, - "max_tokens": 512, "mode": "chat", "output_cost_per_token": 4e-08, "source": "https://console.groq.com/docs/model/meta-llama/llama-prompt-guard-2-86m" @@ -36428,7 +40572,6 @@ "litellm_provider": "groq", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 6e-07, "search_context_cost_per_query": { @@ -36438,6 +40581,7 @@ }, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -36449,7 +40593,6 @@ "litellm_provider": "groq", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-07, "search_context_cost_per_query": { @@ -36459,6 +40602,7 @@ }, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -36470,7 +40614,6 @@ "litellm_provider": "groq", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-07, "search_context_cost_per_query": { @@ -36479,6 +40622,7 @@ "search_context_size_medium": 0.005 }, "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -36489,7 +40633,6 @@ "litellm_provider": "groq", "max_input_tokens": 4000, "max_output_tokens": 50000, - "max_tokens": 50000, "mode": "audio_speech", "source": "https://console.groq.com/docs/model/canopylabs/orpheus-v1-english" }, @@ -36498,7 +40641,6 @@ "litellm_provider": "groq", "max_input_tokens": 4000, "max_output_tokens": 50000, - "max_tokens": 50000, "mode": "audio_speech", "source": "https://console.groq.com/docs/models" }, @@ -36516,7 +40658,6 @@ }, "heroku/claude-3-5-haiku": { "litellm_provider": "heroku", - "max_tokens": 8192, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, @@ -36526,7 +40667,6 @@ }, "heroku/claude-3-5-sonnet-latest": { "litellm_provider": "heroku", - "max_tokens": 8192, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, @@ -36536,7 +40676,6 @@ }, "heroku/claude-3-7-sonnet": { "litellm_provider": "heroku", - "max_tokens": 8192, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, @@ -36546,7 +40685,6 @@ }, "heroku/claude-4-sonnet": { "litellm_provider": "heroku", - "max_tokens": 8192, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, @@ -36556,6 +40694,8 @@ }, "high/1024-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.167, "input_cost_per_pixel": 1.59263611e-07, "litellm_provider": "openai", @@ -36567,6 +40707,8 @@ }, "high/1024-x-1536/gpt-image-1": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.25, "input_cost_per_pixel": 1.58945719e-07, "litellm_provider": "openai", @@ -36578,6 +40720,8 @@ }, "high/1536-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.25, "input_cost_per_pixel": 1.58945719e-07, "litellm_provider": "openai", @@ -36587,12 +40731,62 @@ "/v1/images/generations" ] }, + "hostinger_router/gpt-5.2": { + "cache_read_input_token_cost": 0.00000021, + "input_cost_per_token": 0.0000021, + "litellm_provider": "hostinger_router", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.0000168, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "supported_endpoints": ["/v1/chat/completions", "/v1/responses"], + "source": "https://router.hostinger.com/v1/models" + }, + "hostinger_router/claude-sonnet-5": { + "cache_creation_input_token_cost": 3.3e-06, + "cache_creation_input_token_cost_above_1hr": 5.28e-06, + "cache_read_input_token_cost": 2.64e-07, + "input_cost_per_token": 2.64e-06, + "litellm_provider": "hostinger_router", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.32e-05, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_response_schema": true, + "supported_endpoints": ["/v1/chat/completions", "/v1/messages"], + "source": "https://router.hostinger.com/v1/models" + }, + "hostinger_router/text-embedding-3-large": { + "input_cost_per_token": 1.716e-07, + "litellm_provider": "hostinger_router", + "max_input_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://router.hostinger.com/v1/models" + }, + "hostinger_router/text-embedding-3-small": { + "input_cost_per_token": 3e-08, + "litellm_provider": "hostinger_router", + "max_input_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://router.hostinger.com/v1/models" + }, "hyperbolic/NousResearch/Hermes-3-Llama-3.1-70B": { "input_cost_per_token": 1.2e-07, "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -36605,7 +40799,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07, "supports_function_calling": true, @@ -36618,7 +40811,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -36631,7 +40823,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -36644,7 +40835,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-06, "supports_function_calling": true, @@ -36657,7 +40847,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "supports_function_calling": true, @@ -36670,7 +40859,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-07, "supports_function_calling": true, @@ -36683,7 +40871,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2e-07, "supports_function_calling": true, @@ -36696,7 +40883,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "supports_function_calling": true, @@ -36709,7 +40895,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -36722,7 +40907,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -36735,7 +40919,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -36748,7 +40931,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -36761,7 +40943,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -36774,7 +40955,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -36787,7 +40967,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-06, "supports_function_calling": true, @@ -36800,7 +40979,6 @@ "litellm_provider": "ai21", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 3e-06 }, @@ -36809,7 +40987,6 @@ "litellm_provider": "ai21", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 1e-05 }, @@ -36818,7 +40995,6 @@ "litellm_provider": "ai21", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 1.5e-05 }, @@ -36827,7 +41003,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true @@ -36837,7 +41012,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_tool_choice": true @@ -36847,7 +41021,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_tool_choice": true @@ -36857,7 +41030,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true @@ -36867,7 +41039,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true @@ -36877,7 +41048,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_tool_choice": true @@ -36887,7 +41057,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_tool_choice": true @@ -36897,7 +41066,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true @@ -36907,17 +41075,31 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true }, + "jina-reranker-v3.5": { + "input_cost_per_token": 5e-08, + "litellm_provider": "jina_ai", + "max_input_tokens": 131072, + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://api.jina.ai/v1/models" + }, + "jina-reranker-m0": { + "input_cost_per_token": 5e-08, + "litellm_provider": "jina_ai", + "max_input_tokens": 10240, + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://api.jina.ai/v1/models" + }, "jina-reranker-v2-base-multilingual": { "input_cost_per_token": 5e-08, "litellm_provider": "jina_ai", "max_input_tokens": 1024, "max_output_tokens": 1024, - "max_tokens": 1024, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://api.jina.ai/v1/models" @@ -36932,11 +41114,13 @@ "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05, "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, + "deprecation_date": "2027-04-08", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "jp.anthropic.claude-sonnet-5-5", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -36958,7 +41142,11 @@ "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.65e-06, "output_cost_per_token_batches": 8.25e-06, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "jp.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.375e-06, @@ -36969,7 +41157,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -36986,14 +41173,17 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5.5e-07, - "output_cost_per_token_batches": 2.75e-06 + "output_cost_per_token_batches": 2.75e-06, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "crusoe/deepseek-ai/DeepSeek-R1-0528": { "input_cost_per_token": 3e-06, "litellm_provider": "crusoe", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 7e-06, "supports_function_calling": false, @@ -37006,7 +41196,6 @@ "litellm_provider": "crusoe", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.5e-06, "supports_function_calling": true, @@ -37019,7 +41208,6 @@ "litellm_provider": "crusoe", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-07, "supports_function_calling": true, @@ -37033,7 +41221,6 @@ "litellm_provider": "crusoe", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07, "supports_function_calling": true, @@ -37046,7 +41233,6 @@ "litellm_provider": "crusoe", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.5e-06, "supports_function_calling": false, @@ -37059,7 +41245,6 @@ "litellm_provider": "crusoe", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-07, "supports_function_calling": true, @@ -37072,7 +41257,6 @@ "litellm_provider": "crusoe", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, "supports_function_calling": true, @@ -37086,7 +41270,6 @@ "litellm_provider": "inception", "max_input_tokens": 128000, "max_output_tokens": 50000, - "max_tokens": 50000, "mode": "chat", "output_cost_per_token": 7.5e-07, "supports_function_calling": true, @@ -37101,7 +41284,6 @@ "litellm_provider": "inception", "max_input_tokens": 260000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 7.5e-07, "source": "https://docs.inceptionlabs.ai/get-started/models", @@ -37111,4877 +41293,5132 @@ "supports_system_messages": true, "supports_tool_choice": true }, - "text-completion-inception/mercury-edit-2": { - "cache_read_input_token_cost": 2.5e-08, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "text-completion-inception", - "max_input_tokens": 32000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "completion", - "output_cost_per_token": 7.5e-07 - }, - "lambda_ai/deepseek-llama3.3-70b": { - "input_cost_per_token": 2e-07, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "inferenceapis/deepseek-ai/DeepSeek-V3": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 1.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 6e-07, + "output_cost_per_token": 3.8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/deepseek-r1-0528": { - "input_cost_per_token": 2e-07, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "inferenceapis/deepseek-ai/DeepSeek-V4-Flash": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 1.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 6e-07, + "output_cost_per_token": 3.8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/deepseek-r1-671b": { - "input_cost_per_token": 8e-07, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "inferenceapis/deepseek-ai/DeepSeek-V4-Flash-0731": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 1.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 8e-07, + "output_cost_per_token": 3.8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/deepseek-v3-0324": { - "input_cost_per_token": 2e-07, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "inferenceapis/deepseek-ai/DeepSeek-V4-Pro": { + "cache_read_input_token_cost": 1.7e-07, + "input_cost_per_token": 1.72e-06, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 6e-07, + "output_cost_per_token": 5.15e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/hermes3-405b": { - "input_cost_per_token": 8e-07, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "inferenceapis/deepseek-ai/DeepSeek-V4-Pro-0813": { + "cache_read_input_token_cost": 1.7e-07, + "input_cost_per_token": 1.72e-06, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 8e-07, + "output_cost_per_token": 5.15e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/hermes3-70b": { - "input_cost_per_token": 1.2e-07, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "inferenceapis/deepseek-ai/DeepSeek-V4.1-Flash": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 4e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 3e-07, + "output_cost_per_token": 1.6e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/hermes3-8b": { - "input_cost_per_token": 2.5e-08, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "inferenceapis/deepseek-chat": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 1.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 4e-08, + "output_cost_per_token": 3.8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/lfm-40b": { - "input_cost_per_token": 1e-07, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "inferenceapis/deepseek-flash": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 4e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 2e-07, + "output_cost_per_token": 1.6e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/lfm-7b": { - "input_cost_per_token": 2.5e-08, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "inferenceapis/deepseek-reasoner": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 1.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 4e-08, + "output_cost_per_token": 3.8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/llama-4-maverick-17b-128e-instruct-fp8": { - "input_cost_per_token": 5e-08, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 8192, - "max_tokens": 8192, + "inferenceapis/deepseek-v3": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 1.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 1e-07, + "output_cost_per_token": 3.8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/llama-4-scout-17b-16e-instruct": { - "input_cost_per_token": 5e-08, - "litellm_provider": "lambda_ai", - "max_input_tokens": 16384, - "max_output_tokens": 8192, - "max_tokens": 8192, + "inferenceapis/deepseek-v4-flash": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 1.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 1e-07, + "output_cost_per_token": 3.8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/llama3.1-405b-instruct-fp8": { - "input_cost_per_token": 8e-07, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "inferenceapis/deepseek-v4-pro": { + "cache_read_input_token_cost": 1.7e-07, + "input_cost_per_token": 1.72e-06, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 8e-07, + "output_cost_per_token": 5.15e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/llama3.1-70b-instruct-fp8": { - "input_cost_per_token": 1.2e-07, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "inferenceapis/deepseek-v4.1-flash": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 4e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 3e-07, + "output_cost_per_token": 1.6e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/llama3.1-8b-instruct": { - "input_cost_per_token": 2.5e-08, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "inferenceapis/glm-5.3": { + "cache_read_input_token_cost": 3.4e-07, + "input_cost_per_token": 1.82e-06, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048575, + "max_output_tokens": 1048575, "mode": "chat", - "output_cost_per_token": 4e-08, + "output_cost_per_token": 5.72e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/llama3.1-nemotron-70b-instruct-fp8": { - "input_cost_per_token": 1.2e-07, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "inferenceapis/glm-5.3-flash": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048575, + "max_output_tokens": 1048575, "mode": "chat", - "output_cost_per_token": 3e-07, + "output_cost_per_token": 6.6e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/llama3.2-11b-vision-instruct": { - "input_cost_per_token": 1.5e-08, - "litellm_provider": "lambda_ai", + "inferenceapis/gpt-oss-120b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2.5e-08, + "output_cost_per_token": 8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, + "supports_native_streaming": true, + "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": false }, - "lambda_ai/llama3.2-3b-instruct": { - "input_cost_per_token": 1.5e-08, - "litellm_provider": "lambda_ai", + "inferenceapis/gpt-oss-20b": { + "input_cost_per_token": 4e-08, + "litellm_provider": "inferenceapis", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2.5e-08, + "output_cost_per_token": 1.9e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/llama3.3-70b-instruct-fp8": { - "input_cost_per_token": 1.2e-07, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "inferenceapis/kimi-k2.7-code": { + "cache_read_input_token_cost": 1.8e-07, + "input_cost_per_token": 8.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", - "output_cost_per_token": 3e-07, + "output_cost_per_token": 4.42e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/qwen25-coder-32b-instruct": { - "input_cost_per_token": 5e-08, - "litellm_provider": "lambda_ai", + "inferenceapis/llama-3.1-8b-instant": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 1e-07, + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/qwen3-32b-fp8": { - "input_cost_per_token": 5e-08, - "litellm_provider": "lambda_ai", + "inferenceapis/llama-3.3-70b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 1e-07, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_reasoning": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "low/1024-x-1024/gpt-image-1": { - "deprecation_date": "2026-10-23", - "input_cost_per_image": 0.011, - "input_cost_per_pixel": 1.0490417e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0, - "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "low/1024-x-1536/gpt-image-1": { - "deprecation_date": "2026-10-23", - "input_cost_per_image": 0.016, - "input_cost_per_pixel": 1.0172526e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0, - "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "low/1536-x-1024/gpt-image-1": { - "deprecation_date": "2026-10-23", - "input_cost_per_image": 0.016, - "input_cost_per_pixel": 1.0172526e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0, - "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "max-x-max/50-steps/stability.stable-diffusion-xl-v0": { - "litellm_provider": "bedrock", - "max_input_tokens": 77, - "max_tokens": 77, - "mode": "image_generation", - "output_cost_per_image": 0.036 - }, - "max-x-max/max-steps/stability.stable-diffusion-xl-v0": { - "litellm_provider": "bedrock", - "max_input_tokens": 77, - "max_tokens": 77, - "mode": "image_generation", - "output_cost_per_image": 0.072 - }, - "medium/1024-x-1024/gpt-image-1": { - "deprecation_date": "2026-10-23", - "input_cost_per_image": 0.042, - "input_cost_per_pixel": 4.0054321e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0, - "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "medium/1024-x-1536/gpt-image-1": { - "deprecation_date": "2026-10-23", - "input_cost_per_image": 0.063, - "input_cost_per_pixel": 4.0054321e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0, - "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "medium/1536-x-1024/gpt-image-1": { - "deprecation_date": "2026-10-23", - "input_cost_per_image": 0.063, - "input_cost_per_pixel": 4.0054321e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0, - "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "low/1024-x-1024/gpt-image-1-mini": { - "deprecation_date": "2026-12-01", - "input_cost_per_image": 0.005, - "litellm_provider": "openai", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "low/1024-x-1536/gpt-image-1-mini": { - "deprecation_date": "2026-12-01", - "input_cost_per_image": 0.006, - "litellm_provider": "openai", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "low/1536-x-1024/gpt-image-1-mini": { - "deprecation_date": "2026-12-01", - "input_cost_per_image": 0.006, - "litellm_provider": "openai", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "medium/1024-x-1024/gpt-image-1-mini": { - "deprecation_date": "2026-12-01", - "input_cost_per_image": 0.011, - "litellm_provider": "openai", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "medium/1024-x-1536/gpt-image-1-mini": { - "deprecation_date": "2026-12-01", - "input_cost_per_image": 0.015, - "litellm_provider": "openai", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "medium/1536-x-1024/gpt-image-1-mini": { - "deprecation_date": "2026-12-01", - "input_cost_per_image": 0.015, - "litellm_provider": "openai", - "mode": "image_generation", + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "medlm-large": { - "input_cost_per_character": 5e-06, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "max_tokens": 1024, - "mode": "chat", - "output_cost_per_character": 1.5e-05, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true - }, - "medlm-medium": { - "input_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_character": 1e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true - }, - "meta.llama2-13b-chat-v1": { - "input_cost_per_token": 7.5e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1e-06, - "source": "https://aws.amazon.com/bedrock/pricing/" - }, - "meta.llama2-70b-chat-v1": { - "input_cost_per_token": 1.95e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 2.56e-06, - "source": "https://aws.amazon.com/bedrock/pricing/" - }, - "meta.llama3-1-405b-instruct-v1:0": { - "input_cost_per_token": 2.4e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 2.4e-06, - "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "meta.llama3-1-70b-instruct-v1:0": { - "input_cost_per_token": 7.2e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 7.2e-07, - "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "meta.llama3-1-8b-instruct-v1:0": { - "input_cost_per_token": 2.2e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 2.2e-07, - "supports_function_calling": true, - "supports_tool_choice": false - }, - "meta.llama3-2-11b-instruct-v1:0": { - "input_cost_per_token": 1.6e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.6e-07, - "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", - "supports_function_calling": true, - "supports_tool_choice": false, - "supports_vision": true - }, - "meta.llama3-2-1b-instruct-v1:0": { - "input_cost_per_token": 1e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1e-07, - "supports_function_calling": true, - "supports_tool_choice": false - }, - "meta.llama3-2-3b-instruct-v1:0": { - "input_cost_per_token": 1.5e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-07, + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_tool_choice": false + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": false }, - "meta.llama3-2-90b-instruct-v1:0": { - "input_cost_per_token": 7.2e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "inferenceapis/llama-3.3-70b-instruct": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 7.2e-07, - "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_tool_choice": false, - "supports_vision": true + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": false }, - "meta.llama3-3-70b-instruct-v1:0": { - "input_cost_per_token": 7.2e-07, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "inferenceapis/llama-3.3-70b-versatile": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 7.2e-07, + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_tool_choice": false - }, - "meta.llama3-70b-instruct-v1:0": { - "input_cost_per_token": 2.65e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 3.5e-06 - }, - "meta.llama3-8b-instruct-v1:0": { - "input_cost_per_token": 3e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 6e-07 + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": false }, - "meta.llama4-maverick-17b-instruct-v1:0": { - "input_cost_per_token": 2.4e-07, - "input_cost_per_token_batches": 1.2e-07, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "inferenceapis/meta-llama/Llama-3.3-70B-Instruct": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 9.7e-07, - "output_cost_per_token_batches": 4.85e-07, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "code" + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" ], "supports_function_calling": true, - "supports_tool_choice": false + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": false }, - "meta.llama4-scout-17b-instruct-v1:0": { - "input_cost_per_token": 1.7e-07, - "input_cost_per_token_batches": 8.5e-08, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "inferenceapis/meta-llama/Llama-3.3-70B-Instruct-Turbo": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 6.6e-07, - "output_cost_per_token_batches": 3.3e-07, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "code" + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" ], "supports_function_calling": true, - "supports_tool_choice": false + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": false }, - "meta/muse-spark-1.1": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "meta", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, + "inferenceapis/minimax-m3": { + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 3.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 524288, + "max_output_tokens": 524288, "mode": "chat", - "output_cost_per_token": 4.25e-06, - "search_context_cost_per_query": { - "search_context_size_high": 0.0025, - "search_context_size_low": 0.0025, - "search_context_size_medium": 0.0025 - }, - "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", + "output_cost_per_token": 1.56e-06, + "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], - "supported_modalities": [ - "text", - "image", - "video" - ], - "supported_output_modalities": [ - "text" - ], "supports_function_calling": true, - "supports_minimal_reasoning_effort": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, + "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_xhigh_reasoning_effort": true + "supports_vision": false }, - "meta/muse-spark-1.2": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "meta", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, + "inferenceapis/MiniMaxAI/MiniMax-M3": { + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 3.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 524288, + "max_output_tokens": 524288, "mode": "chat", - "output_cost_per_token": 4.25e-06, - "search_context_cost_per_query": { - "search_context_size_high": 0.0025, - "search_context_size_low": 0.0025, - "search_context_size_medium": 0.0025 - }, - "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", + "output_cost_per_token": 1.56e-06, + "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], - "supported_modalities": [ - "text", - "image", - "video" - ], - "supported_output_modalities": [ - "text" - ], "supports_function_calling": true, - "supports_minimal_reasoning_effort": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, + "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_xhigh_reasoning_effort": true + "supports_vision": false }, - "meta/muse-spark-1.2-contributor": { - "cache_read_input_token_cost": 2e-09, - "input_cost_per_token": 1e-07, - "litellm_provider": "meta", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, + "inferenceapis/moonshotai/Kimi-K2.7-Code": { + "cache_read_input_token_cost": 1.8e-07, + "input_cost_per_token": 8.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", - "output_cost_per_token": 2e-07, - "search_context_cost_per_query": { - "search_context_size_high": 0.0025, - "search_context_size_low": 0.0025, - "search_context_size_medium": 0.0025 - }, - "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", + "output_cost_per_token": 4.42e-06, + "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], - "supported_modalities": [ - "text", - "image", - "video" - ], - "supported_output_modalities": [ - "text" - ], "supports_function_calling": true, - "supports_minimal_reasoning_effort": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, + "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_xhigh_reasoning_effort": true + "supports_vision": false }, - "meta/muse-spark-1.3": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "meta", - "max_input_tokens": 1048576, + "inferenceapis/openai/gpt-oss-120b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 4.25e-06, - "search_context_cost_per_query": { - "search_context_size_high": 0.0025, - "search_context_size_low": 0.0025, - "search_context_size_medium": 0.0025 - }, - "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", + "output_cost_per_token": 8e-07, + "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], - "supported_modalities": [ - "text", - "image", - "video" - ], - "supported_output_modalities": [ - "text" - ], "supports_function_calling": true, - "supports_minimal_reasoning_effort": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_native_streaming": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_xhigh_reasoning_effort": true + "supports_vision": false }, - "meta/muse-spark-1.3-contributor": { - "cache_read_input_token_cost": 2e-09, - "input_cost_per_token": 1e-07, - "litellm_provider": "meta", - "max_input_tokens": 1048576, + "inferenceapis/openai/gpt-oss-20b": { + "input_cost_per_token": 4e-08, + "litellm_provider": "inferenceapis", + "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2e-07, - "search_context_cost_per_query": { - "search_context_size_high": 0.0025, - "search_context_size_low": 0.0025, - "search_context_size_medium": 0.0025 - }, - "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", + "output_cost_per_token": 1.9e-07, + "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], - "supported_modalities": [ - "text", - "image", - "video" - ], - "supported_output_modalities": [ - "text" - ], "supports_function_calling": true, - "supports_minimal_reasoning_effort": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_native_streaming": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_xhigh_reasoning_effort": true - }, - "meta/muse-voice-transcribe-1.0": { - "input_cost_per_second": 0.00005, - "litellm_provider": "meta", - "mode": "audio_transcription", - "source": "https://dev.meta.ai/docs/speech-to-text", - "supported_endpoints": [ - "/v1/realtime" - ], - "supported_modalities": [ - "audio" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true + "supports_vision": false }, - "meta_llama/Llama-3.3-70B-Instruct": { - "litellm_provider": "meta_llama", - "max_input_tokens": 128000, - "max_output_tokens": 4028, - "max_tokens": 4028, + "inferenceapis/Qwen/Qwen3-VL-235B-A22B-Instruct": { + "input_cost_per_token": 2.6e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", - "source": "https://ai.developer.meta.com/docs/models", - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "text" + "output_cost_per_token": 1.15e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" ], "supports_function_calling": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": true }, - "meta_llama/Llama-3.3-8B-Instruct": { - "litellm_provider": "meta_llama", - "max_input_tokens": 128000, - "max_output_tokens": 4028, - "max_tokens": 4028, + "inferenceapis/Qwen/Qwen3.8-Flash": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", - "source": "https://ai.developer.meta.com/docs/models", - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "text" + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" ], "supports_function_calling": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { - "litellm_provider": "meta_llama", - "max_input_tokens": 1000000, - "max_output_tokens": 4028, - "max_tokens": 4028, + "inferenceapis/qwen3-vl": { + "input_cost_per_token": 2.6e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", - "source": "https://ai.developer.meta.com/docs/models", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" + "output_cost_per_token": 1.15e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" ], "supports_function_calling": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": true }, - "meta_llama/Llama-4-Scout-17B-16E-Instruct-FP8": { - "litellm_provider": "meta_llama", - "max_input_tokens": 10000000, - "max_output_tokens": 4028, - "max_tokens": 4028, + "inferenceapis/qwen3-vl-235b": { + "input_cost_per_token": 2.6e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", - "source": "https://ai.developer.meta.com/docs/models", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" + "output_cost_per_token": 1.15e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" ], "supports_function_calling": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": true }, - "minimax.minimax-m2": { - "input_cost_per_token": 3e-07, - "litellm_provider": "bedrock_converse", + "inferenceapis/qwen3.8-flash": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "inferenceapis", "max_input_tokens": 1000000, - "max_output_tokens": 8000, - "max_tokens": 8000, + "max_output_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", - "supports_audio_input": false, + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_system_messages": true, - "supports_native_structured_output": true, - "supports_response_schema": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, "supports_vision": false }, - "minimax.minimax-m2.1": { - "input_cost_per_token": 3e-07, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 196000, - "max_output_tokens": 8000, - "max_tokens": 8000, + "inferenceapis/zai-org/GLM-5.3": { + "cache_read_input_token_cost": 3.4e-07, + "input_cost_per_token": 1.82e-06, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048575, + "max_output_tokens": 1048575, "mode": "chat", - "output_cost_per_token": 1.2e-06, + "output_cost_per_token": 5.72e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_system_messages": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", - "supports_audio_input": false, - "supports_response_schema": true, "supports_vision": false }, - "minimax.minimax-m2.5": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 196000, - "max_output_tokens": 8000, - "max_tokens": 8000, + "inferenceapis/zai-org/GLM-5.3-Flash": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048575, + "max_output_tokens": 1048575, "mode": "chat", + "output_cost_per_token": 6.6e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_system_messages": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", - "supports_audio_input": false, - "supports_response_schema": true, "supports_vision": false }, - "minimax/speech-02-hd": { - "input_cost_per_character": 0.0001, - "litellm_provider": "minimax", - "mode": "audio_speech", - "supported_endpoints": [ - "/v1/audio/speech" - ] - }, - "minimax/speech-02-turbo": { - "input_cost_per_character": 6e-05, - "litellm_provider": "minimax", - "mode": "audio_speech", - "supported_endpoints": [ - "/v1/audio/speech" - ] - }, - "minimax/speech-2.6-hd": { - "input_cost_per_character": 0.0001, - "litellm_provider": "minimax", - "mode": "audio_speech", - "supported_endpoints": [ - "/v1/audio/speech" - ] - }, - "minimax/speech-2.6-turbo": { - "input_cost_per_character": 6e-05, - "litellm_provider": "minimax", - "mode": "audio_speech", - "supported_endpoints": [ - "/v1/audio/speech" - ] + "text-completion-inception/mercury-edit-2": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "text-completion-inception", + "max_input_tokens": 32000, + "max_output_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 7.5e-07 }, - "minimax/MiniMax-M2.1": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "cache_read_input_token_cost": 3e-08, - "cache_creation_input_token_cost": 3.75e-07, - "litellm_provider": "minimax", + "lambda_ai/deepseek-llama3.3-70b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", + "output_cost_per_token": 6e-07, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_prompt_caching": true, + "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, - "max_input_tokens": 1000000, - "max_output_tokens": 8192 + "supports_tool_choice": true }, - "minimax/MiniMax-M2.1-lightning": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 2.4e-06, - "cache_read_input_token_cost": 3e-08, - "cache_creation_input_token_cost": 3.75e-07, - "litellm_provider": "minimax", + "lambda_ai/deepseek-r1-0528": { + "input_cost_per_token": 2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", + "output_cost_per_token": 6e-07, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_prompt_caching": true, + "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, - "max_input_tokens": 1000000, - "max_output_tokens": 8192 + "supports_tool_choice": true }, - "minimax/MiniMax-M2.5": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "cache_read_input_token_cost": 3e-08, - "cache_creation_input_token_cost": 3.75e-07, - "litellm_provider": "minimax", + "lambda_ai/deepseek-r1-671b": { + "input_cost_per_token": 8e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", + "output_cost_per_token": 8e-07, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_prompt_caching": true, + "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, - "max_input_tokens": 1000000, - "max_output_tokens": 8192 + "supports_tool_choice": true }, - "minimax/MiniMax-M2.5-lightning": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 2.4e-06, - "cache_read_input_token_cost": 3e-08, - "cache_creation_input_token_cost": 3.75e-07, - "litellm_provider": "minimax", + "lambda_ai/deepseek-v3-0324": { + "input_cost_per_token": 2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", + "output_cost_per_token": 6e-07, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_prompt_caching": true, - "supports_reasoning": true, + "supports_parallel_function_calling": true, "supports_system_messages": true, - "max_input_tokens": 1000000, - "max_output_tokens": 8192 + "supports_tool_choice": true }, - "minimax/MiniMax-M2": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "cache_read_input_token_cost": 3e-08, - "cache_creation_input_token_cost": 3.75e-07, - "litellm_provider": "minimax", + "lambda_ai/hermes3-405b": { + "input_cost_per_token": 8e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", + "output_cost_per_token": 8e-07, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_prompt_caching": true, - "supports_reasoning": true, + "supports_parallel_function_calling": true, "supports_system_messages": true, - "max_input_tokens": 200000, - "max_output_tokens": 8192 + "supports_tool_choice": true }, - "minimax/MiniMax-M3": { - "input_cost_per_token": 3e-07, - "input_cost_per_token_above_512k_tokens": 6e-07, - "output_cost_per_token": 1.2e-06, - "output_cost_per_token_above_512k_tokens": 2.4e-06, - "cache_read_input_token_cost": 6e-08, - "cache_read_input_token_cost_above_512k_tokens": 1.2e-07, - "litellm_provider": "minimax", + "lambda_ai/hermes3-70b": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", + "output_cost_per_token": 3e-07, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_prompt_caching": true, - "supports_reasoning": true, + "supports_parallel_function_calling": true, "supports_system_messages": true, - "supports_vision": true, - "max_input_tokens": 1000000, - "max_output_tokens": 128000 + "supports_tool_choice": true }, - "mistral.devstral-2-123b": { - "input_cost_per_token": 4e-07, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 256000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "lambda_ai/hermes3-8b": { + "input_cost_per_token": 2.5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2e-06, + "output_cost_per_token": 4e-08, "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_system_messages": true, - "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", - "supports_audio_input": false, - "supports_response_schema": true, - "supports_vision": false + "supports_tool_choice": true }, - "mistral.magistral-small-2509": { - "input_cost_per_token": 5e-07, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 40000, - "max_tokens": 40000, + "lambda_ai/lfm-40b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", - "supports_audio_input": false, + "output_cost_per_token": 2e-07, "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, + "supports_parallel_function_calling": true, "supports_system_messages": true, - "supports_vision": true + "supports_tool_choice": true }, - "mistral.ministral-3-14b-instruct": { - "input_cost_per_token": 2e-07, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8000, - "max_tokens": 8000, + "lambda_ai/lfm-7b": { + "input_cost_per_token": 2.5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", - "supports_audio_input": false, + "output_cost_per_token": 4e-08, "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_system_messages": true, - "supports_native_structured_output": true, - "supports_response_schema": true, - "supports_vision": true + "supports_tool_choice": true }, - "mistral.ministral-3-3b-instruct": { - "input_cost_per_token": 1e-07, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8000, - "max_tokens": 8000, + "lambda_ai/llama-4-maverick-17b-128e-instruct-fp8": { + "input_cost_per_token": 5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", - "supports_audio_input": false, "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_system_messages": true, - "supports_native_structured_output": true, - "supports_response_schema": true, - "supports_vision": true + "supports_tool_choice": true }, - "mistral.ministral-3-8b-instruct": { - "input_cost_per_token": 1.5e-07, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8000, - "max_tokens": 8000, + "lambda_ai/llama-4-scout-17b-16e-instruct": { + "input_cost_per_token": 5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 16384, + "max_output_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.5e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", - "supports_audio_input": false, + "output_cost_per_token": 1e-07, "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_system_messages": true, - "supports_native_structured_output": true, - "supports_response_schema": true, - "supports_vision": true + "supports_tool_choice": true }, - "mistral.mistral-7b-instruct-v0:2": { - "input_cost_per_token": 1.5e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "lambda_ai/llama3.1-405b-instruct-fp8": { + "input_cost_per_token": 8e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token": 8e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "mistral.mistral-large-2402-v1:0": { - "input_cost_per_token": 4e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "lambda_ai/llama3.1-70b-instruct-fp8": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 1.2e-05, - "source": "https://aws.amazon.com/bedrock/pricing/", - "supports_function_calling": true + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "mistral.mistral-large-2407-v1:0": { - "input_cost_per_token": 2e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "lambda_ai/llama3.1-8b-instruct": { + "input_cost_per_token": 2.5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 6e-06, - "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", + "output_cost_per_token": 4e-08, "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "mistral.mistral-large-3-675b-instruct": { - "input_cost_per_token": 5e-07, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 256000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "lambda_ai/llama3.1-nemotron-70b-instruct-fp8": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", - "supports_audio_input": false, + "output_cost_per_token": 3e-07, "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_system_messages": true, - "supports_native_structured_output": true, - "supports_response_schema": true, - "supports_vision": true + "supports_tool_choice": true }, - "mistral.mistral-small-2402-v1:0": { - "input_cost_per_token": 1e-06, - "input_cost_per_token_batches": 5e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 3e-06, - "output_cost_per_token_batches": 1.5e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", - "supports_function_calling": true - }, - "mistral.mixtral-8x7b-instruct-v0:1": { - "input_cost_per_token": 4.5e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "lambda_ai/llama3.2-11b-vision-instruct": { + "input_cost_per_token": 1.5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 7e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", - "supports_tool_choice": true + "output_cost_per_token": 2.5e-08, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, - "mistral.voxtral-mini-3b-2507": { - "input_cost_per_token": 4e-08, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "lambda_ai/llama3.2-3b-instruct": { + "input_cost_per_token": 1.5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 4e-08, - "source": "https://aws.amazon.com/bedrock/pricing/", - "supports_audio_input": true, + "output_cost_per_token": 2.5e-08, + "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_system_messages": true, - "supports_native_structured_output": true + "supports_tool_choice": true }, - "mistral.voxtral-small-24b-2507": { - "input_cost_per_token": 1e-07, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "lambda_ai/llama3.3-70b-instruct-fp8": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", - "supports_audio_input": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_system_messages": true, - "supports_native_structured_output": true + "supports_tool_choice": true }, - "mistral/codestral-2508": { - "cache_read_input_token_cost": 3e-08, - "input_cost_per_token": 3e-07, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "lambda_ai/qwen25-coder-32b-instruct": { + "input_cost_per_token": 5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 9e-07, - "source": "https://docs.mistral.ai/models/model-cards/codestral-25-08", - "supports_assistant_prefill": true, + "output_cost_per_token": 1e-07, "supports_function_calling": true, - "supports_response_schema": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "mistral/codestral-latest": { - "cache_read_input_token_cost": 3e-08, - "input_cost_per_token": 3e-07, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "lambda_ai/qwen3-32b-fp8": { + "input_cost_per_token": 5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 9e-07, - "source": "https://docs.mistral.ai/models/model-cards/codestral-25-08", - "supports_assistant_prefill": true, + "output_cost_per_token": 1e-07, "supports_function_calling": true, - "supports_response_schema": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "mistral/codestral-mamba-latest": { - "cache_read_input_token_cost": 2.5e-08, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "mistral", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "low/1024-x-1024/gpt-image-1": { + "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", + "input_cost_per_image": 0.011, + "input_cost_per_pixel": 1.0490417e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "low/1024-x-1536/gpt-image-1": { + "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", + "input_cost_per_image": 0.016, + "input_cost_per_pixel": 1.0172526e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "low/1536-x-1024/gpt-image-1": { + "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", + "input_cost_per_image": 0.016, + "input_cost_per_pixel": 1.0172526e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "max-x-max/50-steps/stability.stable-diffusion-xl-v0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.036 + }, + "max-x-max/max-steps/stability.stable-diffusion-xl-v0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.072 + }, + "medium/1024-x-1024/gpt-image-1": { + "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", + "input_cost_per_image": 0.042, + "input_cost_per_pixel": 4.0054321e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "medium/1024-x-1536/gpt-image-1": { + "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", + "input_cost_per_image": 0.063, + "input_cost_per_pixel": 4.0054321e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "medium/1536-x-1024/gpt-image-1": { + "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", + "input_cost_per_image": 0.063, + "input_cost_per_pixel": 4.0054321e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "low/1024-x-1024/gpt-image-1-mini": { + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", + "input_cost_per_image": 0.005, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "low/1024-x-1536/gpt-image-1-mini": { + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", + "input_cost_per_image": 0.006, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "low/1536-x-1024/gpt-image-1-mini": { + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", + "input_cost_per_image": 0.006, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "medium/1024-x-1024/gpt-image-1-mini": { + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", + "input_cost_per_image": 0.011, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "medium/1024-x-1536/gpt-image-1-mini": { + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", + "input_cost_per_image": 0.015, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "medium/1536-x-1024/gpt-image-1-mini": { + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", + "input_cost_per_image": 0.015, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "medlm-large": { + "input_cost_per_character": 5e-06, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 8192, + "max_output_tokens": 1024, "mode": "chat", - "output_cost_per_token": 2.5e-07, - "source": "https://mistral.ai/technology/", - "supports_assistant_prefill": true, + "output_cost_per_character": 1.5e-05, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_tool_choice": true }, - "mistral/devstral-small-latest": { - "cache_read_input_token_cost": 1e-08, - "input_cost_per_token": 1e-07, - "litellm_provider": "mistral", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "medlm-medium": { + "input_cost_per_character": 5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 32768, + "max_output_tokens": 8192, "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://docs.mistral.ai/models/devstral-small-2-25-12", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, + "output_cost_per_character": 1e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_tool_choice": true }, - "mistral/devstral-latest": { - "cache_read_input_token_cost": 4e-08, - "input_cost_per_token": 4e-07, - "litellm_provider": "mistral", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "meta.llama2-13b-chat-v1": { + "input_cost_per_token": 7.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 4096, + "max_output_tokens": 4096, "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://mistral.ai/news/devstral-2-vibe-cli", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "output_cost_per_token": 1e-06, + "source": "https://aws.amazon.com/bedrock/pricing/" }, - "mistral/devstral-medium-latest": { - "cache_read_input_token_cost": 4e-08, - "input_cost_per_token": 4e-07, - "litellm_provider": "mistral", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "meta.llama2-70b-chat-v1": { + "input_cost_per_token": 1.95e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 4096, + "max_output_tokens": 4096, "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://mistral.ai/news/devstral-2-vibe-cli", - "supports_assistant_prefill": true, + "output_cost_per_token": 2.56e-06, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "meta.llama3-1-405b-instruct-v1:0": { + "deprecation_date": "2026-07-07", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "input_cost_per_token": 2.4e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": false }, - "mistral/ministral-14b-2512": { - "input_cost_per_token": 2e-07, - "litellm_provider": "mistral", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "meta.llama3-1-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "input_cost_per_token": 7.2e-07, + "input_cost_per_token_batches": 3.6e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://docs.mistral.ai/models/ministral-3-14b-25-12", - "supports_assistant_prefill": true, + "output_cost_per_token": 7.2e-07, + "output_cost_per_token_batches": 3.6e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 2e-08 + "supports_tool_choice": false }, - "mistral/ministral-14b-latest": { - "input_cost_per_token": 2e-07, - "litellm_provider": "mistral", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "meta.llama3-1-8b-instruct-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "input_cost_per_token": 2.2e-07, + "input_cost_per_token_batches": 1.1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://docs.mistral.ai/models/ministral-3-14b-25-12", - "supports_assistant_prefill": true, + "output_cost_per_token": 2.2e-07, + "output_cost_per_token_batches": 1.1e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 2e-08 + "supports_tool_choice": false }, - "mistral/ministral-3b-2512": { - "input_cost_per_token": 1e-07, - "litellm_provider": "mistral", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "meta.llama3-2-11b-instruct-v1:0": { + "deprecation_date": "2026-07-07", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "input_cost_per_token": 1.6e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, "mode": "chat", - "output_cost_per_token": 1e-07, - "source": "https://docs.mistral.ai/models/ministral-3-3b-25-12", - "supports_assistant_prefill": true, + "output_cost_per_token": 1.6e-07, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 1e-08 + "supports_tool_choice": false, + "supports_vision": true }, - "mistral/ministral-3b-latest": { + "meta.llama3-2-1b-instruct-v1:0": { + "deprecation_date": "2026-07-07", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.md", "input_cost_per_token": 1e-07, - "litellm_provider": "mistral", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-07, - "source": "https://docs.mistral.ai/models/ministral-3-3b-25-12", - "supports_assistant_prefill": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.md", "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 1e-08 + "supports_tool_choice": false }, - "mistral/mistral-embed-2312": { - "input_cost_per_token": 1e-07, - "litellm_provider": "mistral", - "max_input_tokens": 8192, - "max_tokens": 8192, - "mode": "embedding", - "source": "https://docs.mistral.ai/models/mistral-embed-23-12" + "meta.llama3-2-3b-instruct-v1:0": { + "deprecation_date": "2026-07-07", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.md", + "input_cost_per_token": 1.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.md", + "supports_function_calling": true, + "supports_tool_choice": false }, - "mistral/mistral-medium-3": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 1.5e-06, - "litellm_provider": "mistral", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "meta.llama3-2-90b-instruct-v1:0": { + "deprecation_date": "2026-07-07", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "input_cost_per_token": 7.2e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, "mode": "chat", - "output_cost_per_token": 7.5e-06, - "reasoning_effort_levels": [ - "none", - "high" - ], - "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", - "supports_assistant_prefill": true, + "output_cost_per_token": 7.2e-07, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, + "supports_tool_choice": false, "supports_vision": true }, - "mistral/voxtral-mini-transcribe-realtime-latest": { - "input_cost_per_second": 0.0001, - "litellm_provider": "mistral", - "mode": "audio_transcription", - "source": "https://docs.mistral.ai/models/model-cards/voxtral-mini-transcribe-realtime-26-02", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], + "meta.llama3-3-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "input_cost_per_token": 7.2e-07, + "input_cost_per_token_batches": 3.6e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "output_cost_per_token_batches": 3.6e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta.llama3-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md", + "input_cost_per_token": 2.65e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 3.5e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" + }, + "meta.llama3-8b-instruct-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md", + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" + }, + "meta.llama4-maverick-17b-instruct-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-maverick-17b-instruct.md", + "input_cost_per_token": 2.4e-07, + "input_cost_per_token_batches": 1.2e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 9.7e-07, + "output_cost_per_token_batches": 4.85e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-maverick-17b-instruct.md", "supported_modalities": [ - "audio" + "text", + "image" ], "supported_output_modalities": [ - "text" + "text", + "code" ], - "supports_audio_input": true + "supports_function_calling": true, + "supports_tool_choice": false }, - "mistral/voxtral-mini-tts-latest": { - "input_cost_per_character": 1.6e-05, - "litellm_provider": "mistral", - "mode": "audio_speech", - "source": "https://docs.mistral.ai/models/model-cards/voxtral-tts-26-03", - "supported_endpoints": [ - "/v1/audio/speech" - ], + "meta.llama4-scout-17b-instruct-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-scout-17b-instruct.md", + "input_cost_per_token": 1.7e-07, + "input_cost_per_token_batches": 8.5e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 10000000, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "output_cost_per_token_batches": 3.3e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-scout-17b-instruct.md", "supported_modalities": [ - "text" + "text", + "image" ], "supported_output_modalities": [ - "audio" + "text", + "code" ], - "supports_audio_output": true + "supports_function_calling": true, + "supports_tool_choice": false }, - "mistral/voxtral-small-2507": { - "cache_read_input_token_cost": 1e-08, - "input_cost_per_token": 1e-07, - "litellm_provider": "mistral", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 4e-07, - "source": "https://docs.mistral.ai/models/voxtral-small-25-07", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/voxtral-small-latest": { - "cache_read_input_token_cost": 1e-08, - "input_cost_per_token": 1e-07, - "litellm_provider": "mistral", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 4e-07, - "source": "https://docs.mistral.ai/models/voxtral-small-25-07", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/zai-glm-5-2": { - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 1.4e-06, - "litellm_provider": "mistral", + "meta/muse-ember-1.0": { + "cache_read_input_token_cost": 4e-09, + "cache_read_input_token_cost_above_200k_tokens": 1.2e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_200k_tokens": 3e-07, + "litellm_provider": "meta", + "max_input_tokens": 1048576, + "max_output_tokens": 524288, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_above_200k_tokens": 1.5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.0025, + "search_context_size_low": 0.0025, + "search_context_size_medium": 0.0025 + }, + "source": "https://dev.meta.ai/docs/pricing-rate-limits", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "meta/muse-spark-1.1": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "meta", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 4.4e-06, - "reasoning_effort_levels": [ - "none", - "minimal", - "low", - "medium", - "high", - "xhigh", - "max" + "output_cost_per_token": 4.25e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.0025, + "search_context_size_low": 0.0025, + "search_context_size_medium": 0.0025 + }, + "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text" ], - "source": "https://docs.mistral.ai/models/zai-glm-5-2", - "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_minimal_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true }, - "mistral/zai-glm-5-3": { - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 1.4e-06, - "litellm_provider": "mistral", + "meta/muse-spark-1.2": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "meta", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 4.4e-06, - "reasoning_effort_levels": [ - "low", - "high", - "max" + "output_cost_per_token": 4.25e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.0025, + "search_context_size_low": 0.0025, + "search_context_size_medium": 0.0025 + }, + "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text" ], - "source": "https://docs.mistral.ai/models/zai-glm-5-3", - "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_minimal_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true }, - "mistral/zai-glm-5": { - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 1.4e-06, - "litellm_provider": "mistral", + "meta/muse-spark-1.2-contributor": { + "cache_read_input_token_cost": 2e-09, + "input_cost_per_token": 1e-07, + "litellm_provider": "meta", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 4.4e-06, - "reasoning_effort_levels": [ - "low", - "high", - "max" + "output_cost_per_token": 2e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.0025, + "search_context_size_low": 0.0025, + "search_context_size_medium": 0.0025 + }, + "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text" ], - "source": "https://docs.mistral.ai/models/zai-glm-5-3", - "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_minimal_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true }, - "mistral/zai-glm-latest": { - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 1.4e-06, - "litellm_provider": "mistral", + "meta/muse-spark-1.3": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "meta", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 4.4e-06, - "reasoning_effort_levels": [ - "low", - "high", - "max" + "output_cost_per_token": 4.25e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.0025, + "search_context_size_low": 0.0025, + "search_context_size_medium": 0.0025 + }, + "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text" ], - "source": "https://docs.mistral.ai/models/zai-glm-5-3", - "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_minimal_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true }, - "mistral/glm-5-2": { - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 1.4e-06, - "litellm_provider": "mistral", + "meta/muse-spark-1.3-contributor": { + "cache_read_input_token_cost": 2e-09, + "input_cost_per_token": 1e-07, + "litellm_provider": "meta", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 4.4e-06, - "reasoning_effort_levels": [ - "none", - "minimal", - "low", - "medium", - "high", - "xhigh", - "max" + "output_cost_per_token": 2e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.0025, + "search_context_size_low": 0.0025, + "search_context_size_medium": 0.0025 + }, + "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text" ], - "source": "https://docs.mistral.ai/models/zai-glm-5-2", - "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_minimal_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true }, - "mistral/mistral-ocr-latest": { - "litellm_provider": "mistral", - "ocr_cost_per_page": 0.004, - "ocr_cost_per_page_batches": 0.002, - "annotation_cost_per_page": 0.005, - "annotation_cost_per_page_batches": 0.0025, - "mode": "ocr", + "meta/muse-voice-transcribe-1.0": { + "input_cost_per_second": 0.00005, + "litellm_provider": "meta", + "mode": "audio_transcription", + "source": "https://dev.meta.ai/docs/speech-to-text", "supported_endpoints": [ - "/v1/ocr", - "/v1/batch" + "/v1/realtime" ], - "source": "https://mistral.ai/pricing#api-pricing" - }, - "mistral/mistral-ocr-4-0": { - "litellm_provider": "mistral", - "ocr_cost_per_page": 0.004, - "ocr_cost_per_page_batches": 0.002, - "annotation_cost_per_page": 0.005, - "annotation_cost_per_page_batches": 0.0025, - "mode": "ocr", - "supported_endpoints": [ - "/v1/ocr", - "/v1/batch" + "supported_modalities": [ + "audio" ], - "source": "https://mistral.ai/pricing#api-pricing" - }, - "mistral/mistral-ocr-4-1": { - "annotation_cost_per_page": 0.005, - "annotation_cost_per_page_batches": 0.0025, - "litellm_provider": "mistral", - "mode": "ocr", - "ocr_cost_per_page": 0.004, - "ocr_cost_per_page_batches": 0.002, - "source": "https://docs.mistral.ai/models/model-cards/ocr-4-1", - "supported_endpoints": [ - "/v1/ocr", - "/v1/batch" - ] - }, - "mistral/mistral-ocr-2512": { - "litellm_provider": "mistral", - "ocr_cost_per_page": 0.002, - "ocr_cost_per_page_batches": 0.001, - "annotation_cost_per_page": 0.003, - "annotation_cost_per_page_batches": 0.0015, - "mode": "ocr", - "supported_endpoints": [ - "/v1/ocr", - "/v1/batch" + "supported_output_modalities": [ + "text" ], - "source": "https://mistral.ai/pricing#api-pricing" + "supports_audio_input": true }, - "mistral/magistral-medium-latest": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 1.5e-06, - "litellm_provider": "mistral", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "meta/muse-wonder-1.0": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 4e-06, + "litellm_provider": "meta", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 7.5e-06, - "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", - "supports_assistant_prefill": true, + "output_cost_per_token": 2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.0025, + "search_context_size_low": 0.0025, + "search_context_size_medium": 0.0025 + }, + "source": "https://dev.meta.ai/docs/pricing-rate-limits", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true }, - "mistral/magistral-small-latest": { - "cache_read_input_token_cost": 1.5e-08, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "mistral", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "meta_llama/Llama-3.3-70B-Instruct": { + "litellm_provider": "meta_llama", + "max_input_tokens": 128000, + "max_output_tokens": 4028, "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03", - "supports_assistant_prefill": true, + "source": "https://ai.developer.meta.com/docs/models", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "mistral/mistral-embed": { - "input_cost_per_token": 1e-07, - "litellm_provider": "mistral", - "max_input_tokens": 8192, - "max_tokens": 8192, - "mode": "embedding" - }, - "mistral/codestral-embed": { - "cache_read_input_token_cost": 1.5e-08, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "mistral", - "max_input_tokens": 8192, - "max_tokens": 8192, - "mode": "embedding" + "supports_tool_choice": true }, - "mistral/codestral-embed-2505": { - "cache_read_input_token_cost": 1.5e-08, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "mistral", - "max_input_tokens": 8192, - "max_tokens": 8192, - "mode": "embedding" + "meta_llama/Llama-3.3-8B-Instruct": { + "litellm_provider": "meta_llama", + "max_input_tokens": 128000, + "max_output_tokens": 4028, + "mode": "chat", + "source": "https://ai.developer.meta.com/docs/models", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_tool_choice": true }, - "mistral/mistral-large-latest": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 5e-07, - "litellm_provider": "mistral", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { + "litellm_provider": "meta_llama", + "max_input_tokens": 1000000, + "max_output_tokens": 4028, "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", - "supports_assistant_prefill": true, + "source": "https://ai.developer.meta.com/docs/models", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_tool_choice": true }, - "mistral/mistral-large-3": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 5e-07, - "litellm_provider": "mistral", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "meta_llama/Llama-4-Scout-17B-16E-Instruct-FP8": { + "litellm_provider": "meta_llama", + "max_input_tokens": 10000000, + "max_output_tokens": 4028, "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", - "supports_assistant_prefill": true, + "source": "https://ai.developer.meta.com/docs/models", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_tool_choice": true }, - "mistral/mistral-large-2512": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 5e-07, - "litellm_provider": "mistral", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "minimax.minimax-m2": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.2e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 8000, "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", - "supports_assistant_prefill": true, + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_batches": 6e-07, + "output_cost_per_token_flex": 6e-07, + "output_cost_per_token_priority": 2.1e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supports_audio_input": false, "supports_function_calling": true, + "supports_system_messages": true, + "supports_native_structured_output": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_vision": false }, - "mistral/mistral-medium": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 1.5e-06, - "litellm_provider": "mistral", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.25e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 196000, + "max_output_tokens": 8000, "mode": "chat", - "output_cost_per_token": 7.5e-06, - "reasoning_effort_levels": [ - "none", - "high" - ], - "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", - "supports_assistant_prefill": true, + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_batches": 6e-07, + "output_cost_per_token_flex": 6e-07, + "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false }, - "mistral/mistral-medium-2604": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 1.5e-06, - "litellm_provider": "mistral", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "minimax.minimax-m2.5": { + "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.25e-07, + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_flex": 6e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 196000, + "max_output_tokens": 8000, "mode": "chat", - "output_cost_per_token": 7.5e-06, - "reasoning_effort_levels": [ - "none", - "high" - ], - "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", - "supports_assistant_prefill": true, + "output_cost_per_token_batches": 6e-07, + "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, - "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supports_audio_input": false, "supports_response_schema": true, + "supports_vision": false + }, + "minimax/speech-02-hd": { + "input_cost_per_character": 0.0001, + "litellm_provider": "minimax", + "mode": "audio_speech", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "minimax/speech-02-turbo": { + "input_cost_per_character": 6e-05, + "litellm_provider": "minimax", + "mode": "audio_speech", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "minimax/speech-2.6-hd": { + "input_cost_per_character": 0.0001, + "litellm_provider": "minimax", + "mode": "audio_speech", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "minimax/speech-2.6-turbo": { + "input_cost_per_character": 6e-05, + "litellm_provider": "minimax", + "mode": "audio_speech", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "minimax/MiniMax-M2.1": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 3e-08, + "cache_creation_input_token_cost": 3.75e-07, + "litellm_provider": "minimax", + "mode": "chat", + "supports_function_calling": true, "supports_tool_choice": true, - "supports_vision": true + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "max_input_tokens": 1000000, + "max_output_tokens": 8192 }, - "mistral/mistral-medium-latest": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 1.5e-06, - "litellm_provider": "mistral", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "minimax/MiniMax-M2.1-lightning": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 2.4e-06, + "cache_read_input_token_cost": 3e-08, + "cache_creation_input_token_cost": 3.75e-07, + "litellm_provider": "minimax", "mode": "chat", - "output_cost_per_token": 7.5e-06, - "reasoning_effort_levels": [ - "none", - "high" - ], - "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", - "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, + "supports_system_messages": true, + "max_input_tokens": 1000000, + "max_output_tokens": 8192 + }, + "minimax/MiniMax-M2.5": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 3e-08, + "cache_creation_input_token_cost": 3.75e-07, + "litellm_provider": "minimax", + "mode": "chat", + "supports_function_calling": true, "supports_tool_choice": true, - "supports_vision": true + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "max_input_tokens": 1000000, + "max_output_tokens": 8192 }, - "mistral/mistral-medium-3-5": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 1.5e-06, - "litellm_provider": "mistral", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "minimax/MiniMax-M2.5-lightning": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 2.4e-06, + "cache_read_input_token_cost": 3e-08, + "cache_creation_input_token_cost": 3.75e-07, + "litellm_provider": "minimax", "mode": "chat", - "output_cost_per_token": 7.5e-06, - "reasoning_effort_levels": [ - "none", - "high" - ], - "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", - "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, + "supports_system_messages": true, + "max_input_tokens": 1000000, + "max_output_tokens": 8192 + }, + "minimax/MiniMax-M2": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 3e-08, + "cache_creation_input_token_cost": 3.75e-07, + "litellm_provider": "minimax", + "mode": "chat", + "supports_function_calling": true, "supports_tool_choice": true, - "supports_vision": true + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "max_input_tokens": 200000, + "max_output_tokens": 8192 }, - "mistral/mistral-small": { - "cache_read_input_token_cost": 1e-08, - "input_cost_per_token": 1e-07, - "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "minimax/MiniMax-M3": { + "input_cost_per_token": 3e-07, + "input_cost_per_token_above_512k_tokens": 6e-07, + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_above_512k_tokens": 2.4e-06, + "cache_read_input_token_cost": 6e-08, + "cache_read_input_token_cost_above_512k_tokens": 1.2e-07, + "litellm_provider": "minimax", "mode": "chat", - "output_cost_per_token": 3e-07, - "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_vision": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000 }, - "mistral/mistral-small-latest": { - "cache_read_input_token_cost": 1.5e-08, + "minimax/MiniMax-M3.1-Flash": { "input_cost_per_token": 1.5e-07, - "litellm_provider": "mistral", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", "output_cost_per_token": 6e-07, - "reasoning_effort_levels": [ - "none", - "high" - ], - "source": "https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03", - "supports_assistant_prefill": true, + "cache_read_input_token_cost": 1.5e-08, + "litellm_provider": "minimax", + "mode": "chat", + "source": "https://platform.minimax.io/docs/guides/pricing-paygo", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "reasoning_effort_levels": [ + "low", + "medium", + "high", + "xhigh", + "max" + ], + "supports_vision": true, + "max_input_tokens": 1000000 }, - "mistral/ministral-3-3b-2512": { - "cache_read_input_token_cost": 1e-08, - "input_cost_per_token": 1e-07, - "litellm_provider": "mistral", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "minimax/minimax-latest": { + "alias_of": "minimax/MiniMax-M3" + }, + "minimax/MiniMax-H3": { + "litellm_provider": "minimax", + "mode": "video_generation", + "source": "https://platform.minimax.io/docs/guides/pricing-paygo", + "output_cost_per_second": 0.08, + "output_cost_per_second_768p": 0.08, + "output_cost_per_second_2k": 0.13, + "input_cost_per_image": 0.04, + "provider_specific_entry": { + "minimax_free_input_images": 5 + }, + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "metadata": { + "comment": "V2 async task API. Pay-as-you-go list price $0.08/s at 768P and $0.13/s at 2K, plus $0.04 per input image beyond the first 5. Audio input is free. Reference video input is rejected, since MiniMax bills its duration only after the create call." + } + }, + "minimax/MiniMax-H3-Max": { + "litellm_provider": "minimax", + "mode": "video_generation", + "source": "https://platform.minimax.io/docs/guides/pricing-paygo", + "output_cost_per_second": 0.08, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_768p": 0.08, + "input_cost_per_image": 0.074, + "provider_specific_entry": { + "minimax_free_input_images": 2 + }, + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "metadata": { + "comment": "V2 async task API, fast tier. Pay-as-you-go list price $0.05/s at 480P and $0.08/s at 768P; no 2K. Plus $0.074 per input image beyond the first 2. Audio input is free. Reference video input is rejected, since MiniMax bills its duration only after the create call." + } + }, + "mistral.devstral-2-123b": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "input_cost_per_token": 4e-07, + "input_cost_per_token_batches": 2e-07, + "input_cost_per_token_flex": 2e-07, + "input_cost_per_token_priority": 7e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 256000, + "max_output_tokens": 32000, "mode": "chat", - "output_cost_per_token": 1e-07, - "source": "https://mistral.ai/pricing", - "supports_assistant_prefill": true, + "output_cost_per_token": 2e-06, + "output_cost_per_token_batches": 1e-06, + "output_cost_per_token_flex": 1e-06, + "output_cost_per_token_priority": 3.5e-06, "supports_function_calling": true, - "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false }, - "mistral/ministral-3-8b-2512": { - "cache_read_input_token_cost": 1.5e-08, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "mistral", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "mistral.magistral-small-2509": { + "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "input_cost_per_token_flex": 2.5e-07, + "input_cost_per_token_priority": 8.8e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 40000, "mode": "chat", - "output_cost_per_token": 1.5e-07, - "source": "https://mistral.ai/pricing", - "supports_assistant_prefill": true, + "output_cost_per_token": 1.5e-06, + "output_cost_per_token_batches": 7.5e-07, + "output_cost_per_token_flex": 7.5e-07, + "output_cost_per_token_priority": 2.63e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supports_audio_input": false, "supports_function_calling": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, + "supports_system_messages": true, "supports_vision": true }, - "mistral/ministral-3-14b-2512": { - "cache_read_input_token_cost": 2e-08, + "mistral.ministral-3-14b-instruct": { "input_cost_per_token": 2e-07, - "litellm_provider": "mistral", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "input_cost_per_token_batches": 1e-07, + "input_cost_per_token_flex": 1e-07, + "input_cost_per_token_priority": 3.5e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 2e-07, - "source": "https://mistral.ai/pricing", - "supports_assistant_prefill": true, + "output_cost_per_token_batches": 1e-07, + "output_cost_per_token_flex": 1e-07, + "output_cost_per_token_priority": 3.5e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supports_audio_input": false, "supports_function_calling": true, + "supports_system_messages": true, + "supports_native_structured_output": true, "supports_response_schema": true, - "supports_tool_choice": true, "supports_vision": true }, - "mistral/ministral-8b-2512": { - "cache_read_input_token_cost": 1.5e-08, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "mistral", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "mistral.ministral-3-3b-instruct": { + "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "input_cost_per_token_flex": 5e-08, + "input_cost_per_token_priority": 1.7e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 8000, "mode": "chat", - "output_cost_per_token": 1.5e-07, - "source": "https://mistral.ai/pricing", - "supports_assistant_prefill": true, + "output_cost_per_token": 1e-07, + "output_cost_per_token_batches": 5e-08, + "output_cost_per_token_flex": 5e-08, + "output_cost_per_token_priority": 1.7e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supports_audio_input": false, "supports_function_calling": true, + "supports_system_messages": true, + "supports_native_structured_output": true, "supports_response_schema": true, - "supports_tool_choice": true, "supports_vision": true }, - "mistral/ministral-8b-latest": { - "cache_read_input_token_cost": 1.5e-08, + "mistral.ministral-3-8b-instruct": { "input_cost_per_token": 1.5e-07, - "litellm_provider": "mistral", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "input_cost_per_token_batches": 7e-08, + "input_cost_per_token_flex": 7e-08, + "input_cost_per_token_priority": 2.6e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.5e-07, - "source": "https://mistral.ai/pricing", - "supports_assistant_prefill": true, + "output_cost_per_token_batches": 7e-08, + "output_cost_per_token_flex": 7e-08, + "output_cost_per_token_priority": 2.6e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supports_audio_input": false, "supports_function_calling": true, + "supports_system_messages": true, + "supports_native_structured_output": true, "supports_response_schema": true, - "supports_tool_choice": true, "supports_vision": true }, - "mistral/mistral-tiny": { - "cache_read_input_token_cost": 2.5e-08, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "mistral", + "mistral.mistral-7b-instruct-v0:2": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", + "input_cost_per_token": 1.5e-07, + "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, "mode": "chat", - "output_cost_per_token": 2.5e-07, - "supports_assistant_prefill": true, - "supports_response_schema": true, + "output_cost_per_token": 2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", "supports_tool_choice": true }, - "mistral/open-mistral-nemo": { - "cache_read_input_token_cost": 3e-08, - "input_cost_per_token": 3e-07, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "mistral.mistral-large-2402-v1:0": { + "input_cost_per_token": 4e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 4096, "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://mistral.ai/technology/", - "supports_assistant_prefill": true, - "supports_response_schema": true, - "supports_tool_choice": true + "output_cost_per_token": 1.2e-05, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md", + "supports_function_calling": true }, - "mistral/pixtral-large-latest": { - "cache_read_input_token_cost": 2e-07, + "mistral.mistral-large-2407-v1:0": { "input_cost_per_token": 2e-06, - "litellm_provider": "mistral", + "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 6e-06, - "supports_assistant_prefill": true, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_tool_choice": true }, - "moonshot.kimi-k2-thinking": { - "input_cost_per_token": 6e-07, + "mistral.mistral-large-3-675b-instruct": { + "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "input_cost_per_token_flex": 2.5e-07, + "input_cost_per_token_priority": 8.8e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, - "max_output_tokens": 16000, - "max_tokens": 16000, + "max_output_tokens": 32000, "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token": 1.5e-06, + "output_cost_per_token_batches": 7.5e-07, + "output_cost_per_token_flex": 7.5e-07, + "output_cost_per_token_priority": 2.63e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, - "supports_reasoning": true, "supports_system_messages": true, "supports_native_structured_output": true, "supports_response_schema": true, - "supports_vision": false + "supports_vision": true }, - "moonshotai.kimi-k2.5": { - "input_cost_per_token": 6e-07, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 256000, - "max_output_tokens": 16000, - "max_tokens": 16000, + "mistral.mistral-small-2402-v1:0": { + "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-06, - "supports_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "source": "https://aws.amazon.com/bedrock/pricing/", - "supports_audio_input": false, - "supports_response_schema": true + "output_cost_per_token_batches": 1.5e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-small.md", + "supports_function_calling": true }, - "moonshot/kimi-k2.7-code": { - "cache_read_input_token_cost": 1.9e-07, - "input_cost_per_token": 9.5e-07, - "litellm_provider": "moonshot", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "mistral.mixtral-8x7b-instruct-v0:1": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", + "input_cost_per_token": 4.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 4096, "mode": "chat", - "output_cost_per_token": 4e-06, - "source": "https://platform.kimi.ai/docs/pricing/chat-k27-code", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true + "output_cost_per_token": 7e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", + "supports_tool_choice": true }, - "moonshot/kimi-k2.5": { - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 6e-07, - "litellm_provider": "moonshot", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "mistral.voxtral-mini-3b-2507": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "input_cost_per_token": 4e-08, + "input_cost_per_token_batches": 2e-08, + "input_cost_per_token_flex": 2e-08, + "input_cost_per_token_priority": 7e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 32768, + "max_output_tokens": 8192, "mode": "chat", - "output_cost_per_token": 3e-06, - "source": "https://platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true + "output_cost_per_token": 4e-08, + "output_cost_per_token_batches": 2e-08, + "output_cost_per_token_flex": 2e-08, + "output_cost_per_token_priority": 7e-08, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supports_audio_input": true, + "supports_system_messages": true, + "supports_native_structured_output": true }, - "moonshot/kimi-k2.6": { - "cache_read_input_token_cost": 1.6e-07, - "input_cost_per_token": 9.5e-07, - "litellm_provider": "moonshot", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "mistral.voxtral-small-24b-2507": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "input_cost_per_token_flex": 5e-08, + "input_cost_per_token_priority": 1.7e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 32768, + "max_output_tokens": 8192, "mode": "chat", - "output_cost_per_token": 4e-06, - "source": "https://platform.kimi.ai/docs/pricing/chat-k26", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true + "output_cost_per_token": 3e-07, + "output_cost_per_token_batches": 1.5e-07, + "output_cost_per_token_flex": 1.5e-07, + "output_cost_per_token_priority": 5.2e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supports_audio_input": true, + "supports_system_messages": true, + "supports_native_structured_output": true }, - "moonshot/kimi-k3": { - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "litellm_provider": "moonshot", - "max_input_tokens": 1048576, - "max_output_tokens": 1048576, - "max_tokens": 1048576, + "bedrock/ap-southeast-2/mistral.voxtral-mini-3b-2507": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "input_cost_per_token": 4.12e-08, + "input_cost_per_token_batches": 2.06e-08, + "input_cost_per_token_flex": 2.06e-08, + "input_cost_per_token_priority": 7.21e-08, + "litellm_provider": "bedrock", + "max_input_tokens": 32768, + "max_output_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.5e-05, - "reasoning_effort_levels": [ - "low", - "high", - "max" - ], - "source": "https://platform.kimi.ai/docs/pricing/chat-k3", + "output_cost_per_token": 4.12e-08, + "output_cost_per_token_batches": 2.06e-08, + "output_cost_per_token_flex": 2.06e-08, + "output_cost_per_token_priority": 7.21e-08, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/ap-southeast-2/index.json", + "supports_audio_input": true, + "supports_system_messages": true, + "supports_native_structured_output": true + }, + "bedrock/ap-southeast-2/mistral.voxtral-small-24b-2507": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "input_cost_per_token": 1.03e-07, + "input_cost_per_token_batches": 5.15e-08, + "input_cost_per_token_flex": 5.15e-08, + "input_cost_per_token_priority": 1.8025e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 3.09e-07, + "output_cost_per_token_batches": 1.545e-07, + "output_cost_per_token_flex": 1.545e-07, + "output_cost_per_token_priority": 5.4075e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/ap-southeast-2/index.json", + "supports_audio_input": true, + "supports_system_messages": true, + "supports_native_structured_output": true + }, + "bedrock/ap-northeast-1/mistral.voxtral-mini-3b-2507": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "input_cost_per_token": 5e-08, + "input_cost_per_token_batches": 3e-08, + "input_cost_per_token_flex": 3e-08, + "input_cost_per_token_priority": 9e-08, + "litellm_provider": "bedrock", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5e-08, + "output_cost_per_token_batches": 3e-08, + "output_cost_per_token_flex": 3e-08, + "output_cost_per_token_priority": 9e-08, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/ap-northeast-1/index.json", + "supports_audio_input": true, + "supports_system_messages": true, + "supports_native_structured_output": true + }, + "bedrock/ap-northeast-1/mistral.voxtral-small-24b-2507": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "input_cost_per_token": 1.2e-07, + "input_cost_per_token_batches": 6e-08, + "input_cost_per_token_flex": 6e-08, + "input_cost_per_token_priority": 2.1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 3.6e-07, + "output_cost_per_token_batches": 1.8e-07, + "output_cost_per_token_flex": 1.8e-07, + "output_cost_per_token_priority": 6.3e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/ap-northeast-1/index.json", + "supports_audio_input": true, + "supports_system_messages": true, + "supports_native_structured_output": true + }, + "bedrock/eu-west-2/mistral.voxtral-mini-3b-2507": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "input_cost_per_token": 6e-08, + "input_cost_per_token_batches": 3e-08, + "input_cost_per_token_flex": 3e-08, + "input_cost_per_token_priority": 1.1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-08, + "output_cost_per_token_batches": 3e-08, + "output_cost_per_token_flex": 3e-08, + "output_cost_per_token_priority": 1.1e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/eu-west-2/index.json", + "supports_audio_input": true, + "supports_system_messages": true, + "supports_native_structured_output": true + }, + "bedrock/eu-west-2/mistral.voxtral-small-24b-2507": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "input_cost_per_token": 1.6e-07, + "input_cost_per_token_batches": 8e-08, + "input_cost_per_token_flex": 8e-08, + "input_cost_per_token_priority": 2.8e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4.7e-07, + "output_cost_per_token_batches": 2.3e-07, + "output_cost_per_token_flex": 2.3e-07, + "output_cost_per_token_priority": 8.2e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/eu-west-2/index.json", + "supports_audio_input": true, + "supports_system_messages": true, + "supports_native_structured_output": true + }, + "mistral/codestral-2508": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://docs.mistral.ai/models/model-cards/codestral-25-08", + "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true + "supports_tool_choice": true }, - "moonshot/moonshot-v1-128k": { - "input_cost_per_token": 2e-06, - "litellm_provider": "moonshot", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "mistral/codestral-latest": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://platform.moonshot.ai/docs/pricing", + "output_cost_per_token": 9e-07, + "source": "https://docs.mistral.ai/models/model-cards/codestral-25-08", + "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, - "moonshot/moonshot-v1-128k-vision-preview": { - "input_cost_per_token": 2e-06, - "litellm_provider": "moonshot", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "mistral/codestral-mamba-latest": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 256000, + "max_output_tokens": 256000, "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://platform.moonshot.ai/docs/pricing", + "output_cost_per_token": 2.5e-07, + "source": "https://mistral.ai/technology/", + "supports_assistant_prefill": true, + "supports_tool_choice": true + }, + "mistral/devstral-small-latest": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 3e-07, + "reasoning_effort_levels": [ + "none", + "high" + ], + "source": "https://docs.mistral.ai/models/devstral-small-2-25-12", + "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_tool_choice": true }, - "moonshot/moonshot-v1-32k": { - "input_cost_per_token": 1e-06, - "litellm_provider": "moonshot", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, + "mistral/devstral-latest": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 4e-07, + "litellm_provider": "mistral", + "max_input_tokens": 256000, + "max_output_tokens": 256000, "mode": "chat", - "output_cost_per_token": 3e-06, - "source": "https://platform.moonshot.ai/docs/pricing", + "output_cost_per_token": 2e-06, + "reasoning_effort_levels": [ + "none", + "high" + ], + "source": "https://mistral.ai/news/devstral-2-vibe-cli", + "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, - "moonshot/moonshot-v1-32k-vision-preview": { - "input_cost_per_token": 1e-06, - "litellm_provider": "moonshot", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, + "mistral/devstral-medium-latest": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 4e-07, + "litellm_provider": "mistral", + "max_input_tokens": 256000, + "max_output_tokens": 256000, "mode": "chat", - "output_cost_per_token": 3e-06, - "source": "https://platform.moonshot.ai/docs/pricing", + "output_cost_per_token": 2e-06, + "reasoning_effort_levels": [ + "none", + "high" + ], + "source": "https://mistral.ai/news/devstral-2-vibe-cli", + "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_tool_choice": true }, - "moonshot/moonshot-v1-8k": { + "mistral/ministral-14b-2512": { "input_cost_per_token": 2e-07, - "litellm_provider": "moonshot", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://platform.moonshot.ai/docs/pricing", + "output_cost_per_token": 2e-07, + "source": "https://docs.mistral.ai/models/ministral-3-14b-25-12", + "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true, + "cache_read_input_token_cost": 2e-08 }, - "moonshot/moonshot-v1-8k-vision-preview": { + "mistral/ministral-14b-latest": { "input_cost_per_token": 2e-07, - "litellm_provider": "moonshot", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://platform.moonshot.ai/docs/pricing", + "output_cost_per_token": 2e-07, + "source": "https://docs.mistral.ai/models/ministral-3-14b-25-12", + "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 2e-08 }, - "moonshot/moonshot-v1-auto": { - "input_cost_per_token": 2e-06, - "litellm_provider": "moonshot", + "mistral/ministral-3b-2512": { + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://platform.moonshot.ai/docs/pricing", + "output_cost_per_token": 1e-07, + "source": "https://docs.mistral.ai/models/ministral-3-3b-25-12", + "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true, + "cache_read_input_token_cost": 1e-08 }, - "morph/morph-v3-fast": { - "input_cost_per_token": 8e-07, - "litellm_provider": "morph", - "max_input_tokens": 16000, - "max_output_tokens": 16000, - "max_tokens": 16000, + "mistral/ministral-3b-latest": { + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 1.2e-06, - "supports_function_calling": false, - "supports_parallel_function_calling": false, - "supports_system_messages": true, - "supports_tool_choice": false, - "supports_vision": false + "output_cost_per_token": 1e-07, + "source": "https://docs.mistral.ai/models/ministral-3-3b-25-12", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "cache_read_input_token_cost": 1e-08 }, - "morph/morph-v3-large": { - "input_cost_per_token": 9e-07, - "litellm_provider": "morph", - "max_input_tokens": 16000, - "max_output_tokens": 16000, - "max_tokens": 16000, + "mistral/mistral-embed-2312": { + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 8192, + "mode": "embedding", + "source": "https://docs.mistral.ai/models/mistral-embed-23-12" + }, + "mistral/mistral-medium-3": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", - "output_cost_per_token": 1.9e-06, - "supports_function_calling": false, - "supports_parallel_function_calling": false, - "supports_system_messages": true, - "supports_tool_choice": false, - "supports_vision": false + "output_cost_per_token": 7.5e-06, + "reasoning_effort_levels": [ + "none", + "high" + ], + "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "multimodalembedding": { - "input_cost_per_character": 2e-07, - "input_cost_per_image": 0.0001, - "input_cost_per_token": 8e-07, - "input_cost_per_video_per_second": 0.0005, - "input_cost_per_video_per_second_above_15s_interval": 0.002, - "input_cost_per_video_per_second_above_8s_interval": 0.001, - "litellm_provider": "vertex_ai-embedding-models", - "max_input_tokens": 2048, - "max_tokens": 2048, - "mode": "embedding", - "output_cost_per_token": 0, - "output_vector_size": 768, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", + "mistral/voxtral-mini-transcribe-realtime-latest": { + "input_cost_per_second": 0.0001, + "litellm_provider": "mistral", + "mode": "audio_transcription", + "source": "https://docs.mistral.ai/models/model-cards/voxtral-mini-transcribe-realtime-26-02", "supported_endpoints": [ - "/v1/embeddings" + "/v1/audio/transcriptions" ], "supported_modalities": [ - "text", - "image", - "video" - ] + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true }, - "multimodalembedding@001": { - "deprecation_date": "2027-04-01", - "input_cost_per_character": 2e-07, - "input_cost_per_image": 0.0001, - "input_cost_per_token": 8e-07, - "input_cost_per_video_per_second": 0.0005, - "input_cost_per_video_per_second_above_15s_interval": 0.002, - "input_cost_per_video_per_second_above_8s_interval": 0.001, - "litellm_provider": "vertex_ai-embedding-models", - "max_input_tokens": 2048, - "max_tokens": 2048, - "mode": "embedding", - "output_cost_per_token": 0, - "output_vector_size": 768, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", + "mistral/voxtral-mini-tts-latest": { + "input_cost_per_character": 1.6e-05, + "litellm_provider": "mistral", + "mode": "audio_speech", + "source": "https://docs.mistral.ai/models/model-cards/voxtral-tts-26-03", "supported_endpoints": [ - "/v1/embeddings" + "/v1/audio/speech" ], "supported_modalities": [ - "text", - "image", - "video" - ] - }, - "nscale/Qwen/QwQ-32B": { - "input_cost_per_token": 1.8e-07, - "litellm_provider": "nscale", - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + "text" + ], + "supported_output_modalities": [ + "audio" + ], + "supports_audio_output": true }, - "nscale/Qwen/Qwen2.5-Coder-32B-Instruct": { - "input_cost_per_token": 6e-08, - "litellm_provider": "nscale", - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + "mistral/voxtral-mini-transcribe-3": { + "input_cost_per_second": 5.83333e-05, + "litellm_provider": "mistral", + "mode": "audio_transcription", + "source": "https://docs.mistral.ai/models/voxtral-mini-transcribe-3-0", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true }, - "nscale/Qwen/Qwen2.5-Coder-3B-Instruct": { - "input_cost_per_token": 1e-08, - "litellm_provider": "nscale", - "mode": "chat", - "output_cost_per_token": 3e-08, - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + "mistral/voxtral-mini-transcribe-3-0": { + "input_cost_per_second": 5.83333e-05, + "litellm_provider": "mistral", + "mode": "audio_transcription", + "source": "https://docs.mistral.ai/models/voxtral-mini-transcribe-3-0", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true }, - "nscale/Qwen/Qwen2.5-Coder-7B-Instruct": { - "input_cost_per_token": 1e-08, - "litellm_provider": "nscale", - "mode": "chat", - "output_cost_per_token": 3e-08, - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + "mistral/voxtral-small-transcribe-3": { + "input_cost_per_second": 6.66667e-05, + "litellm_provider": "mistral", + "mode": "audio_transcription", + "source": "https://docs.mistral.ai/models/voxtral-small-transcribe-3-0", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true }, - "nscale/black-forest-labs/FLUX.1-schnell": { - "input_cost_per_pixel": 1.3e-09, - "litellm_provider": "nscale", - "mode": "image_generation", - "output_cost_per_pixel": 0.0, - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#image-models", + "mistral/voxtral-small-transcribe-3-0": { + "input_cost_per_second": 6.66667e-05, + "litellm_provider": "mistral", + "mode": "audio_transcription", + "source": "https://docs.mistral.ai/models/voxtral-small-transcribe-3-0", "supported_endpoints": [ - "/v1/images/generations" - ] + "/v1/audio/transcriptions" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true }, - "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { - "input_cost_per_token": 3.75e-07, - "litellm_provider": "nscale", - "metadata": { - "notes": "Pricing listed as $0.75/1M tokens total. Assumed 50/50 split for input/output." - }, - "mode": "chat", - "output_cost_per_token": 3.75e-07, - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + "mistral/voxtral-mini-transcribe-realtime-3": { + "input_cost_per_second": 0.000133333, + "litellm_provider": "mistral", + "mode": "audio_transcription", + "source": "https://docs.mistral.ai/models/voxtral-mini-transcribe-realtime-3-0", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true }, - "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B": { - "input_cost_per_token": 2.5e-08, - "litellm_provider": "nscale", - "metadata": { - "notes": "Pricing listed as $0.05/1M tokens total. Assumed 50/50 split for input/output." - }, - "mode": "chat", - "output_cost_per_token": 2.5e-08, - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + "mistral/voxtral-mini-transcribe-realtime-3-0": { + "input_cost_per_second": 0.000133333, + "litellm_provider": "mistral", + "mode": "audio_transcription", + "source": "https://docs.mistral.ai/models/voxtral-mini-transcribe-realtime-3-0", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true }, - "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": { - "input_cost_per_token": 9e-08, - "litellm_provider": "nscale", - "metadata": { - "notes": "Pricing listed as $0.18/1M tokens total. Assumed 50/50 split for input/output." - }, - "mode": "chat", - "output_cost_per_token": 9e-08, - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + "mistral/voxtral-mini-tts-3": { + "input_cost_per_character": 1.3e-05, + "litellm_provider": "mistral", + "mode": "audio_speech", + "source": "https://docs.mistral.ai/models/voxtral-mini-tts-3-0", + "supported_endpoints": [ + "/v1/audio/speech" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "audio" + ], + "supports_audio_output": true }, - "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": { - "input_cost_per_token": 7e-08, - "litellm_provider": "nscale", - "metadata": { - "notes": "Pricing listed as $0.14/1M tokens total. Assumed 50/50 split for input/output." - }, - "mode": "chat", - "output_cost_per_token": 7e-08, - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" - }, - "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": { - "input_cost_per_token": 1.5e-07, - "litellm_provider": "nscale", - "metadata": { - "notes": "Pricing listed as $0.30/1M tokens total. Assumed 50/50 split for input/output." - }, - "mode": "chat", - "output_cost_per_token": 1.5e-07, - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" - }, - "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": { - "input_cost_per_token": 2e-07, - "litellm_provider": "nscale", - "metadata": { - "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output." - }, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" - }, - "nscale/meta-llama/Llama-3.1-8B-Instruct": { - "input_cost_per_token": 3e-08, - "litellm_provider": "nscale", - "metadata": { - "notes": "Pricing listed as $0.06/1M tokens total. Assumed 50/50 split for input/output." - }, - "mode": "chat", - "output_cost_per_token": 3e-08, - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" - }, - "nscale/meta-llama/Llama-3.3-70B-Instruct": { - "input_cost_per_token": 2e-07, - "litellm_provider": "nscale", - "metadata": { - "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output." - }, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + "mistral/voxtral-mini-tts-3-0": { + "input_cost_per_character": 1.3e-05, + "litellm_provider": "mistral", + "mode": "audio_speech", + "source": "https://docs.mistral.ai/models/voxtral-mini-tts-3-0", + "supported_endpoints": [ + "/v1/audio/speech" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "audio" + ], + "supports_audio_output": true }, - "nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct": { - "input_cost_per_token": 9e-08, - "litellm_provider": "nscale", + "mistral/voxtral-small-2507": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", - "output_cost_per_token": 2.9e-07, - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + "output_cost_per_token": 4e-07, + "source": "https://docs.mistral.ai/models/voxtral-small-25-07", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "nscale/mistralai/mixtral-8x22b-instruct-v0.1": { - "input_cost_per_token": 6e-07, - "litellm_provider": "nscale", - "metadata": { - "notes": "Pricing listed as $1.20/1M tokens total. Assumed 50/50 split for input/output." - }, + "mistral/voxtral-small-latest": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" - }, - "nscale/stabilityai/stable-diffusion-xl-base-1.0": { - "input_cost_per_pixel": 3e-09, - "litellm_provider": "nscale", - "mode": "image_generation", - "output_cost_per_pixel": 0.0, - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#image-models", - "supported_endpoints": [ - "/v1/images/generations" - ] + "output_cost_per_token": 4e-07, + "source": "https://docs.mistral.ai/models/voxtral-small-25-07", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "nebius/deepseek-ai/DeepSeek-R1": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 2.4e-06, - "litellm_provider": "nebius", + "mistral/zai-glm-5-2": { + "cache_read_input_token_cost": 1.4e-07, + "deprecation_date": "2026-10-31", + "deprecation_source": "https://docs.mistral.ai/getting-started/models/models_overview", + "input_cost_per_token": 1.4e-06, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, "mode": "chat", + "output_cost_per_token": 4.4e-06, + "reasoning_effort_levels": [ + "none", + "minimal", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "source": "https://docs.mistral.ai/models/zai-glm-5-2", + "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "source": "https://nebius.com/prices" + "supports_response_schema": true, + "supports_tool_choice": true }, - "nebius/deepseek-ai/DeepSeek-R1-0528": { - "max_tokens": 164000, - "max_input_tokens": 164000, - "max_output_tokens": 164000, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 2.4e-06, - "litellm_provider": "nebius", + "mistral/deepseek-v4-1-flash-1017": { + "cache_read_input_token_cost": 7e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://docs.mistral.ai/models/deepseek-v4-flash-1017", + "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "source": "https://nebius.com/prices" + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "nebius/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 7.5e-07, - "litellm_provider": "nebius", + "mistral/zai-glm-5-3": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, "mode": "chat", + "output_cost_per_token": 4.4e-06, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://docs.mistral.ai/models/zai-glm-5-3", + "supports_assistant_prefill": true, "supports_function_calling": true, - "source": "https://nebius.com/prices" + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "nebius/deepseek-ai/DeepSeek-V3": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "nebius", + "mistral/zai-glm-5-3-flash": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, "mode": "chat", + "output_cost_per_token": 5e-07, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://docs.mistral.ai/models/zai-glm-5-3-flash", + "supports_assistant_prefill": true, "supports_function_calling": true, - "source": "https://nebius.com/prices" + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "nebius/deepseek-ai/DeepSeek-V3-0324": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "nebius", + "mistral/zai-glm-5": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, "mode": "chat", + "output_cost_per_token": 4.4e-06, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://docs.mistral.ai/models/zai-glm-5-3", + "supports_assistant_prefill": true, "supports_function_calling": true, - "source": "https://nebius.com/prices" + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "nebius/google/gemma-3-27b-it": { - "max_tokens": 110000, - "max_input_tokens": 110000, - "max_output_tokens": 110000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "nebius", + "mistral/zai-glm-latest": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, "mode": "chat", + "output_cost_per_token": 4.4e-06, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://docs.mistral.ai/models/zai-glm-5-3", + "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_vision": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/google%2Fgemma-3-27b-it" + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "nebius/meta-llama/Llama-3.3-70B-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, + "mistral/glm-5-2": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, "max_output_tokens": 131072, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "nebius", "mode": "chat", + "output_cost_per_token": 4.4e-06, + "reasoning_effort_levels": [ + "none", + "minimal", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "source": "https://docs.mistral.ai/models/zai-glm-5-2", + "supports_assistant_prefill": true, "supports_function_calling": true, - "source": "https://nebius.com/prices" + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "nebius/meta-llama/Llama-Guard-3-8B": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 2e-08, - "output_cost_per_token": 6e-08, - "litellm_provider": "nebius", - "mode": "chat", - "source": "https://nebius.com/prices" + "mistral/mistral-ocr-latest": { + "litellm_provider": "mistral", + "ocr_cost_per_page": 0.004, + "ocr_cost_per_page_batches": 0.002, + "annotation_cost_per_page": 0.005, + "annotation_cost_per_page_batches": 0.0025, + "mode": "ocr", + "supported_endpoints": [ + "/v1/ocr", + "/v1/batch" + ], + "source": "https://mistral.ai/pricing#api-pricing" }, - "nebius/meta-llama/Meta-Llama-3.1-8B-Instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 2e-08, - "output_cost_per_token": 6e-08, - "litellm_provider": "nebius", - "mode": "chat", - "supports_function_calling": true, - "source": "https://nebius.com/prices" + "mistral/mistral-ocr-4-0": { + "deprecation_date": "2026-09-30", + "litellm_provider": "mistral", + "ocr_cost_per_page": 0.004, + "ocr_cost_per_page_batches": 0.002, + "annotation_cost_per_page": 0.005, + "annotation_cost_per_page_batches": 0.0025, + "mode": "ocr", + "supported_endpoints": [ + "/v1/ocr", + "/v1/batch" + ], + "source": "https://mistral.ai/pricing#api-pricing" }, - "nebius/meta-llama/Meta-Llama-3.1-70B-Instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "nebius", - "mode": "chat", - "supports_function_calling": true, - "source": "https://nebius.com/prices" + "mistral/mistral-ocr-4-1": { + "annotation_cost_per_page": 0.005, + "annotation_cost_per_page_batches": 0.0025, + "litellm_provider": "mistral", + "mode": "ocr", + "ocr_cost_per_page": 0.004, + "ocr_cost_per_page_batches": 0.002, + "source": "https://docs.mistral.ai/models/model-cards/ocr-4-1", + "supported_endpoints": [ + "/v1/ocr", + "/v1/batch" + ] }, - "nebius/meta-llama/Meta-Llama-3.1-405B-Instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "nebius", - "mode": "chat", - "supports_function_calling": true, - "source": "https://nebius.com/prices" + "mistral/mistral-ocr-2512": { + "litellm_provider": "mistral", + "ocr_cost_per_page": 0.002, + "ocr_cost_per_page_batches": 0.001, + "annotation_cost_per_page": 0.003, + "annotation_cost_per_page_batches": 0.0015, + "mode": "ocr", + "supported_endpoints": [ + "/v1/ocr", + "/v1/batch" + ], + "source": "https://mistral.ai/pricing#api-pricing" }, - "nebius/mistralai/Mistral-Nemo-Instruct-2407": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 4e-08, - "output_cost_per_token": 1.2e-07, - "litellm_provider": "nebius", + "mistral/magistral-medium-latest": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", + "output_cost_per_token": 7.5e-06, + "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", + "supports_assistant_prefill": true, "supports_function_calling": true, - "source": "https://nebius.com/prices" + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "nebius/NousResearch/Hermes-3-Llama-3.1-405B": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "nebius", + "mistral/magistral-small-latest": { + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03", + "supports_assistant_prefill": true, "supports_function_calling": true, - "source": "https://nebius.com/prices" + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "nebius/nvidia/Llama-3.1-Nemotron-Ultra-253B-v1": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 1.8e-06, - "litellm_provider": "nebius", + "mistral/mistral-embed": { + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 8192, + "mode": "embedding" + }, + "mistral/codestral-embed": { + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 8192, + "mode": "embedding" + }, + "mistral/codestral-embed-2505": { + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 8192, + "mode": "embedding" + }, + "mistral/mistral-large-4": { + "cache_read_input_token_cost": 7e-08, + "input_cost_per_token": 7e-07, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", + "output_cost_per_token": 2.1e-06, + "reasoning_effort_levels": [ + "none", + "high" + ], + "source": "https://docs.mistral.ai/models/mistral-large-4-0", + "supports_assistant_prefill": true, "supports_function_calling": true, - "source": "https://nebius.com/prices" + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "nebius/nvidia/Llama-3.3-Nemotron-Super-49B-v1": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "nebius", + "mistral/mistral-large-4-0": { + "cache_read_input_token_cost": 7e-08, + "input_cost_per_token": 7e-07, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", + "output_cost_per_token": 2.1e-06, + "reasoning_effort_levels": [ + "none", + "high" + ], + "source": "https://docs.mistral.ai/models/mistral-large-4-0", + "supports_assistant_prefill": true, "supports_function_calling": true, - "source": "https://nebius.com/prices" + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "nebius/Qwen/Qwen3-235B-A22B": { - "max_tokens": 262144, + "mistral/mistral-large-latest": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 5e-07, + "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "nebius", "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", + "supports_assistant_prefill": true, "supports_function_calling": true, - "source": "https://nebius.com/prices" + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "nebius/Qwen/Qwen3-32B": { - "max_tokens": 40960, - "max_input_tokens": 40960, - "max_output_tokens": 40960, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "nebius", + "mistral/mistral-large-3": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", + "supports_assistant_prefill": true, "supports_function_calling": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-32B" + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "nebius/Qwen/Qwen3-30B-A3B": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "nebius", + "mistral/mistral-large-2512": { + "deprecation_date": "2027-04-30", + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", + "supports_assistant_prefill": true, "supports_function_calling": true, - "source": "https://nebius.com/prices" - }, - "nebius/Qwen/Qwen3-14B": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 8e-08, - "output_cost_per_token": 2.4e-07, - "litellm_provider": "nebius", - "mode": "chat", - "supports_function_calling": true, - "source": "https://nebius.com/prices" - }, - "nebius/Qwen/Qwen3-4B": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 8e-08, - "output_cost_per_token": 2.4e-07, - "litellm_provider": "nebius", - "mode": "chat", - "supports_function_calling": true, - "source": "https://nebius.com/prices" + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "nebius/Qwen/QwQ-32B": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 4.5e-07, - "litellm_provider": "nebius", + "mistral/mistral-medium": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", + "output_cost_per_token": 7.5e-06, + "reasoning_effort_levels": [ + "none", + "high" + ], + "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", + "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, - "source": "https://nebius.com/prices" + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "nebius/Qwen/Qwen2.5-72B-Instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "nebius", + "mistral/mistral-medium-2604": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", + "output_cost_per_token": 7.5e-06, + "reasoning_effort_levels": [ + "none", + "high" + ], + "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", + "supports_assistant_prefill": true, "supports_function_calling": true, - "source": "https://nebius.com/prices" + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "nebius/Qwen/Qwen2.5-32B-Instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 6e-08, - "output_cost_per_token": 2e-07, - "litellm_provider": "nebius", + "mistral/mistral-medium-latest": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", + "output_cost_per_token": 7.5e-06, + "reasoning_effort_levels": [ + "none", + "high" + ], + "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", + "supports_assistant_prefill": true, "supports_function_calling": true, - "source": "https://nebius.com/prices" + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "nebius/Qwen/Qwen2.5-Coder-7B": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-08, - "output_cost_per_token": 3e-08, - "litellm_provider": "nebius", + "mistral/mistral-medium-3-5": { + "deprecation_date": "2027-04-30", + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", + "output_cost_per_token": 7.5e-06, + "reasoning_effort_levels": [ + "none", + "high" + ], + "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", + "supports_assistant_prefill": true, "supports_function_calling": true, - "source": "https://nebius.com/prices" + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "nebius/Qwen/Qwen2.5-VL-72B-Instruct": { - "max_tokens": 32000, + "mistral/mistral-small": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", "max_input_tokens": 32000, - "max_output_tokens": 32000, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 7.5e-07, - "litellm_provider": "nebius", + "max_output_tokens": 8191, "mode": "chat", + "output_cost_per_token": 3e-07, + "reasoning_effort_levels": [ + "none", + "high" + ], + "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_vision": true, - "source": "https://tokenfactory.nebius.com/models/catalog/image2text/Qwen%2FQwen2.5-VL-72B-Instruct" + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "nebius/Qwen/Qwen2-VL-72B-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "nebius", + "mistral/mistral-small-latest": { + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", + "output_cost_per_token": 6e-07, + "reasoning_effort_levels": [ + "none", + "high" + ], + "source": "https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03", + "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_vision": true, - "source": "https://nebius.com/prices" + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "nebius/Qwen/Qwen2-VL-7B-Instruct": { - "max_tokens": 131072, + "mistral/ministral-3-3b-2512": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 2e-08, - "output_cost_per_token": 6e-08, - "litellm_provider": "nebius", - "mode": "chat", - "supports_vision": true, - "source": "https://nebius.com/prices" - }, - "nebius/deepseek-ai/DeepSeek-V4-Flash": { - "max_tokens": 1048576, - "max_input_tokens": 1048576, - "max_output_tokens": 1048576, - "input_cost_per_token": 1.4e-07, - "output_cost_per_token": 2.8e-07, - "litellm_provider": "nebius", "mode": "chat", + "output_cost_per_token": 1e-07, + "source": "https://mistral.ai/pricing", + "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_reasoning": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Flash" + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "nebius/deepseek-ai/DeepSeek-V4-Flash-0731": { - "max_tokens": 1024000, - "max_input_tokens": 1024000, - "max_output_tokens": 1024000, - "input_cost_per_token": 1.4e-07, - "output_cost_per_token": 2.8e-07, - "litellm_provider": "nebius", + "mistral/ministral-3-8b-2512": { + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://mistral.ai/pricing", + "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_reasoning": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Flash-0731" + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "nebius/deepseek-ai/DeepSeek-V4-Pro": { - "max_tokens": 1048576, - "max_input_tokens": 1048576, - "max_output_tokens": 1048576, - "input_cost_per_token": 1.75e-06, - "output_cost_per_token": 3.5e-06, - "litellm_provider": "nebius", + "mistral/ministral-3-14b-2512": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://mistral.ai/pricing", + "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_reasoning": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Pro" + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "nebius/deepseek-ai/DeepSeek-V4-Pro-0813": { - "input_cost_per_token": 1.32e-06, - "litellm_provider": "nebius", + "mistral/ministral-8b-2512": { + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", - "output_cost_per_token": 3.96e-06, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Pro-0813", + "output_cost_per_token": 1.5e-07, + "source": "https://mistral.ai/pricing", + "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_reasoning": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "nebius/deepseek-ai/DeepSeek-V4.1-Flash": { - "input_cost_per_token": 3e-07, - "litellm_provider": "nebius", - "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, + "mistral/ministral-8b-latest": { + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://tokenfactory.nebius.com/endpoints?modals=endpoint-details&model-id=deepseek-ai/DeepSeek-V4.1-Flash", + "output_cost_per_token": 1.5e-07, + "source": "https://mistral.ai/pricing", + "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, "supports_vision": true }, - "nebius/MiniMaxAI/MiniMax-M2.5": { - "max_tokens": 196608, - "max_input_tokens": 196608, - "max_output_tokens": 196608, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "nebius", + "mistral/mistral-tiny": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, "mode": "chat", - "supports_function_calling": true, - "supports_reasoning": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/MiniMaxAI%2FMiniMax-M2.5" + "output_cost_per_token": 2.5e-07, + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "nebius/MiniMaxAI/MiniMax-M3": { - "max_tokens": 1048576, - "max_input_tokens": 1048576, - "max_output_tokens": 1048576, + "mistral/open-mistral-nemo": { + "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "nebius", + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, "mode": "chat", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_vision": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/MiniMaxAI%2FMiniMax-M3" + "output_cost_per_token": 3e-07, + "source": "https://mistral.ai/technology/", + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "nebius/moonshotai/Kimi-K2.6": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 9.5e-07, - "output_cost_per_token": 4e-06, - "litellm_provider": "nebius", + "mistral/pixtral-large-latest": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_reasoning": true, - "supports_vision": true, - "source": "https://tokenfactory.nebius.com/models/catalog/image2text/moonshotai%2FKimi-K2.6" + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "nebius/moonshotai/Kimi-K2.7-Code": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 9.5e-07, - "output_cost_per_token": 4e-06, - "litellm_provider": "nebius", + "moonshot.kimi-k2-thinking": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "input_cost_per_token": 6e-07, + "input_cost_per_token_batches": 3e-07, + "input_cost_per_token_priority": 1.05e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 256000, + "max_output_tokens": 16000, "mode": "chat", + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_priority": 4.38e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supports_audio_input": false, "supports_function_calling": true, "supports_reasoning": true, - "supports_vision": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/moonshotai%2FKimi-K2.7-Code" + "supports_system_messages": true, + "supports_native_structured_output": true, + "supports_response_schema": true, + "supports_vision": false }, - "nebius/moonshotai/Kimi-K3": { - "max_tokens": 1024000, - "max_input_tokens": 1024000, - "max_output_tokens": 1024000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "nebius", + "moonshotai.kimi-k2.5": { + "input_cost_per_token": 6e-07, + "input_cost_per_token_batches": 3e-07, + "input_cost_per_token_flex": 3e-07, + "input_cost_per_token_priority": 1.05e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 256000, + "max_output_tokens": 16000, "mode": "chat", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_vision": true, - "source": "https://tokenfactory.nebius.com/models/catalog/image2text/moonshotai%2FKimi-K3" - }, - "nebius/NousResearch/Hermes-4-405B": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1e-06, "output_cost_per_token": 3e-06, - "litellm_provider": "nebius", - "mode": "chat", - "supports_function_calling": true, - "supports_reasoning": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/NousResearch%2FHermes-4-405B" - }, - "nebius/NousResearch/Hermes-4-70B": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "nebius", - "mode": "chat", + "output_cost_per_token_batches": 1.5e-06, + "output_cost_per_token_flex": 1.5e-06, + "output_cost_per_token_priority": 5.25e-06, "supports_function_calling": true, - "supports_reasoning": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/NousResearch%2FHermes-4-70B" + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supports_audio_input": false, + "supports_response_schema": true }, - "nebius/nvidia/Cosmos3-Super-Reasoner": { - "max_tokens": 262144, + "moonshot/kimi-k2.7-code": { + "cache_read_input_token_cost": 1.9e-07, + "input_cost_per_token": 9.5e-07, + "litellm_provider": "moonshot", "max_input_tokens": 262144, "max_output_tokens": 262144, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "nebius", "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://platform.kimi.ai/docs/pricing/chat-k27-code", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_vision": true, - "source": "https://tokenfactory.nebius.com/models/catalog/image2text/nvidia%2FCosmos3-Super-Reasoner" + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true }, - "nebius/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, + "moonshot/kimi-k2.5": { + "cache_read_input_token_cost": 1e-07, + "deprecation_date": "2026-08-31", "input_cost_per_token": 6e-07, - "output_cost_per_token": 1.8e-06, - "litellm_provider": "nebius", - "mode": "chat", - "supports_reasoning": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FLlama-3_1-Nemotron-Ultra-253B-v1" - }, - "nebius/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B": { - "max_tokens": 262144, + "litellm_provider": "moonshot", "max_input_tokens": 262144, "max_output_tokens": 262144, - "input_cost_per_token": 6e-08, - "output_cost_per_token": 2.4e-07, - "litellm_provider": "nebius", "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart", "supports_function_calling": true, "supports_reasoning": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNVIDIA-Nemotron-3-Nano-30B-A3B" + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true }, - "nebius/nvidia/Nemotron-3-Nano-Omni": { - "max_tokens": 262144, + "moonshot/kimi-k2.6": { + "cache_read_input_token_cost": 1.6e-07, + "input_cost_per_token": 9.5e-07, + "litellm_provider": "moonshot", "max_input_tokens": 262144, "max_output_tokens": 262144, - "input_cost_per_token": 6e-08, - "output_cost_per_token": 2.4e-07, - "litellm_provider": "nebius", "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://platform.kimi.ai/docs/pricing/chat-k26", "supports_function_calling": true, "supports_reasoning": true, - "supports_vision": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNemotron-3-Nano-Omni" + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true }, - "nebius/nvidia/nemotron-3-super-120b-a12b": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 9e-07, - "litellm_provider": "nebius", + "moonshot/kimi-k3.1-pro": { + "cache_creation_input_token_cost": 2e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", + "output_cost_per_token": 1e-05, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://platform.kimi.ai/docs/pricing/chat", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2Fnemotron-3-super-120b-a12b" + "supports_response_schema": true, + "supports_vision": true }, - "nebius/nvidia/Nemotron-3-Ultra-550b-a55b": { - "max_tokens": 1048576, + "moonshot/kimi-k3.1-pro-highspeed": { + "cache_creation_input_token_cost": 0.000004, + "cache_creation_input_token_cost_above_1hr": 0.000008, + "cache_read_input_token_cost": 2e-7, + "input_cost_per_token": 0.000004, + "litellm_provider": "moonshot", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "nebius", "mode": "chat", + "output_cost_per_token": 0.00002, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://platform.kimi.ai/docs/pricing/chat", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNemotron-3-Ultra-550b-a55b" + "supports_response_schema": true, + "supports_vision": true }, - "nebius/nvidia/Nemotron-3_5-Lightning": { - "max_tokens": 1048576, + "moonshot/kimi-k3": { + "cache_creation_input_token_cost": 3e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "moonshot", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "input_cost_per_token": 6e-08, - "output_cost_per_token": 2.4e-07, - "litellm_provider": "nebius", "mode": "chat", + "output_cost_per_token": 1.5e-05, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://platform.kimi.ai/docs/pricing/chat-k3", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNemotron-3_5-Lightning" + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true }, - "nebius/openai/gpt-oss-120b": { - "max_tokens": 131072, + "moonshot/kimi-latest": { + "alias_of": "moonshot/kimi-k3" + }, + "moonshot/moonshot-v1-128k": { + "deprecation_date": "2026-08-31", + "input_cost_per_token": 2e-06, + "litellm_provider": "moonshot", "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "nebius", "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, - "supports_reasoning": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/openai%2Fgpt-oss-120b" + "supports_response_schema": true, + "supports_tool_choice": true }, - "nebius/openbmb/MiniCPM-V-4_5": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "input_cost_per_token": 6.58e-07, - "output_cost_per_token": 1.11e-06, - "litellm_provider": "nebius", + "moonshot/moonshot-v1-128k-vision-preview": { + "deprecation_date": "2026-08-31", + "input_cost_per_token": 2e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "supports_vision": true, - "source": "https://tokenfactory.nebius.com/models/catalog/image2text/openbmb%2FMiniCPM-V-4_5" + "output_cost_per_token": 5e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "nebius/Qwen/Qwen3-235B-A22B-Instruct-2507": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "nebius", + "moonshot/moonshot-v1-32k": { + "deprecation_date": "2026-08-31", + "input_cost_per_token": 1e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-235B-A22B-Instruct-2507" + "supports_response_schema": true, + "supports_tool_choice": true }, - "nebius/Qwen/Qwen3-30B-A3B-Instruct-2507": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "nebius", + "moonshot/moonshot-v1-32k-vision-preview": { + "deprecation_date": "2026-08-31", + "input_cost_per_token": 1e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-30B-A3B-Instruct-2507" + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "nebius/Qwen/Qwen3-Next-80B-A3B-Thinking": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "nebius", + "moonshot/moonshot-v1-8k": { + "deprecation_date": "2026-08-31", + "input_cost_per_token": 2e-07, + "litellm_provider": "moonshot", + "max_input_tokens": 8192, + "max_output_tokens": 8192, "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, - "supports_reasoning": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-Next-80B-A3B-Thinking" + "supports_response_schema": true, + "supports_tool_choice": true }, - "nebius/Qwen/Qwen3.5-397B-A17B": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 3.6e-06, - "litellm_provider": "nebius", + "moonshot/moonshot-v1-8k-vision-preview": { + "deprecation_date": "2026-08-31", + "input_cost_per_token": 2e-07, + "litellm_provider": "moonshot", + "max_input_tokens": 8192, + "max_output_tokens": 8192, "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, - "supports_reasoning": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3.5-397B-A17B" + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "nebius/zai-org/GLM-5.1": { - "max_tokens": 202752, - "max_input_tokens": 202752, - "max_output_tokens": 202752, - "input_cost_per_token": 1.4e-06, - "output_cost_per_token": 4.4e-06, - "litellm_provider": "nebius", + "moonshot/moonshot-v1-auto": { + "deprecation_date": "2026-08-31", + "input_cost_per_token": 2e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, - "supports_reasoning": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.1" + "supports_response_schema": true, + "supports_tool_choice": true }, - "nebius/zai-org/GLM-5.2": { - "max_tokens": 1048576, + "morph/morph-kimik3": { "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "input_cost_per_token": 1.4e-06, - "output_cost_per_token": 4.4e-06, - "litellm_provider": "nebius", + "input_cost_per_token": 2.5e-06, + "output_cost_per_token": 1.4e-05, + "cache_read_input_token_cost": 2.9e-07, + "litellm_provider": "morph", "mode": "chat", "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, "supports_reasoning": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.2" + "supports_prompt_caching": true, + "source": "https://www.morphllm.com/pricing", + "supports_vision": true }, - "nebius/zai-org/GLM-5.3": { - "input_cost_per_token": 1.4e-06, - "litellm_provider": "nebius", + "morph/morph-kimik3-fast": { "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 6e-06, + "output_cost_per_token": 2.25e-05, + "cache_read_input_token_cost": 6e-07, + "litellm_provider": "morph", "mode": "chat", - "output_cost_per_token": 4.4e-06, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.3", "supports_function_calling": true, - "supports_reasoning": true + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "source": "https://www.morphllm.com/pricing", + "supports_vision": true }, - "nebius/zai-org/GLM-5.3-Flash": { - "max_tokens": 1024000, - "max_input_tokens": 1024000, - "max_output_tokens": 1024000, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "nebius", + "morph/morph-glm53-744b": { + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 1.19e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 1.955e-07, + "litellm_provider": "morph", "mode": "chat", "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, "supports_reasoning": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.3-Flash" - }, - "nebius/BAAI/bge-en-icl": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "input_cost_per_token": 1e-08, - "output_cost_per_token": 0.0, - "litellm_provider": "nebius", - "mode": "embedding", - "source": "https://nebius.com/prices" - }, - "nebius/BAAI/bge-multilingual-gemma2": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "input_cost_per_token": 1e-08, - "output_cost_per_token": 0.0, - "litellm_provider": "nebius", - "mode": "embedding", - "source": "https://nebius.com/prices" - }, - "nebius/intfloat/e5-mistral-7b-instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "input_cost_per_token": 1e-08, - "output_cost_per_token": 0.0, - "litellm_provider": "nebius", - "mode": "embedding", - "source": "https://nebius.com/prices" - }, - "nebius/Qwen/Qwen3-Embedding-8B": { - "max_tokens": 40960, - "max_input_tokens": 40960, - "input_cost_per_token": 1e-08, - "output_cost_per_token": 0.0, - "litellm_provider": "nebius", - "mode": "embedding", - "source": "https://tokenfactory.nebius.com/models/catalog/embedding/Qwen%2FQwen3-Embedding-8B" + "supports_prompt_caching": true, + "source": "https://www.morphllm.com/pricing" }, - "nvidia.nemotron-nano-12b-v2": { + "morph/morph-glm53flash": { + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "input_cost_per_token": 2e-07, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8000, - "max_tokens": 8000, + "output_cost_per_token": 7e-07, + "cache_read_input_token_cost": 4e-08, + "litellm_provider": "morph", "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", - "supports_audio_input": false, "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_system_messages": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "source": "https://www.morphllm.com/pricing", "supports_vision": true }, - "nvidia.nemotron-nano-9b-v2": { - "input_cost_per_token": 6e-08, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8000, - "max_tokens": 8000, - "mode": "chat", - "output_cost_per_token": 2.3e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_vision": false - }, - "nvidia.nemotron-nano-3-30b": { - "input_cost_per_token": 6e-08, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 256000, - "max_output_tokens": 8000, - "max_tokens": 8000, + "morph/morph-dsv41flash": { + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 8e-07, + "cache_read_input_token_cost": 8e-09, + "litellm_provider": "morph", "mode": "chat", - "output_cost_per_token": 2.4e-07, "supports_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", - "supports_audio_input": false, - "supports_native_structured_output": true, + "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": false - }, - "nvidia.nemotron-super-3-120b": { - "input_cost_per_token": 1.5e-07, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 256000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 6.5e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", - "supports_audio_input": false, - "supports_function_calling": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": false - }, - "o1": { - "cache_read_input_token_cost": 7.5e-06, - "deprecation_date": "2026-10-23", - "input_cost_per_token": 1.5e-05, - "input_cost_per_token_batches": 7.5e-06, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "output_cost_per_token": 6e-05, - "output_cost_per_token_batches": 3e-05, - "source": "https://developers.openai.com/api/docs/pricing", - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, + "source": "https://www.morphllm.com/pricing", "supports_vision": true }, - "o1-2024-12-17": { - "cache_read_input_token_cost": 7.5e-06, - "deprecation_date": "2026-10-23", - "input_cost_per_token": 1.5e-05, - "input_cost_per_token_batches": 7.5e-06, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "morph/morph-dsv41flash-1017": { + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 8e-07, + "cache_read_input_token_cost": 8e-09, + "litellm_provider": "morph", "mode": "chat", - "output_cost_per_token": 6e-05, - "output_cost_per_token_batches": 3e-05, - "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "source": "https://www.morphllm.com/pricing", "supports_vision": true }, - "o1-pro": { - "deprecation_date": "2026-10-23", - "input_cost_per_token": 0.00015, - "input_cost_per_token_batches": 7.5e-05, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "responses", - "output_cost_per_token": 0.0006, - "output_cost_per_token_batches": 0.0003, - "source": "https://developers.openai.com/api/docs/pricing", - "supported_endpoints": [ - "/v1/responses", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], + "morph/morph-dsv41flash-abliterated": { + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 3e-08, + "litellm_provider": "morph", + "mode": "chat", "supports_function_calling": true, - "supports_native_streaming": false, "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "source": "https://www.morphllm.com/pricing", "supports_vision": true }, - "o1-pro-2025-03-19": { - "deprecation_date": "2026-10-23", - "input_cost_per_token": 0.00015, - "input_cost_per_token_batches": 7.5e-05, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "responses", - "output_cost_per_token": 0.0006, - "output_cost_per_token_batches": 0.0003, - "source": "https://developers.openai.com/api/docs/pricing", - "supported_endpoints": [ - "/v1/responses", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], + "morph/morph-dsv4flash": { + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 1.41953125e-07, + "output_cost_per_token": 3.99625e-07, + "cache_read_input_token_cost": 3.59375e-08, + "litellm_provider": "morph", + "mode": "chat", "supports_function_calling": true, - "supports_native_streaming": false, "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "source": "https://www.morphllm.com/pricing" + }, + "morph/morph-v3-fast": { + "input_cost_per_token": 8e-07, + "litellm_provider": "morph", + "max_input_tokens": 16000, + "max_output_tokens": 16000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "supports_function_calling": false, + "supports_parallel_function_calling": false, "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_tool_choice": false, + "supports_vision": false }, - "o3": { - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_flex": 2.5e-07, - "cache_read_input_token_cost_priority": 8.75e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_batches": 1e-06, - "input_cost_per_token_flex": 1e-06, - "input_cost_per_token_priority": 3.5e-06, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "morph/morph-v3-large": { + "input_cost_per_token": 9e-07, + "litellm_provider": "morph", + "max_input_tokens": 16000, + "max_output_tokens": 16000, "mode": "chat", - "output_cost_per_token": 8e-06, - "output_cost_per_token_batches": 4e-06, - "output_cost_per_token_flex": 4e-06, - "output_cost_per_token_priority": 1.4e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "source": "https://developers.openai.com/api/docs/pricing", - "supported_endpoints": [ - "/v1/responses", - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, + "output_cost_per_token": 1.9e-06, + "supports_function_calling": false, "supports_parallel_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_system_messages": true, + "supports_tool_choice": false, + "supports_vision": false }, - "o3-deep-research": { - "cache_read_input_token_cost": 2.5e-06, - "input_cost_per_token": 1e-05, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "responses", - "output_cost_per_token": 4e-05, - "source": "https://developers.openai.com/api/docs/models/o3-deep-research", + "multimodalembedding": { + "input_cost_per_character": 2e-07, + "input_cost_per_image": 0.0001, + "input_cost_per_token": 8e-07, + "input_cost_per_video_per_second": 0.0005, + "input_cost_per_video_per_second_above_15s_interval": 0.002, + "input_cost_per_video_per_second_above_8s_interval": 0.001, + "litellm_provider": "vertex_ai-embedding-models", + "max_input_tokens": 2048, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", "supported_endpoints": [ - "/v1/batch", - "/v1/responses" + "/v1/embeddings" ], "supported_modalities": [ "text", - "image" - ], - "supported_output_modalities": [ - "text" + "image", + "video" ], - "supports_function_calling": false, - "supports_native_streaming": true, - "supports_parallel_function_calling": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": true, - "supports_pdf_input": true, - "deprecation_date": "2026-07-23" + "supports_embedding_image_input": true }, - "o3-2025-04-16": { - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_flex": 2.5e-07, - "cache_read_input_token_cost_priority": 8.75e-07, - "deprecation_date": "2026-12-11", - "input_cost_per_token": 2e-06, - "input_cost_per_token_batches": 1e-06, - "input_cost_per_token_flex": 1e-06, - "input_cost_per_token_priority": 3.5e-06, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "output_cost_per_token": 8e-06, - "output_cost_per_token_batches": 4e-06, - "output_cost_per_token_flex": 4e-06, - "output_cost_per_token_priority": 1.4e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "source": "https://developers.openai.com/api/docs/pricing", + "multimodalembedding@001": { + "deprecation_date": "2027-04-01", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "input_cost_per_character": 2e-07, + "input_cost_per_image": 0.0001, + "input_cost_per_token": 8e-07, + "input_cost_per_video_per_second": 0.0005, + "input_cost_per_video_per_second_above_15s_interval": 0.002, + "input_cost_per_video_per_second_above_8s_interval": 0.001, + "litellm_provider": "vertex_ai-embedding-models", + "max_input_tokens": 2048, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", "supported_endpoints": [ - "/v1/responses", - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" + "/v1/embeddings" ], "supported_modalities": [ "text", - "image" - ], - "supported_output_modalities": [ - "text" + "image", + "video" ], - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_embedding_image_input": true }, - "o3-mini": { - "cache_read_input_token_cost": 5.5e-07, - "deprecation_date": "2026-10-23", - "input_cost_per_token": 1.1e-06, - "input_cost_per_token_batches": 5.5e-07, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "nscale/Qwen/QwQ-32B": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "nscale", "mode": "chat", - "output_cost_per_token": 4.4e-06, - "output_cost_per_token_batches": 2.2e-06, - "source": "https://developers.openai.com/api/docs/pricing", - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false + "output_cost_per_token": 2e-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, - "o3-mini-2025-01-31": { - "cache_read_input_token_cost": 5.5e-07, - "deprecation_date": "2026-10-23", - "input_cost_per_token": 1.1e-06, - "input_cost_per_token_batches": 5.5e-07, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "nscale/Qwen/Qwen2.5-Coder-32B-Instruct": { + "input_cost_per_token": 6e-08, + "litellm_provider": "nscale", "mode": "chat", - "output_cost_per_token": 4.4e-06, - "output_cost_per_token_batches": 2.2e-06, - "source": "https://developers.openai.com/api/docs/pricing", - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false + "output_cost_per_token": 2e-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, - "o3-pro": { - "input_cost_per_token": 2e-05, - "input_cost_per_token_batches": 1e-05, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "responses", - "output_cost_per_token": 8e-05, - "output_cost_per_token_batches": 4e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "source": "https://developers.openai.com/api/docs/pricing", + "nscale/Qwen/Qwen2.5-Coder-3B-Instruct": { + "input_cost_per_token": 1e-08, + "litellm_provider": "nscale", + "mode": "chat", + "output_cost_per_token": 3e-08, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/Qwen/Qwen2.5-Coder-7B-Instruct": { + "input_cost_per_token": 1e-08, + "litellm_provider": "nscale", + "mode": "chat", + "output_cost_per_token": 3e-08, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/black-forest-labs/FLUX.1-schnell": { + "input_cost_per_pixel": 1.3e-09, + "litellm_provider": "nscale", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#image-models", "supported_endpoints": [ - "/v1/responses", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "/v1/images/generations" + ] }, - "o3-pro-2025-06-10": { - "deprecation_date": "2026-12-11", - "input_cost_per_token": 2e-05, - "input_cost_per_token_batches": 1e-05, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "responses", - "output_cost_per_token": 8e-05, - "output_cost_per_token_batches": 4e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { + "input_cost_per_token": 3.75e-07, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.75/1M tokens total. Assumed 50/50 split for input/output." }, - "source": "https://developers.openai.com/api/docs/pricing", - "supported_endpoints": [ - "/v1/responses", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "mode": "chat", + "output_cost_per_token": 3.75e-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, - "o4-mini": { - "cache_read_input_token_cost": 2.75e-07, - "cache_read_input_token_cost_flex": 1.38e-07, - "cache_read_input_token_cost_priority": 5e-07, - "deprecation_date": "2026-10-23", - "input_cost_per_token": 1.1e-06, - "input_cost_per_token_batches": 5.5e-07, - "input_cost_per_token_flex": 5.5e-07, - "input_cost_per_token_priority": 2e-06, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B": { + "input_cost_per_token": 2.5e-08, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.05/1M tokens total. Assumed 50/50 split for input/output." + }, "mode": "chat", - "output_cost_per_token": 4.4e-06, - "output_cost_per_token_batches": 2.2e-06, - "output_cost_per_token_flex": 2.2e-06, - "output_cost_per_token_priority": 8e-06, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "output_cost_per_token": 2.5e-08, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": { + "input_cost_per_token": 9e-08, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.18/1M tokens total. Assumed 50/50 split for input/output." }, - "source": "https://developers.openai.com/api/docs/pricing", - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "mode": "chat", + "output_cost_per_token": 9e-08, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, - "o4-mini-deep-research": { - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 2e-06, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "responses", - "output_cost_per_token": 8e-06, - "source": "https://developers.openai.com/api/docs/models/o4-mini-deep-research", - "supported_endpoints": [ - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": false, - "supports_native_streaming": true, - "supports_parallel_function_calling": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": true, - "supports_pdf_input": true, - "deprecation_date": "2026-07-23" + "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": { + "input_cost_per_token": 7e-08, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.14/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 7e-08, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, - "o4-mini-2025-04-16": { - "cache_read_input_token_cost": 2.75e-07, - "cache_read_input_token_cost_flex": 1.38e-07, - "cache_read_input_token_cost_priority": 5e-07, - "deprecation_date": "2026-10-23", - "input_cost_per_token": 1.1e-06, - "input_cost_per_token_batches": 5.5e-07, - "input_cost_per_token_flex": 5.5e-07, - "input_cost_per_token_priority": 2e-06, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.30/1M tokens total. Assumed 50/50 split for input/output." + }, "mode": "chat", - "output_cost_per_token": 4.4e-06, - "output_cost_per_token_batches": 2.2e-06, - "output_cost_per_token_flex": 2.2e-06, - "output_cost_per_token_priority": 8e-06, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "output_cost_per_token": 1.5e-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": { + "input_cost_per_token": 2e-07, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output." }, - "source": "https://developers.openai.com/api/docs/pricing", - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, - "oci/meta.llama-3.1-8b-instruct": { - "input_cost_per_token": 7.2e-07, - "litellm_provider": "oci", - "max_input_tokens": 128000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "nscale/meta-llama/Llama-3.1-8B-Instruct": { + "input_cost_per_token": 3e-08, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.06/1M tokens total. Assumed 50/50 split for input/output." + }, "mode": "chat", - "output_cost_per_token": 7.2e-07, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", - "supports_function_calling": true, - "supports_response_schema": false, - "supports_native_streaming": true + "output_cost_per_token": 3e-08, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, - "oci/meta.llama-3.1-70b-instruct": { - "input_cost_per_token": 7.2e-07, - "litellm_provider": "oci", + "nscale/meta-llama/Llama-3.3-70B-Instruct": { + "input_cost_per_token": 2e-07, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct": { + "input_cost_per_token": 9e-08, + "litellm_provider": "nscale", + "mode": "chat", + "output_cost_per_token": 2.9e-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/mistralai/mixtral-8x22b-instruct-v0.1": { + "input_cost_per_token": 6e-07, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $1.20/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/stabilityai/stable-diffusion-xl-base-1.0": { + "input_cost_per_pixel": 3e-09, + "litellm_provider": "nscale", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#image-models", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "nebius/deepseek-ai/DeepSeek-R1": { "max_input_tokens": 128000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "max_output_tokens": 128000, + "input_cost_per_token": 8e-07, + "output_cost_per_token": 2.4e-06, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 7.2e-07, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false, - "supports_native_streaming": true + "supports_reasoning": true, + "source": "https://nebius.com/prices" }, - "oci/meta.llama-3.1-405b-instruct": { - "input_cost_per_token": 1.068e-05, - "litellm_provider": "oci", - "max_input_tokens": 128000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "nebius/deepseek-ai/DeepSeek-R1-0528": { + "max_input_tokens": 164000, + "max_output_tokens": 164000, + "input_cost_per_token": 8e-07, + "output_cost_per_token": 2.4e-06, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 1.068e-05, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false, - "supports_native_streaming": true + "supports_reasoning": true, + "source": "https://nebius.com/prices" }, - "oci/meta.llama-3.2-90b-vision-instruct": { - "input_cost_per_token": 2e-06, - "litellm_provider": "oci", + "nebius/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { "max_input_tokens": 128000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "max_output_tokens": 128000, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 7.5e-07, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false, - "supports_native_streaming": true, - "supports_vision": true + "source": "https://nebius.com/prices" }, - "oci/meta.llama-3.3-70b-instruct": { - "input_cost_per_token": 7.2e-07, - "litellm_provider": "oci", + "nebius/deepseek-ai/DeepSeek-V3": { "max_input_tokens": 128000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "max_output_tokens": 128000, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 1.5e-06, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 7.2e-07, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false, - "supports_native_streaming": true + "source": "https://nebius.com/prices" }, - "oci/meta.llama-4-maverick-17b-128e-instruct-fp8": { - "input_cost_per_token": 7.2e-07, - "litellm_provider": "oci", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, + "nebius/deepseek-ai/DeepSeek-V3-0324": { + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 1.5e-06, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 7.2e-07, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false, - "supports_native_streaming": true, - "supports_vision": true + "source": "https://nebius.com/prices" }, - "oci/meta.llama-4-scout-17b-16e-instruct": { - "input_cost_per_token": 7.2e-07, - "litellm_provider": "oci", - "max_input_tokens": 10485760, - "max_output_tokens": 8192, - "max_tokens": 8192, + "nebius/google/gemma-3-27b-it": { + "max_input_tokens": 110000, + "max_output_tokens": 110000, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 7.2e-07, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false, - "supports_native_streaming": true + "supports_vision": true, + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 4e-08 }, - "oci/xai.grok-3": { - "input_cost_per_token": 3e-06, - "litellm_provider": "oci", + "nebius/meta-llama/Llama-3.3-70B-Instruct": { "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false, - "supports_native_streaming": true + "source": "https://nebius.com/prices" }, - "oci/xai.grok-3-fast": { - "input_cost_per_token": 5e-06, - "litellm_provider": "oci", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "nebius/meta-llama/Llama-Guard-3-8B": { + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 2e-08, + "output_cost_per_token": 6e-08, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 2.5e-05, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", - "supports_function_calling": true, - "supports_response_schema": false, - "supports_native_streaming": true + "source": "https://nebius.com/prices" }, - "oci/xai.grok-3-mini": { - "input_cost_per_token": 3e-07, - "litellm_provider": "oci", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "nebius/meta-llama/Meta-Llama-3.1-8B-Instruct": { + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 2e-08, + "output_cost_per_token": 6e-08, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 5e-07, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false, - "supports_native_streaming": true + "source": "https://nebius.com/prices" }, - "oci/xai.grok-3-mini-fast": { - "input_cost_per_token": 6e-07, - "litellm_provider": "oci", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "nebius/meta-llama/Meta-Llama-3.1-70B-Instruct": { + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 4e-06, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false, - "supports_native_streaming": true + "source": "https://nebius.com/prices" }, - "oci/xai.grok-4": { - "input_cost_per_token": 3e-06, - "litellm_provider": "oci", + "nebius/meta-llama/Meta-Llama-3.1-405B-Instruct": { "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 3e-06, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false, - "supports_native_streaming": true + "source": "https://nebius.com/prices" }, - "oci/cohere.command-latest": { - "input_cost_per_token": 1.56e-06, - "litellm_provider": "oci", + "nebius/mistralai/Mistral-Nemo-Instruct-2407": { "max_input_tokens": 128000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "max_output_tokens": 128000, + "input_cost_per_token": 4e-08, + "output_cost_per_token": 1.2e-07, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 1.56e-06, - "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", "supports_function_calling": true, - "supports_response_schema": false, - "supports_native_streaming": true + "source": "https://nebius.com/prices" }, - "oci/cohere.command-a-03-2025": { - "input_cost_per_token": 1.56e-06, - "litellm_provider": "oci", - "max_input_tokens": 256000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "nebius/NousResearch/Hermes-3-Llama-3.1-405B": { + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 3e-06, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 1.56e-06, - "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", "supports_function_calling": true, - "supports_response_schema": false, - "supports_native_streaming": true + "source": "https://nebius.com/prices" }, - "oci/cohere.command-plus-latest": { - "input_cost_per_token": 1.56e-06, - "litellm_provider": "oci", + "nebius/nvidia/Llama-3.1-Nemotron-Ultra-253B-v1": { "max_input_tokens": 128000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "max_output_tokens": 128000, + "input_cost_per_token": 6e-07, + "output_cost_per_token": 1.8e-06, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 1.56e-06, - "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", "supports_function_calling": true, - "supports_response_schema": false, - "supports_native_streaming": true + "source": "https://nebius.com/prices" }, - "oci/google.gemini-2.5-flash": { - "input_cost_per_token": 1.5e-07, - "litellm_provider": "oci", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "nebius/nvidia/Llama-3.3-Nemotron-Super-49B-v1": { + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "nebius", "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices" + }, + "nebius/Qwen/Qwen3-235B-A22B": { + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 2e-07, "output_cost_per_token": 6e-07, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices" + }, + "nebius/Qwen/Qwen3-32B": { + "max_input_tokens": 40960, + "max_output_tokens": 40960, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-32B" + }, + "nebius/Qwen/Qwen3-30B-A3B": { + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices" + }, + "nebius/Qwen/Qwen3-14B": { + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 8e-08, + "output_cost_per_token": 2.4e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices" + }, + "nebius/Qwen/Qwen3-4B": { + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 8e-08, + "output_cost_per_token": 2.4e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices" + }, + "nebius/Qwen/QwQ-32B": { + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 4.5e-07, + "litellm_provider": "nebius", + "mode": "chat", "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_native_streaming": true, - "supports_image_size": false, "supports_reasoning": true, - "supports_system_messages": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "supports_video_input": true + "source": "https://nebius.com/prices" }, - "oci/google.gemini-2.5-pro": { - "input_cost_per_token": 1.25e-06, - "litellm_provider": "oci", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "nebius/Qwen/Qwen2.5-72B-Instruct": { + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices" + }, + "nebius/Qwen/Qwen2.5-32B-Instruct": { + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 2e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices" + }, + "nebius/Qwen/Qwen2.5-Coder-7B": { + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 1e-08, + "output_cost_per_token": 3e-08, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices" + }, + "nebius/Qwen/Qwen2.5-VL-72B-Instruct": { + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 7.5e-07, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": true, "supports_vision": true, - "supports_native_streaming": true, - "supports_reasoning": true, - "supports_system_messages": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "supports_video_input": true + "source": "https://tokenfactory.nebius.com/models/catalog/image2text/Qwen%2FQwen2.5-VL-72B-Instruct" }, - "oci/google.gemini-2.5-flash-lite": { - "input_cost_per_token": 7.5e-08, - "litellm_provider": "oci", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "nebius/Qwen/Qwen2-VL-72B-Instruct": { + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": true, "supports_vision": true, - "supports_native_streaming": true, - "supports_image_size": false, - "supports_reasoning": false, - "supports_system_messages": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "supports_video_input": true + "source": "https://nebius.com/prices" }, - "oci/cohere.command-a-vision": { - "input_cost_per_token": 1.56e-06, - "litellm_provider": "oci", - "max_input_tokens": 256000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "nebius/Qwen/Qwen2-VL-7B-Instruct": { + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-08, + "output_cost_per_token": 6e-08, + "litellm_provider": "nebius", + "mode": "chat", + "supports_vision": true, + "source": "https://nebius.com/prices" + }, + "nebius/deepseek-ai/DeepSeek-V4-Flash": { + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 2.8e-07, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 1.56e-06, - "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", "supports_function_calling": true, - "supports_response_schema": false, - "supports_native_streaming": true, - "supports_vision": true + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Flash" }, - "oci/cohere.command-a-reasoning": { - "input_cost_per_token": 1.56e-06, - "litellm_provider": "oci", - "max_input_tokens": 256000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "nebius/deepseek-ai/DeepSeek-V4-Flash-0731": { + "max_input_tokens": 1048576, + "max_output_tokens": 1024000, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 2.8e-07, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 1.56e-06, - "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", - "supports_function_calling": false, - "supports_response_schema": false, - "supports_native_streaming": true + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 1e-08 }, - "oci/cohere.embed-multilingual-image-v3.0": { - "input_cost_per_token": 1e-07, - "litellm_provider": "oci", - "max_input_tokens": 512, - "mode": "embedding", - "output_vector_size": 1024, - "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", - "supports_vision": true + "nebius/deepseek-ai/DeepSeek-V4-Pro": { + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 1.75e-06, + "output_cost_per_token": 3.5e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 1.4e-07 }, - "oci/cohere.command-a-reasoning-08-2025": { - "input_cost_per_token": 1.56e-06, - "litellm_provider": "oci", - "max_input_tokens": 256000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "nebius/deepseek-ai/DeepSeek-V4-Pro-0813": { + "input_cost_per_token": 1.32e-06, + "litellm_provider": "nebius", + "max_input_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 1.56e-06, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "output_cost_per_token": 3.96e-06, + "source": "https://tokenfactory.nebius.com/api/public/models_info", "supports_function_calling": true, - "supports_response_schema": false + "supports_reasoning": true, + "cache_read_input_token_cost": 4e-08 }, - "oci/cohere.command-a-vision-07-2025": { - "input_cost_per_token": 1.56e-06, - "litellm_provider": "oci", - "max_input_tokens": 128000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "nebius/deepseek-ai/DeepSeek-V4.1-Flash": { + "input_cost_per_token": 3e-07, + "litellm_provider": "nebius", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, "mode": "chat", - "output_cost_per_token": 1.56e-06, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "output_cost_per_token": 1.2e-06, + "source": "https://tokenfactory.nebius.com/api/public/models_info", "supports_function_calling": true, - "supports_response_schema": false, - "supports_vision": true + "supports_reasoning": true, + "supports_vision": true, + "cache_read_input_token_cost": 1e-08 }, - "oci/cohere.command-a-translate-08-2025": { - "input_cost_per_token": 9e-08, - "litellm_provider": "oci", - "max_input_tokens": 256000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "nebius/MiniMaxAI/MiniMax-M2.5": { + "max_input_tokens": 196608, + "max_output_tokens": 196608, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 9e-08, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", - "supports_function_calling": false, - "supports_response_schema": false + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/MiniMaxAI%2FMiniMax-M2.5" }, - "oci/cohere.command-r-08-2024": { - "input_cost_per_token": 1.5e-07, - "litellm_provider": "oci", - "max_input_tokens": 128000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "nebius/MiniMaxAI/MiniMax-M3": { + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 1.5e-07, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false + "supports_reasoning": true, + "supports_vision": true, + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 6e-08 }, - "oci/cohere.command-r-plus-08-2024": { - "input_cost_per_token": 1.56e-06, - "litellm_provider": "oci", - "max_input_tokens": 128000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "nebius/moonshotai/Kimi-K2.6": { + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 9.5e-07, + "output_cost_per_token": 4e-06, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 1.56e-06, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false + "supports_reasoning": true, + "supports_vision": true, + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 1.6e-07 }, - "oci/meta.llama-3.2-11b-vision-instruct": { + "nebius/moonshotai/Kimi-K2.7-Code": { + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 9.5e-07, + "output_cost_per_token": 4e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 1.5e-07 + }, + "nebius/moonshotai/Kimi-K3.1-Pro": { "input_cost_per_token": 2e-06, - "litellm_provider": "oci", - "max_input_tokens": 128000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 2e-07, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false, - "supports_vision": true + "supports_reasoning": true, + "supports_vision": true, + "supports_prompt_caching": true, + "source": "https://tokenfactory.nebius.com/api/public/models_info" }, - "oci/meta.llama-3.3-70b-instruct-fp8-dynamic": { - "input_cost_per_token": 7.2e-07, - "litellm_provider": "oci", - "max_input_tokens": 128000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "nebius/moonshotai/Kimi-K3": { + "max_input_tokens": 1048576, + "max_output_tokens": 1024000, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 7.2e-07, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false + "supports_reasoning": true, + "supports_vision": true, + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 3e-07 }, - "oci/xai.grok-4-fast": { - "input_cost_per_token": 5e-06, - "litellm_provider": "oci", + "nebius/NousResearch/Hermes-4-405B": { "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 3e-06, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 2.5e-05, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 2e-07 }, - "oci/xai.grok-4.1-fast": { - "input_cost_per_token": 5e-06, - "litellm_provider": "oci", + "nebius/NousResearch/Hermes-4-70B": { "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 2.5e-05, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/NousResearch%2FHermes-4-70B" }, - "oci/xai.grok-4.20": { - "input_cost_per_token": 3e-06, - "litellm_provider": "oci", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "nebius/nvidia/Cosmos3-Super-Reasoner": { + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false + "supports_reasoning": true, + "supports_vision": true, + "source": "https://tokenfactory.nebius.com/models/catalog/image2text/nvidia%2FCosmos3-Super-Reasoner" }, - "oci/xai.grok-4.20-multi-agent": { - "input_cost_per_token": 3e-06, - "litellm_provider": "oci", + "nebius/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1": { "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, + "input_cost_per_token": 6e-07, + "output_cost_per_token": 1.8e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FLlama-3_1-Nemotron-Ultra-253B-v1" + }, + "nebius/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B": { + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 2.4e-07, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 1.2e-08 }, - "oci/xai.grok-code-fast-1": { - "input_cost_per_token": 5e-06, - "litellm_provider": "oci", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "nebius/nvidia/Nemotron-3-Nano-Omni": { + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 2.4e-07, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 2.5e-05, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false + "supports_reasoning": true, + "supports_vision": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNemotron-3-Nano-Omni" }, - "oci/openai.gpt-5": { - "input_cost_per_token": 1.25e-06, - "litellm_provider": "oci", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "nebius/nvidia/nemotron-3-super-120b-a12b": { + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 9e-07, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_native_streaming": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 6e-08 }, - "oci/openai.gpt-5-mini": { - "input_cost_per_token": 2.5e-07, - "litellm_provider": "oci", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "nebius/nvidia/Nemotron-3-Ultra-550b-a55b": { + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 3e-06, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_native_streaming": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 1.2e-07 }, - "oci/openai.gpt-5-nano": { - "input_cost_per_token": 5e-08, - "litellm_provider": "oci", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "nebius/nvidia/Nemotron-3_5-Lightning": { + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 2.4e-07, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 4e-07, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_native_streaming": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 3e-08 }, - "oci/cohere.embed-english-v3.0": { - "input_cost_per_token": 1e-07, - "litellm_provider": "oci", - "max_input_tokens": 512, - "max_tokens": 512, - "mode": "embedding", - "output_cost_per_token": 0.0, - "output_vector_size": 1024, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" + "nebius/openai/gpt-oss-120b": { + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 1e-07 }, - "oci/cohere.embed-english-light-v3.0": { - "input_cost_per_token": 1e-07, - "litellm_provider": "oci", - "max_input_tokens": 512, - "max_tokens": 512, - "mode": "embedding", - "output_cost_per_token": 0.0, - "output_vector_size": 384, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" - }, - "oci/cohere.embed-multilingual-v3.0": { - "input_cost_per_token": 1e-07, - "litellm_provider": "oci", - "max_input_tokens": 512, - "max_tokens": 512, - "mode": "embedding", - "output_cost_per_token": 0.0, - "output_vector_size": 1024, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" - }, - "oci/cohere.embed-multilingual-light-v3.0": { - "input_cost_per_token": 1e-07, - "litellm_provider": "oci", - "max_input_tokens": 512, - "max_tokens": 512, - "mode": "embedding", - "output_cost_per_token": 0.0, - "output_vector_size": 384, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" - }, - "oci/cohere.embed-english-image-v3.0": { - "input_cost_per_token": 1e-07, - "litellm_provider": "oci", - "max_input_tokens": 512, - "max_tokens": 512, - "mode": "embedding", - "output_cost_per_token": 0.0, - "output_vector_size": 1024, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", - "supports_embedding_image_input": true - }, - "oci/cohere.embed-english-light-image-v3.0": { - "input_cost_per_token": 1e-07, - "litellm_provider": "oci", - "max_input_tokens": 512, - "max_tokens": 512, - "mode": "embedding", - "output_cost_per_token": 0.0, - "output_vector_size": 384, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", - "supports_embedding_image_input": true - }, - "oci/cohere.embed-multilingual-light-image-v3.0": { - "input_cost_per_token": 1e-07, - "litellm_provider": "oci", - "max_input_tokens": 512, - "max_tokens": 512, - "mode": "embedding", - "output_cost_per_token": 0.0, - "output_vector_size": 384, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", - "supports_embedding_image_input": true - }, - "oci/cohere.embed-v4.0": { - "input_cost_per_token": 1.2e-07, - "litellm_provider": "oci", - "max_input_tokens": 128000, - "max_tokens": 128000, - "mode": "embedding", - "output_cost_per_token": 0.0, - "output_vector_size": 1536, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", - "supports_embedding_image_input": true - }, - "ollama/codegeex4": { - "input_cost_per_token": 0.0, - "litellm_provider": "ollama", - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.0, - "supports_function_calling": false - }, - "ollama/codegemma": { - "input_cost_per_token": 0.0, - "litellm_provider": "ollama", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "completion", - "output_cost_per_token": 0.0 - }, - "ollama/codellama": { - "input_cost_per_token": 0.0, - "litellm_provider": "ollama", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "completion", - "output_cost_per_token": 0.0 - }, - "ollama/deepseek-coder-v2-base": { - "input_cost_per_token": 0.0, - "litellm_provider": "ollama", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "completion", - "output_cost_per_token": 0.0, - "supports_function_calling": true - }, - "ollama/deepseek-coder-v2-instruct": { - "input_cost_per_token": 0.0, - "litellm_provider": "ollama", - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.0, - "supports_function_calling": true - }, - "ollama/deepseek-coder-v2-lite-base": { - "input_cost_per_token": 0.0, - "litellm_provider": "ollama", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "completion", - "output_cost_per_token": 0.0, - "supports_function_calling": true - }, - "ollama/deepseek-coder-v2-lite-instruct": { - "input_cost_per_token": 0.0, - "litellm_provider": "ollama", - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.0, - "supports_function_calling": true - }, - "ollama/deepseek-v3.1:671b-cloud": { - "input_cost_per_token": 0.0, - "litellm_provider": "ollama", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, - "mode": "chat", - "output_cost_per_token": 0.0, - "supports_function_calling": true - }, - "ollama/gpt-oss:120b-cloud": { - "input_cost_per_token": 0.0, - "litellm_provider": "ollama", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 0.0, - "supports_function_calling": true - }, - "ollama/gpt-oss:20b-cloud": { - "input_cost_per_token": 0.0, - "litellm_provider": "ollama", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 0.0, - "supports_function_calling": true - }, - "ollama/internlm2_5-20b-chat": { - "input_cost_per_token": 0.0, - "litellm_provider": "ollama", - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "max_tokens": 8192, + "nebius/openbmb/MiniCPM-V-4_5": { + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "input_cost_per_token": 6.58e-07, + "output_cost_per_token": 1.11e-06, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 0.0, - "supports_function_calling": true + "supports_vision": true, + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 1.3e-07 }, - "ollama/llama2": { - "input_cost_per_token": 0.0, - "litellm_provider": "ollama", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "nebius/Qwen/Qwen3-235B-A22B-Instruct-2507": { + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 0.0 - }, - "ollama/llama2-uncensored": { - "input_cost_per_token": 0.0, - "litellm_provider": "ollama", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "completion", - "output_cost_per_token": 0.0 + "supports_function_calling": true, + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 5e-08 }, - "ollama/llama2:13b": { - "input_cost_per_token": 0.0, - "litellm_provider": "ollama", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "nebius/Qwen/Qwen3-30B-A3B-Instruct-2507": { + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 0.0 + "supports_function_calling": true, + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 1e-07 }, - "ollama/llama2:70b": { - "input_cost_per_token": 0.0, - "litellm_provider": "ollama", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "nebius/Qwen/Qwen3-Next-80B-A3B-Thinking": { + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 0.0 + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-Next-80B-A3B-Thinking" }, - "ollama/llama2:7b": { - "input_cost_per_token": 0.0, - "litellm_provider": "ollama", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "nebius/Qwen/Qwen3.5-397B-A17B": { + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 6e-07, + "output_cost_per_token": 3.6e-06, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 0.0 + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 1.2e-07 }, - "ollama/llama3": { - "input_cost_per_token": 0.0, - "litellm_provider": "ollama", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "nebius/Qwen/Qwen3.8-27B": { + "input_cost_per_token": 4.5e-07, + "litellm_provider": "nebius", + "max_input_tokens": 262144, "mode": "chat", - "output_cost_per_token": 0.0 + "output_cost_per_token": 3e-06, + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "supports_function_calling": true, + "supports_reasoning": true, + "cache_read_input_token_cost": 1e-07 }, - "ollama/llama3.1": { - "input_cost_per_token": 0.0, - "litellm_provider": "ollama", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "nebius/zai-org/GLM-5.1": { + "max_input_tokens": 202752, + "max_output_tokens": 202752, + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 0.0, - "supports_function_calling": true + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 2.6e-07 }, - "ollama/llama3:70b": { - "input_cost_per_token": 0.0, - "litellm_provider": "ollama", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "nebius/zai-org/GLM-5.2": { + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 0.0 + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 1.4e-07 }, - "ollama/llama3:8b": { - "input_cost_per_token": 0.0, - "litellm_provider": "ollama", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "nebius/zai-org/GLM-5.3": { + "input_cost_per_token": 1.4e-06, + "litellm_provider": "nebius", + "max_input_tokens": 1048576, + "max_output_tokens": 1024000, "mode": "chat", - "output_cost_per_token": 0.0 - }, - "ollama/mistral": { - "input_cost_per_token": 0.0, - "litellm_provider": "ollama", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "completion", - "output_cost_per_token": 0.0, - "supports_function_calling": true + "output_cost_per_token": 4.4e-06, + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "supports_function_calling": true, + "supports_reasoning": true, + "cache_read_input_token_cost": 2.6e-07 }, - "ollama/mistral-7B-Instruct-v0.1": { - "input_cost_per_token": 0.0, - "litellm_provider": "ollama", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "nebius/zai-org/GLM-5.3-Flash": { + "max_input_tokens": 1048576, + "max_output_tokens": 1024000, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 5e-07, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 0.0, - "supports_function_calling": true + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "supports_vision": true, + "cache_read_input_token_cost": 3e-08 }, - "ollama/mistral-7B-Instruct-v0.2": { - "input_cost_per_token": 0.0, - "litellm_provider": "ollama", + "nebius/BAAI/bge-en-icl": { "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 0.0, - "supports_function_calling": true - }, - "ollama/mistral-large-instruct-2407": { - "input_cost_per_token": 0.0, - "litellm_provider": "ollama", - "max_input_tokens": 65536, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", + "input_cost_per_token": 1e-08, "output_cost_per_token": 0.0, - "supports_function_calling": true + "litellm_provider": "nebius", + "mode": "embedding", + "source": "https://nebius.com/prices" }, - "ollama/mixtral-8x22B-Instruct-v0.1": { - "input_cost_per_token": 0.0, - "litellm_provider": "ollama", - "max_input_tokens": 65536, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", + "nebius/BAAI/bge-multilingual-gemma2": { + "max_input_tokens": 8192, + "input_cost_per_token": 1e-08, "output_cost_per_token": 0.0, - "supports_function_calling": true + "litellm_provider": "nebius", + "mode": "embedding", + "source": "https://nebius.com/prices" }, - "ollama/mixtral-8x7B-Instruct-v0.1": { - "input_cost_per_token": 0.0, - "litellm_provider": "ollama", + "nebius/intfloat/e5-mistral-7b-instruct": { "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", + "input_cost_per_token": 1e-08, "output_cost_per_token": 0.0, - "supports_function_calling": true - }, - "ollama/orca-mini": { - "input_cost_per_token": 0.0, - "litellm_provider": "ollama", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "completion", - "output_cost_per_token": 0.0 + "litellm_provider": "nebius", + "mode": "embedding", + "source": "https://nebius.com/prices" }, - "ollama/qwen3-coder:480b-cloud": { - "input_cost_per_token": 0.0, - "litellm_provider": "ollama", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", + "nebius/Qwen/Qwen3-Embedding-8B": { + "max_input_tokens": 40960, + "input_cost_per_token": 1e-08, "output_cost_per_token": 0.0, - "supports_function_calling": true - }, - "ollama/vicuna": { - "input_cost_per_token": 0.0, - "litellm_provider": "ollama", - "max_input_tokens": 2048, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "completion", - "output_cost_per_token": 0.0 - }, - "omni-moderation-2024-09-26": { - "input_cost_per_token": 0.0, - "litellm_provider": "openai", - "max_input_tokens": 32768, - "max_output_tokens": 0, - "max_tokens": 0, - "mode": "moderation", - "output_cost_per_token": 0.0 - }, - "omni-moderation-latest": { - "input_cost_per_token": 0.0, - "litellm_provider": "openai", - "max_input_tokens": 32768, - "max_output_tokens": 0, - "max_tokens": 0, - "mode": "moderation", - "output_cost_per_token": 0.0 + "litellm_provider": "nebius", + "mode": "embedding", + "source": "https://tokenfactory.nebius.com/models/catalog/embedding/Qwen%2FQwen3-Embedding-8B" }, - "openai.gpt-oss-120b-1:0": { - "input_cost_per_token": 1.5e-07, + "nvidia.nemotron-nano-12b-v2": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "input_cost_per_token": 2e-07, + "input_cost_per_token_batches": 1e-07, + "input_cost_per_token_flex": 1e-07, + "input_cost_per_token_priority": 3.5e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_flex": 3e-07, + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supports_audio_input": false, "supports_function_calling": true, - "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_system_messages": true, + "supports_vision": true }, - "openai.gpt-oss-20b-1:0": { - "input_cost_per_token": 7e-08, + "nvidia.nemotron-nano-9b-v2": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "input_cost_per_token": 6e-08, + "input_cost_per_token_batches": 3e-08, + "input_cost_per_token_flex": 3e-08, + "input_cost_per_token_priority": 1.1e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 8000, "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token": 2.3e-07, + "output_cost_per_token_batches": 1.2e-07, + "output_cost_per_token_flex": 1.2e-07, + "output_cost_per_token_priority": 4e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supports_audio_input": false, "supports_function_calling": true, - "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_system_messages": true, + "supports_vision": false }, - "openai.gpt-oss-safeguard-120b": { - "input_cost_per_token": 1.5e-07, + "nvidia.nemotron-nano-3-30b": { + "input_cost_per_token": 6e-08, + "input_cost_per_token_batches": 3e-08, + "input_cost_per_token_flex": 3e-08, + "input_cost_per_token_priority": 1.1e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 16000, - "max_tokens": 16000, + "max_input_tokens": 256000, + "max_output_tokens": 8000, "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", - "supports_audio_input": false, + "output_cost_per_token": 2.4e-07, + "output_cost_per_token_batches": 1.2e-07, + "output_cost_per_token_flex": 1.2e-07, + "output_cost_per_token_priority": 4.2e-07, "supports_function_calling": true, - "supports_response_schema": true, "supports_system_messages": true, + "supports_tool_choice": true, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supports_audio_input": false, + "supports_native_structured_output": true, + "supports_response_schema": true, "supports_vision": false }, - "openai.gpt-oss-safeguard-20b": { - "input_cost_per_token": 7e-08, + "nvidia.nemotron-super-3-120b": { + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "input_cost_per_token_flex": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 16000, - "max_tokens": 16000, + "max_input_tokens": 256000, + "max_output_tokens": 32000, "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token": 6.5e-07, + "output_cost_per_token_batches": 3.25e-07, + "output_cost_per_token_flex": 3.25e-07, + "output_cost_per_token_priority": 1.1375e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, - "supports_vision": false - }, - "openrouter/anthropic/claude-3-haiku": { - "cache_creation_input_token_cost": 3e-07, - "cache_creation_input_token_cost_above_1hr": 5e-07, - "cache_read_input_token_cost": 3e-08, - "input_cost_per_image": 0.0004, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "openrouter", - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "supports_function_calling": true, "supports_tool_choice": true, - "supports_vision": true, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_web_search": true + "supports_vision": false }, - "openrouter/anthropic/claude-3.5-sonnet": { - "input_cost_per_token": 3e-06, - "litellm_provider": "openrouter", + "o1": { + "cache_read_input_token_cost": 7.5e-06, + "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", + "input_cost_per_token": 1.5e-05, + "input_cost_per_token_batches": 7.5e-06, + "litellm_provider": "openai", "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 100000, "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 6e-05, + "fedramp_uplift_multiplier": 1.1, + "output_cost_per_token_batches": 3e-05, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, - "openrouter/anthropic/claude-3.7-sonnet": { - "input_cost_per_image": 0.0048, - "input_cost_per_token": 3e-06, - "litellm_provider": "openrouter", + "o1-2024-12-17": { + "cache_read_input_token_cost": 7.5e-06, + "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", + "input_cost_per_token": 1.5e-05, + "input_cost_per_token_batches": 7.5e-06, + "litellm_provider": "openai", "max_input_tokens": 200000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 100000, "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 6e-05, + "fedramp_uplift_multiplier": 1.1, + "output_cost_per_token_batches": 3e-05, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, - "openrouter/anthropic/claude-opus-4.1": { - "input_cost_per_image": 0.0048, - "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 3e-05, - "cache_read_input_token_cost": 1.5e-06, - "input_cost_per_token": 1.5e-05, - "litellm_provider": "openrouter", + "o1-pro": { + "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", + "input_cost_per_token": 0.00015, + "input_cost_per_token_batches": 7.5e-05, + "litellm_provider": "openai", "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "max_output_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 0.0006, + "fedramp_uplift_multiplier": 1.1, + "output_cost_per_token_batches": 0.0003, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/responses", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_native_streaming": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": true, - "supports_response_schema": false, - "supports_web_search": true + "supports_vision": true }, - "openrouter/anthropic/claude-sonnet-4": { - "input_cost_per_image": 0.0048, - "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost": 3e-07, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "litellm_provider": "openrouter", + "o1-pro-2025-03-19": { + "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", + "input_cost_per_token": 0.00015, + "input_cost_per_token_batches": 7.5e-05, + "litellm_provider": "openai", "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "max_output_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 0.0006, + "fedramp_uplift_multiplier": 1.1, + "output_cost_per_token_batches": 0.0003, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/responses", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_native_streaming": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": true, - "supports_response_schema": false, - "supports_web_search": true + "supports_vision": true }, - "openrouter/anthropic/claude-sonnet-4.6": { - "supports_adaptive_thinking": true, - "supports_legacy_thinking": true, - "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost": 3e-07, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "o3": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_flex": 2.5e-07, + "cache_read_input_token_cost_priority": 8.75e-07, + "deprecation_date": "2026-12-11", + "successor_model": "gpt-5.6-sol", + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, "mode": "chat", - "output_cost_per_token": 1.5e-05, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 8e-06, + "fedramp_uplift_multiplier": 1.1, + "output_cost_per_token_batches": 4e-06, + "output_cost_per_token_flex": 4e-06, + "output_cost_per_token_priority": 1.4e-05, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "standard" + ], + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/responses", + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_max_reasoning_effort": true, + "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 1024, - "supports_audio_input": false, - "supports_pdf_input": true, - "supports_response_schema": true, "supports_web_search": true }, - "openrouter/anthropic/claude-opus-4.5": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 5e-06, - "litellm_provider": "openrouter", + "o3-deep-research": { + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_token": 1e-05, + "litellm_provider": "openai", "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 2.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, + "max_output_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 4e-05, + "fedramp_uplift_multiplier": 1.1, + "source": "https://developers.openai.com/api/docs/models/o3-deep-research", + "supported_endpoints": [ + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true, + "supports_response_schema": false, + "supports_tool_choice": false, "supports_vision": true, - "supports_output_config": true, - "prompt_cache_min_tokens": 4096, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_pdf_input": true, - "supports_response_schema": true, - "supports_web_search": true + "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol" }, - "openrouter/anthropic/claude-opus-4.6": { - "supports_adaptive_thinking": true, - "supports_legacy_thinking": true, - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_1hr": 1e-05, + "o3-deep-research-2025-06-26": { + "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_token": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 4e-05, + "fedramp_uplift_multiplier": 1.1, + "source": "https://developers.openai.com/api/docs/models/o3-deep-research", + "supported_endpoints": [ + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": true, + "supports_pdf_input": true + }, + "o3-2025-04-16": { "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "cache_read_input_token_cost_flex": 2.5e-07, + "cache_read_input_token_cost_priority": 8.75e-07, + "deprecation_date": "2026-12-11", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, "mode": "chat", - "output_cost_per_token": 2.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 8e-06, + "fedramp_uplift_multiplier": 1.1, + "output_cost_per_token_batches": 4e-06, + "output_cost_per_token_flex": 4e-06, + "output_cost_per_token_priority": 1.4e-05, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "standard" + ], + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/responses", + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_max_reasoning_effort": true, + "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 4096, - "supports_response_schema": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": true, "supports_web_search": true }, - "openrouter/anthropic/claude-sonnet-4.5": { - "input_cost_per_image": 0.0048, - "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "o3-mini": { + "cache_read_input_token_cost": 5.5e-07, + "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", + "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 4.4e-06, + "fedramp_uplift_multiplier": 1.1, + "output_cost_per_token_batches": 2.2e-06, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, + "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": true, "supports_response_schema": true, - "supports_web_search": true + "supports_tool_choice": true, + "supports_vision": false }, - "openrouter/anthropic/claude-haiku-4.5": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost_above_1hr": 2e-06, - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", + "o3-mini-2025-01-31": { + "cache_read_input_token_cost": 5.5e-07, + "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", + "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, + "litellm_provider": "openai", "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_output_tokens": 100000, "mode": "chat", - "output_cost_per_token": 5e-06, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 4.4e-06, + "fedramp_uplift_multiplier": 1.1, + "output_cost_per_token_batches": 2.2e-06, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, + "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 4096, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": true, "supports_response_schema": true, - "supports_web_search": true + "supports_tool_choice": true, + "supports_vision": false }, - "openrouter/anthropic/claude-opus-4.7": { - "supports_adaptive_thinking": true, - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.5e-05, - "supports_assistant_prefill": false, - "supports_computer_use": true, + "o3-pro": { + "deprecation_date": "2026-12-11", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", + "input_cost_per_token": 2e-05, + "input_cost_per_token_batches": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 8e-05, + "fedramp_uplift_multiplier": 1.1, + "output_cost_per_token_batches": 4e-05, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "pro" + ], + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/responses", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_parallel_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "prompt_cache_min_tokens": 2048, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_web_search": true }, - "openrouter/anthropic/claude-opus-5": { - "prompt_cache_min_tokens": 512, - "supports_adaptive_thinking": true, - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_assistant_prefill": false, - "supports_audio_input": false, - "supports_computer_use": true, + "o3-pro-2025-06-10": { + "deprecation_date": "2026-12-11", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", + "input_cost_per_token": 2e-05, + "input_cost_per_token_batches": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 8e-05, + "fedramp_uplift_multiplier": 1.1, + "output_cost_per_token_batches": 4e-05, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "pro" + ], + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/responses", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_parallel_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "supports_xhigh_reasoning_effort": true + "supports_web_search": true }, - "openrouter/anthropic/claude-opus-5.5": { - "cache_creation_input_token_cost": 5e-06, - "cache_creation_input_token_cost_above_1hr": 8e-06, - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "o4-mini": { + "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost_flex": 1.38e-07, + "cache_read_input_token_cost_priority": 5e-07, + "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", + "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, + "input_cost_per_token_flex": 5.5e-07, + "input_cost_per_token_priority": 2e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, "mode": "chat", - "output_cost_per_token": 2e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 4.4e-06, + "fedramp_uplift_multiplier": 1.1, + "output_cost_per_token_batches": 2.2e-06, + "output_cost_per_token_flex": 2.2e-06, + "output_cost_per_token_priority": 8e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, + "supports_parallel_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -41990,2157 +46427,1259 @@ "supports_vision": true, "supports_web_search": true }, - "openrouter/bytedance/ui-tars-1.5-7b": { - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "o4-mini-deep-research": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 8e-06, + "fedramp_uplift_multiplier": 1.1, + "source": "https://developers.openai.com/api/docs/models/o4-mini-deep-research", + "supported_endpoints": [ + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": false, - "supports_pdf_input": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": false, "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, + "supports_reasoning": true, + "supports_response_schema": false, "supports_tool_choice": false, "supports_vision": true, - "supports_web_search": false + "supports_pdf_input": true, + "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol" }, - "openrouter/deepseek/deepseek-chat": { - "input_cost_per_token": 2.574e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.0287e-06, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false + "o4-mini-deep-research-2025-06-26": { + "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 8e-06, + "fedramp_uplift_multiplier": 1.1, + "source": "https://developers.openai.com/api/docs/models/o4-mini-deep-research", + "supported_endpoints": [ + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": true, + "supports_pdf_input": true }, - "openrouter/deepseek/deepseek-chat-v3-0324": { - "cache_read_input_token_cost": 1.1e-07, - "input_cost_per_token": 2.9e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 147456, - "max_tokens": 147456, + "o4-mini-2025-04-16": { + "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost_flex": 1.38e-07, + "cache_read_input_token_cost_priority": 5e-07, + "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", + "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, + "input_cost_per_token_flex": 5.5e-07, + "input_cost_per_token_priority": 2e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, "mode": "chat", - "output_cost_per_token": 1.14e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 4.4e-06, + "fedramp_uplift_multiplier": 1.1, + "output_cost_per_token_batches": 2.2e-06, + "output_cost_per_token_flex": 2.2e-06, + "output_cost_per_token_priority": 8e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_vision": true, + "supports_web_search": true }, - "openrouter/deepseek/deepseek-chat-v3.1": { - "input_cost_per_token": 2.5e-07, - "input_cost_per_token_cache_hit": 2e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 32768, - "max_tokens": 32768, + "oci/meta.llama-3.1-8b-instruct": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 4000, "mode": "chat", - "output_cost_per_token": 9.5e-07, - "supports_assistant_prefill": true, + "output_cost_per_token": 7.2e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "cache_read_input_token_cost": 1.3e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false + "supports_response_schema": false, + "supports_native_streaming": true }, - "openrouter/deepseek/deepseek-v3.2": { - "cache_read_input_token_cost": 2.8e-08, - "deprecation_date": "2026-09-28", - "input_cost_per_token": 2.8e-07, - "input_cost_per_token_cache_hit": 2.8e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 65536, - "max_tokens": 65536, + "oci/meta.llama-3.1-70b-instruct": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 4000, "mode": "chat", - "output_cost_per_token": 4.2e-07, - "supports_assistant_prefill": true, + "output_cost_per_token": 7.2e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": false, - "supports_vision": false, - "supports_web_search": false + "supports_response_schema": false, + "supports_native_streaming": true }, - "openrouter/deepseek/deepseek-v3.2-exp": { - "cache_read_input_token_cost": 2e-08, - "deprecation_date": "2026-09-28", - "input_cost_per_token": 2.7e-07, - "input_cost_per_token_cache_hit": 2e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 147456, - "max_tokens": 147456, + "oci/meta.llama-3.1-405b-instruct": { + "input_cost_per_token": 1.068e-05, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 4000, "mode": "chat", - "output_cost_per_token": 4.1e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_assistant_prefill": true, - "supports_audio_input": false, + "output_cost_per_token": 1.068e-05, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_response_schema": false, + "supports_native_streaming": true }, - "openrouter/deepseek/deepseek-r1": { - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 7e-07, - "input_cost_per_token_cache_hit": 1.4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 64000, - "max_output_tokens": 16000, - "max_tokens": 16000, + "oci/meta.llama-3.2-90b-vision-instruct": { + "input_cost_per_token": 2e-06, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 4000, "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_assistant_prefill": true, - "supports_audio_input": false, + "output_cost_per_token": 2e-06, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_response_schema": false, + "supports_native_streaming": true, + "supports_vision": true }, - "openrouter/deepseek/deepseek-r1-0528": { - "cache_read_input_token_cost": 3.5e-07, - "input_cost_per_token": 5e-07, - "input_cost_per_token_cache_hit": 1.4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 32768, - "max_tokens": 32768, + "oci/meta.llama-3.3-70b-instruct": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 4000, "mode": "chat", - "output_cost_per_token": 2.15e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_assistant_prefill": true, - "supports_audio_input": false, + "output_cost_per_token": 7.2e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_response_schema": false, + "supports_native_streaming": true }, - "openrouter/deepseek/deepseek-v4-pro": { - "cache_read_input_token_cost": 7.9025e-08, - "input_cost_per_token": 9.483e-07, - "litellm_provider": "openrouter", + "oci/meta.llama-4-maverick-17b-128e-instruct-fp8": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "oci", "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, + "max_output_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.8966e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 7.2e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_response_schema": false, + "supports_native_streaming": true, + "supports_vision": true }, - "openrouter/deepseek/deepseek-v4.1-flash": { - "cache_read_input_token_cost": 6e-09, + "oci/meta.llama-4-scout-17b-16e-instruct": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "oci", + "max_input_tokens": 10485760, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_native_streaming": true + }, + "oci/xai.grok-3": { + "input_cost_per_token": 3e-06, + "litellm_provider": "oci", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_native_streaming": true + }, + "oci/xai.grok-3-fast": { + "input_cost_per_token": 5e-06, + "litellm_provider": "oci", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_native_streaming": true + }, + "oci/xai.grok-3-mini": { "input_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, + "litellm_provider": "oci", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 5e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "supports_response_schema": false, + "supports_native_streaming": true }, - "openrouter/deepseek/deepseek-v4-pro-0813": { - "cache_read_input_token_cost": 1.72e-07, - "input_cost_per_token": 2.4298e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, + "oci/xai.grok-3-mini-fast": { + "input_cost_per_token": 6e-07, + "litellm_provider": "oci", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 4.2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 4e-06, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_response_schema": false, + "supports_native_streaming": true }, - "openrouter/fireworks/ember-1": { + "oci/xai.grok-4": { "input_cost_per_token": 3e-06, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "mode": "chat", "output_cost_per_token": 1.5e-05, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_native_streaming": true + }, + "oci/cohere.command-latest": { + "input_cost_per_token": 1.56e-06, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 4000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1.56e-06, + "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_parallel_function_calling": false, - "supports_pdf_input": false, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false + "supports_response_schema": false, + "supports_native_streaming": true }, - "openrouter/google/gemini-2.5-flash": { - "cache_creation_input_token_cost": 8.33333333333333e-08, - "cache_read_input_audio_token_cost": 1e-07, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 3e-07, - "litellm_provider": "openrouter", + "oci/cohere.command-a-03-2025": { + "input_cost_per_token": 1.56e-06, + "litellm_provider": "oci", + "max_input_tokens": 256000, + "max_output_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 1.56e-06, + "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_native_streaming": true + }, + "oci/cohere.command-plus-latest": { + "input_cost_per_token": 1.56e-06, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 1.56e-06, + "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_native_streaming": true + }, + "oci/google.gemini-2.5-flash": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "oci", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, "mode": "chat", - "output_cost_per_token": 2.5e-06, - "supports_audio_output": false, + "output_cost_per_token": 6e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, "supports_vision": true, + "supports_native_streaming": true, "supports_image_size": false, - "cache_read_input_token_cost": 3e-08, - "deprecation_date": "2026-10-20", - "supports_prompt_caching": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_pdf_input": true, "supports_reasoning": true, - "supports_web_search": true, + "supports_system_messages": true, + "supports_pdf_input": true, + "supports_audio_input": true, "supports_video_input": true }, - "openrouter/google/gemini-2.5-pro": { - "cache_creation_input_token_cost": 3.75e-07, - "cache_read_input_audio_token_cost": 1.25e-07, - "input_cost_per_audio_token": 1.25e-06, + "oci/google.gemini-2.5-pro": { "input_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", + "litellm_provider": "oci", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1e-05, - "supports_audio_output": false, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, "supports_vision": true, - "cache_read_input_token_cost": 1.25e-07, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, - "deprecation_date": "2026-10-20", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 1.5e-05, - "supports_prompt_caching": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_pdf_input": true, - "supports_reasoning": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-3-pro-preview": { - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_200k_tokens": 4e-06, - "input_cost_per_token_batches": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_token": 1.2e-05, - "output_cost_per_token_above_200k_tokens": 1.8e-05, - "output_cost_per_token_batches": 6e-06, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_native_streaming": true, "supports_reasoning": true, - "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true + "supports_pdf_input": true, + "supports_audio_input": true, + "supports_video_input": true }, - "openrouter/google/gemini-3-flash-preview": { - "cache_creation_input_token_cost": 8.33333333333333e-08, - "cache_read_input_audio_token_cost": 1e-07, - "cache_read_input_token_cost": 5e-08, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 5e-07, - "litellm_provider": "openrouter", + "oci/google.gemini-2.5-flash-lite": { + "input_cost_per_token": 7.5e-08, + "litellm_provider": "oci", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", - "output_cost_per_reasoning_token": 3e-06, - "output_cost_per_token": 3e-06, - "rpm": 2000, - "source": "https://openrouter.ai/api/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_audio_output": false, + "output_cost_per_token": 3e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, "supports_vision": true, - "supports_web_search": true, - "tpm": 800000, + "supports_native_streaming": true, + "supports_image_size": false, + "supports_reasoning": false, + "supports_system_messages": true, + "supports_pdf_input": true, + "supports_audio_input": true, "supports_video_input": true }, - "openrouter/google/gemini-3.1-flash-lite-preview": { - "cache_creation_input_token_cost": 8.33333333333333e-08, - "cache_read_input_audio_token_cost": 5e-08, - "cache_read_input_token_cost": 2.5e-08, - "input_cost_per_audio_token": 5e-07, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "oci/cohere.command-a-vision": { + "input_cost_per_token": 1.56e-06, + "litellm_provider": "oci", + "max_input_tokens": 256000, + "max_output_tokens": 8192, "mode": "chat", - "output_cost_per_reasoning_token": 1.5e-06, - "output_cost_per_token": 1.5e-06, - "rpm": 2000, - "source": "https://openrouter.ai/api/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_audio_output": false, + "output_cost_per_token": 1.56e-06, + "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 800000 + "supports_response_schema": false, + "supports_native_streaming": true, + "supports_vision": true }, - "openrouter/google/gemini-3.1-flash-lite": { - "cache_creation_input_token_cost": 8.33333333333333e-08, - "cache_read_input_audio_token_cost": 5e-08, - "cache_read_input_token_cost": 2.5e-08, - "input_cost_per_audio_token": 5e-07, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "oci/cohere.command-a-reasoning": { + "input_cost_per_token": 1.56e-06, + "litellm_provider": "oci", + "max_input_tokens": 256000, + "max_output_tokens": 8192, "mode": "chat", - "output_cost_per_reasoning_token": 1.5e-06, - "output_cost_per_token": 1.5e-06, - "rpm": 2000, - "source": "https://openrouter.ai/api/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 800000 + "output_cost_per_token": 1.56e-06, + "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", + "supports_function_calling": false, + "supports_response_schema": false, + "supports_native_streaming": true }, - "openrouter/google/gemini-3.1-pro-preview": { - "cache_creation_input_token_cost": 3.75e-07, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, - "cache_read_input_audio_token_cost": 2e-07, - "input_cost_per_audio_token": 2e-06, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_200k_tokens": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "oci/cohere.embed-multilingual-image-v3.0": { + "input_cost_per_token": 1e-07, + "litellm_provider": "oci", + "max_input_tokens": 512, + "mode": "embedding", + "output_vector_size": 1024, + "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", + "supports_embedding_image_input": true, + "supports_vision": true + }, + "oci/cohere.command-a-reasoning-08-2025": { + "input_cost_per_token": 1.56e-06, + "litellm_provider": "oci", + "max_input_tokens": 256000, + "max_output_tokens": 4000, "mode": "chat", - "output_cost_per_token": 1.2e-05, - "output_cost_per_token_above_200k_tokens": 1.8e-05, - "source": "https://openrouter.ai/api/v1/models", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, + "output_cost_per_token": 1.56e-06, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true + "supports_response_schema": false }, - "openrouter/gryphe/mythomax-l2-13b": { - "input_cost_per_token": 8e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 8192, - "max_output_tokens": 3686, - "max_tokens": 3686, + "oci/cohere.command-a-vision-07-2025": { + "input_cost_per_token": 1.56e-06, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 4000, "mode": "chat", - "output_cost_per_token": 1.1e-07, - "supports_tool_choice": false, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false + "output_cost_per_token": 1.56e-06, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_vision": true }, - "openrouter/mancer/weaver": { - "input_cost_per_token": 4e-07, - "litellm_provider": "openrouter", - "max_tokens": 6000, + "oci/cohere.command-a-translate-08-2025": { + "input_cost_per_token": 9e-08, + "litellm_provider": "oci", + "max_input_tokens": 256000, + "max_output_tokens": 4000, "mode": "chat", - "output_cost_per_token": 7.5e-07, - "supports_tool_choice": false, - "max_input_tokens": 8000, - "max_output_tokens": 6000, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 9e-08, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false + "supports_response_schema": false }, - "openrouter/meta-llama/llama-3-70b-instruct": { - "input_cost_per_token": 5.9e-07, - "litellm_provider": "openrouter", - "max_tokens": 8000, + "oci/cohere.command-r-08-2024": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 4000, "mode": "chat", - "output_cost_per_token": 7.9e-07, - "supports_tool_choice": true, - "max_input_tokens": 8192, - "max_output_tokens": 8000 + "output_cost_per_token": 1.5e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false }, - "openrouter/minimax/minimax-m2": { - "input_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 204800, - "max_output_tokens": 176947, - "max_tokens": 176947, + "oci/cohere.command-r-plus-08-2024": { + "input_cost_per_token": 1.56e-06, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 4000, "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1.56e-06, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_response_schema": false }, - "openrouter/mistralai/devstral-2512": { - "cache_read_input_token_cost": 4e-08, - "input_cost_per_image": 0, - "input_cost_per_token": 4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, + "oci/meta.llama-3.2-11b-vision-instruct": { + "input_cost_per_token": 2e-06, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 4000, "mode": "chat", "output_cost_per_token": 2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_response_schema": false, + "supports_vision": true }, - "openrouter/mistralai/ministral-3b-2512": { - "cache_read_input_token_cost": 1e-08, - "input_cost_per_image": 0, - "input_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 104857, - "max_tokens": 104857, + "oci/meta.llama-3.3-70b-instruct-fp8-dynamic": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 4000, "mode": "chat", - "output_cost_per_token": 1e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 7.2e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "supports_response_schema": false }, - "openrouter/mistralai/ministral-8b-2512": { - "cache_read_input_token_cost": 1.5e-08, - "input_cost_per_image": 0, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, + "oci/xai.grok-4-fast": { + "input_cost_per_token": 5e-06, + "litellm_provider": "oci", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 1.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 2.5e-05, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "supports_response_schema": false }, - "openrouter/mistralai/ministral-14b-2512": { - "cache_read_input_token_cost": 2e-08, - "input_cost_per_image": 0, - "input_cost_per_token": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, + "oci/xai.grok-4.1-fast": { + "input_cost_per_token": 5e-06, + "litellm_provider": "oci", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 2.5e-05, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "supports_response_schema": false }, - "openrouter/mistralai/mistral-7b-instruct": { - "input_cost_per_token": 1.3e-07, - "litellm_provider": "openrouter", - "max_tokens": 8191, + "oci/xai.grok-4.20": { + "input_cost_per_token": 3e-06, + "litellm_provider": "oci", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 1.3e-07, - "supports_tool_choice": true, - "max_input_tokens": 32768, - "max_output_tokens": 8191 + "output_cost_per_token": 1.5e-05, + "reasoning_effort_levels": [], + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false }, - "openrouter/mistralai/mistral-large": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 2e-06, - "litellm_provider": "openrouter", - "max_tokens": 102400, + "oci/xai.grok-4.20-multi-agent": { + "input_cost_per_token": 3e-06, + "litellm_provider": "oci", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 6e-06, - "supports_tool_choice": true, - "max_input_tokens": 128000, - "max_output_tokens": 102400, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1.5e-05, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false + "supports_response_schema": false }, - "openrouter/mistralai/mistral-small-3.1-24b-instruct": { - "input_cost_per_token": 3.51e-07, - "litellm_provider": "openrouter", - "max_tokens": 102400, + "oci/xai.grok-4.20-0309-non-reasoning": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "oci", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 5.55e-07, - "supports_tool_choice": true, - "max_input_tokens": 128000, - "max_output_tokens": 102400, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_vision": true, - "supports_web_search": false + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "reasoning_effort_levels": [], + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true }, - "openrouter/mistralai/mistral-small-3.2-24b-instruct": { - "input_cost_per_token": 9.375e-08, - "litellm_provider": "openrouter", - "max_tokens": 16384, + "oci/xai.grok-4.20-0309-reasoning": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "oci", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 2.5e-07, - "supports_tool_choice": true, - "max_input_tokens": 256000, - "max_output_tokens": 16384, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "reasoning_effort_levels": [], + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false + "supports_reasoning": true }, - "openrouter/mistralai/mixtral-8x22b-instruct": { + "oci/xai.grok-4.20-non-reasoning": { "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 2e-06, - "litellm_provider": "openrouter", - "max_tokens": 52428, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "oci", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 6e-06, - "supports_tool_choice": true, - "max_input_tokens": 65536, - "max_output_tokens": 52428, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "reasoning_effort_levels": [], + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true }, - "openrouter/moonshotai/kimi-k2.5": { - "cache_read_input_token_cost": 7e-08, - "input_cost_per_token": 4.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, + "oci/xai.grok-4.20-reasoning": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "oci", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 2.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "reasoning_effort_levels": [], + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": false + "supports_reasoning": true }, - "openrouter/nvidia/nemotron-3.5-lightning": { - "cache_read_input_token_cost": 3e-08, - "input_cost_per_token": 6e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, + "oci/xai.grok-code-fast-1": { + "input_cost_per_token": 5e-06, + "litellm_provider": "oci", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 1.6e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 2.5e-05, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_response_schema": false }, - "openrouter/openai/gpt-3.5-turbo": { - "input_cost_per_token": 5e-07, - "litellm_provider": "openrouter", - "max_tokens": 4096, + "oci/openai.gpt-5": { + "input_cost_per_token": 1.25e-06, + "litellm_provider": "oci", + "max_input_tokens": 272000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.5e-06, - "supports_tool_choice": true, - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1e-05, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, + "supports_native_streaming": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false + "supports_vision": true }, - "openrouter/openai/gpt-3.5-turbo-16k": { - "input_cost_per_token": 3e-06, - "litellm_provider": "openrouter", - "max_tokens": 4096, + "oci/openai.gpt-5-mini": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "oci", + "max_input_tokens": 272000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 4e-06, - "supports_tool_choice": true, - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 2e-06, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, + "supports_native_streaming": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false + "supports_vision": true }, - "openrouter/openai/gpt-4": { - "input_cost_per_token": 3e-05, - "litellm_provider": "openrouter", - "max_tokens": 4096, + "oci/openai.gpt-5-nano": { + "input_cost_per_token": 5e-08, + "litellm_provider": "oci", + "max_input_tokens": 272000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 6e-05, - "supports_tool_choice": true, - "max_input_tokens": 8191, - "max_output_tokens": 4096, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 4e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, + "supports_native_streaming": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false + "supports_vision": true }, - "openrouter/openai/gpt-4.1": { - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, + "oci/openai.gpt-oss-120b": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 8e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 6e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_native_streaming": true, + "supports_reasoning": true }, - "openrouter/openai/gpt-4.1-mini": { - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, + "oci/openai.gpt-oss-20b": { + "input_cost_per_token": 7e-08, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.6e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 3e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_native_streaming": true, + "supports_reasoning": true }, - "openrouter/openai/gpt-4.1-nano": { - "cache_read_input_token_cost": 2.5e-08, + "oci/cohere.embed-english-v3.0": { "input_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 4e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "litellm_provider": "oci", + "max_input_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, - "openrouter/openai/gpt-4o": { - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", + "oci/cohere.embed-english-light-v3.0": { + "input_cost_per_token": 1e-07, + "litellm_provider": "oci", + "max_input_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 384, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" + }, + "oci/cohere.embed-multilingual-v3.0": { + "input_cost_per_token": 1e-07, + "litellm_provider": "oci", + "max_input_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" + }, + "oci/cohere.embed-multilingual-light-v3.0": { + "input_cost_per_token": 1e-07, + "litellm_provider": "oci", + "max_input_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 384, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" + }, + "oci/cohere.embed-english-image-v3.0": { + "input_cost_per_token": 1e-07, + "litellm_provider": "oci", + "max_input_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_embedding_image_input": true + }, + "oci/cohere.embed-english-light-image-v3.0": { + "input_cost_per_token": 1e-07, + "litellm_provider": "oci", + "max_input_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 384, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_embedding_image_input": true + }, + "oci/cohere.embed-multilingual-light-image-v3.0": { + "input_cost_per_token": 1e-07, + "litellm_provider": "oci", + "max_input_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 384, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_embedding_image_input": true + }, + "oci/cohere.embed-v4.0": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "oci", "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1536, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_embedding_image_input": true + }, + "ollama/codegeex4": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 32768, + "max_output_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1e-05, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 1.25e-06, - "supports_prompt_caching": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_web_search": true + "output_cost_per_token": 0.0, + "supports_function_calling": false }, - "openrouter/openai/gpt-4o-2024-05-13": { - "input_cost_per_token": 5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, + "ollama/codegemma": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 0.0 + }, + "ollama/codellama": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "mode": "completion", + "output_cost_per_token": 0.0 }, - "openrouter/openai/gpt-5-chat": { - "cache_read_input_token_cost": 1.25e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-05, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_reasoning": true, - "supports_tool_choice": true + "ollama/deepseek-coder-v2-base": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 0.0, + "supports_function_calling": true }, - "openrouter/openai/gpt-5-codex": { - "cache_read_input_token_cost": 1.25e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "ollama/deepseek-coder-v2-instruct": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 32768, + "max_output_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1e-05, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_reasoning": true, - "supports_tool_choice": true + "output_cost_per_token": 0.0, + "supports_function_calling": true }, - "openrouter/openai/gpt-5.2-codex": { - "cache_read_input_token_cost": 1.75e-07, - "input_cost_per_token": 1.75e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "ollama/deepseek-coder-v2-lite-base": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/deepseek-coder-v2-lite-instruct": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 32768, + "max_output_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.4e-05, - "source": "https://openrouter.ai/api/v1/models", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "output_cost_per_token": 0.0, + "supports_function_calling": true }, - "openrouter/openai/gpt-5": { - "cache_read_input_token_cost": 1.25e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "ollama/deepseek-v3.1:671b-cloud": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 163840, + "max_output_tokens": 163840, "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://openrouter.ai/api/v1/models", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "output_cost_per_token": 0.0, + "supports_function_calling": true }, - "openrouter/openai/gpt-5-mini": { - "cache_read_input_token_cost": 2.5e-08, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "ollama/gpt-oss:120b-cloud": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "output_cost_per_token": 0.0, + "supports_function_calling": true }, - "openrouter/openai/gpt-5-nano": { - "cache_read_input_token_cost": 5e-09, - "input_cost_per_token": 5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "ollama/gpt-oss:20b-cloud": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 4e-07, - "source": "https://openrouter.ai/api/v1/models", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "output_cost_per_token": 0.0, + "supports_function_calling": true }, - "openrouter/openai/gpt-5.1-codex-max": { - "cache_read_input_token_cost": 1.25e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "ollama/internlm2_5-20b-chat": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 32768, + "max_output_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://openrouter.ai/api/v1/models", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "output_cost_per_token": 0.0, + "supports_function_calling": true }, - "openrouter/openai/gpt-5.2": { - "input_cost_per_image": 0, - "cache_read_input_token_cost": 1.75e-07, - "input_cost_per_token": 1.75e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "ollama/llama2": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, + "max_output_tokens": 4096, "mode": "chat", - "output_cost_per_token": 1.4e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "output_cost_per_token": 0.0 }, - "openrouter/openai/gpt-5.2-chat": { - "input_cost_per_image": 0, - "cache_read_input_token_cost": 1.75e-07, - "input_cost_per_token": 1.75e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "ollama/llama2-uncensored": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 0.0 + }, + "ollama/llama2:13b": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, + "max_output_tokens": 4096, "mode": "chat", - "output_cost_per_token": 1.4e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "output_cost_per_token": 0.0 }, - "openrouter/openai/gpt-5.2-pro": { - "input_cost_per_image": 0, - "input_cost_per_token": 2.1e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "ollama/llama2:70b": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, + "max_output_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000168, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "output_cost_per_token": 0.0 }, - "openrouter/openai/gpt-5.6-sol": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_272k_tokens": 4e-07, - "default_reasoning_effort": "medium", - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "ollama/llama2:7b": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, + "max_output_tokens": 4096, "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "reasoning_effort_levels": [ - "none", - "low", - "medium", - "high", - "xhigh", - "max" - ], - "source": "https://openrouter.ai/api/v1/models", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "output_cost_per_token": 0.0 }, - "openrouter/openai/gpt-5.6-sol-pro": { - "input_cost_per_token": 4e-06, - "output_cost_per_token": 2e-05, - "cache_read_input_token_cost": 4e-07, - "cache_creation_input_token_cost": 5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1e-05, - "input_cost_per_token_above_272k_tokens": 8e-06, - "output_cost_per_token_above_272k_tokens": 3e-05, - "cache_read_input_token_cost_above_272k_tokens": 8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "ollama/llama3": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_web_search": true + "output_cost_per_token": 0.0 }, - "openrouter/openai/gpt-oss-120b": { - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 65536, - "max_tokens": 65536, + "ollama/llama3.1": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "output_cost_per_token": 0.0, + "supports_function_calling": true }, - "openrouter/openai/gpt-oss-120b:batch": { - "input_cost_per_token": 2.96e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, + "ollama/llama3:70b": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.36e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "output_cost_per_token": 0.0 }, - "openrouter/openai/gpt-oss-20b": { - "cache_read_input_token_cost": 9e-09, - "input_cost_per_token": 1.8e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "ollama/llama3:8b": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, "mode": "chat", - "output_cost_per_token": 9e-08, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "output_cost_per_token": 0.0 }, - "openrouter/openai/o1": { - "cache_read_input_token_cost": 7.5e-06, - "input_cost_per_token": 1.5e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "ollama/mistral": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/mistral-7B-Instruct-v0.1": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, "mode": "chat", - "output_cost_per_token": 6e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "output_cost_per_token": 0.0, + "supports_function_calling": true }, - "openrouter/openai/o3-mini": { - "input_cost_per_token": 1.1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "ollama/mistral-7B-Instruct-v0.2": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", - "output_cost_per_token": 4.4e-06, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": false, - "cache_read_input_token_cost": 5.5e-07, - "supports_prompt_caching": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_web_search": true + "output_cost_per_token": 0.0, + "supports_function_calling": true }, - "openrouter/openai/o3-mini-high": { - "input_cost_per_token": 1.1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "ollama/mistral-large-instruct-2407": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 65536, + "max_output_tokens": 8192, "mode": "chat", - "output_cost_per_token": 4.4e-06, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": false, - "cache_read_input_token_cost": 5.5e-07, - "supports_prompt_caching": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_web_search": true + "output_cost_per_token": 0.0, + "supports_function_calling": true }, - "openrouter/qwen/qwen-2.5-coder-32b-instruct": { - "input_cost_per_token": 6.6e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 29491, - "max_tokens": 29491, + "ollama/mixtral-8x22B-Instruct-v0.1": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 65536, + "max_output_tokens": 65536, "mode": "chat", - "output_cost_per_token": 1e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false + "output_cost_per_token": 0.0, + "supports_function_calling": true }, - "openrouter/qwen/qwen-vl-plus": { - "input_cost_per_token": 2.1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 8192, - "max_output_tokens": 2048, - "max_tokens": 2048, + "ollama/mixtral-8x7B-Instruct-v0.1": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", - "output_cost_per_token": 6.3e-07, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 0.0, + "supports_function_calling": true }, - "openrouter/qwen/qwen3-coder": { - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 3e-07, - "litellm_provider": "openrouter", + "ollama/orca-mini": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 0.0 + }, + "ollama/qwen3-coder:480b-cloud": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_output_tokens": 262144, "mode": "chat", - "output_cost_per_token": 1e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_tool_choice": true, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false + "output_cost_per_token": 0.0, + "supports_function_calling": true }, - "openrouter/qwen/qwen3-coder-plus": { - "cache_creation_input_token_cost": 8.125e-07, - "cache_creation_input_token_cost_above_128k_tokens": 2.4375e-06, - "cache_creation_input_token_cost_above_32k_tokens": 1.4625e-06, - "cache_read_input_token_cost": 1.3e-07, - "cache_read_input_token_cost_above_128k_tokens": 3.9e-07, - "cache_read_input_token_cost_above_32k_tokens": 2.34e-07, - "deprecation_date": "2026-10-09", - "input_cost_per_token": 6.5e-07, - "input_cost_per_token_above_128k_tokens": 1.95e-06, - "input_cost_per_token_above_32k_tokens": 1.17e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "ollama/vicuna": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 2048, + "max_output_tokens": 2048, + "mode": "completion", + "output_cost_per_token": 0.0 + }, + "omni-moderation-2024-09-26": { + "input_cost_per_token": 0.0, + "litellm_provider": "openai", + "max_input_tokens": 32768, + "max_output_tokens": 0, + "mode": "moderation", + "output_cost_per_token": 0.0 + }, + "omni-moderation-latest": { + "input_cost_per_token": 0.0, + "litellm_provider": "openai", + "max_input_tokens": 32768, + "max_output_tokens": 0, + "mode": "moderation", + "output_cost_per_token": 0.0 + }, + "openai.gpt-oss-120b-1:0": { + "supports_vision": false, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_inline_reasoning": true, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "input_cost_per_token_flex": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 16384, "mode": "chat", - "output_cost_per_token": 3.25e-06, - "output_cost_per_token_above_128k_tokens": 9.75e-06, - "output_cost_per_token_above_32k_tokens": 5.85e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_flex": 3e-07, + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, + "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_tool_choice": true }, - "openrouter/qwen/qwen3-235b-a22b-2507": { - "cache_read_input_token_cost": 1.75e-08, - "input_cost_per_token": 8.75e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, + "openai.gpt-oss-20b-1:0": { + "supports_vision": false, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_inline_reasoning": true, + "input_cost_per_token": 7e-08, + "input_cost_per_token_batches": 3.5e-08, + "input_cost_per_token_flex": 3.5e-08, + "input_cost_per_token_priority": 1.225e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 16384, "mode": "chat", - "output_cost_per_token": 3.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 3e-07, + "output_cost_per_token_batches": 1.5e-07, + "output_cost_per_token_flex": 1.5e-07, + "output_cost_per_token_priority": 5.25e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, + "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_tool_choice": true }, - "openrouter/qwen/qwen3-235b-a22b-thinking-2507": { - "deprecation_date": "2026-10-09", - "input_cost_per_token": 2.3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, + "openai.gpt-oss-safeguard-120b": { + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7e-08, + "input_cost_per_token_flex": 7e-08, + "input_cost_per_token_priority": 2.6e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 16000, "mode": "chat", - "output_cost_per_token": 2.3e-06, - "source": "https://openrouter.ai/api/v1/models", + "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_flex": 3e-07, + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, + "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_system_messages": true, + "supports_vision": false }, - "openrouter/qwen/qwen3.6-plus": { - "cache_creation_input_token_cost": 4.0625e-07, - "input_cost_per_token_above_256k_tokens": 1.3e-06, - "cache_creation_input_token_cost_above_256k_tokens": 1.625e-06, - "output_cost_per_token_above_256k_tokens": 3.9e-06, - "input_cost_per_token": 3.25e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "openai.gpt-oss-safeguard-20b": { + "input_cost_per_token": 7e-08, + "input_cost_per_token_batches": 3e-08, + "input_cost_per_token_flex": 3e-08, + "input_cost_per_token_priority": 1.2e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 16000, "mode": "chat", - "output_cost_per_token": 1.95e-06, - "source": "https://openrouter.ai/api/v1/models", + "output_cost_per_token": 2e-07, + "output_cost_per_token_batches": 1e-07, + "output_cost_per_token_flex": 1e-07, + "output_cost_per_token_priority": 3.5e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, + "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "supports_system_messages": true, + "supports_vision": false }, - "openrouter/qwen/qwen3.5-35b-a3b": { - "input_cost_per_token": 1.625e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 16384, - "max_tokens": 16384, + "ovhcloud/DeepSeek-R1-Distill-Llama-70B": { + "input_cost_per_token": 6.7e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 131000, + "max_output_tokens": 131000, "mode": "chat", - "output_cost_per_token": 1.3e-06, - "source": "https://openrouter.ai/api/v1/models", + "output_cost_per_token": 6.7e-07, + "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": true, "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 1.5625e-07, - "supports_audio_input": false, - "supports_pdf_input": false, - "supports_prompt_caching": true, "supports_response_schema": true, - "supports_web_search": false + "supports_tool_choice": true }, - "openrouter/qwen/qwen3.5-27b": { - "input_cost_per_token": 1.95e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, + "ovhcloud/Llama-3.1-8B-Instruct": { + "input_cost_per_token": 1e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 131000, + "max_output_tokens": 131000, "mode": "chat", - "output_cost_per_token": 1.56e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1e-07, + "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "supports_tool_choice": true }, - "openrouter/qwen/qwen3.5-122b-a10b": { - "input_cost_per_token": 2.6e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, + "ovhcloud/Meta-Llama-3_1-70B-Instruct": { + "input_cost_per_token": 6.7e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 131000, + "max_output_tokens": 131000, "mode": "chat", - "output_cost_per_token": 2.08e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 6.7e-07, + "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", + "supports_function_calling": false, + "supports_response_schema": false, + "supports_tool_choice": false + }, + "ovhcloud/Meta-Llama-3_3-70B-Instruct": { + "input_cost_per_token": 6.7e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 6.7e-07, + "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "supports_tool_choice": true }, - "openrouter/qwen/qwen3.5-flash-02-23": { - "input_cost_per_token": 6.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "ovhcloud/Mistral-7B-Instruct-v0.3": { + "input_cost_per_token": 1e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 127000, + "max_output_tokens": 127000, "mode": "chat", - "output_cost_per_token": 2.6e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1e-07, + "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "supports_tool_choice": true }, - "openrouter/qwen/qwen3.5-plus-02-15": { - "input_cost_per_token": 2.6e-07, - "input_cost_per_token_above_256k_tokens": 3.25e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "ovhcloud/Mistral-Nemo-Instruct-2407": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 118000, + "max_output_tokens": 118000, "mode": "chat", - "output_cost_per_token": 1.56e-06, - "output_cost_per_token_above_256k_tokens": 1.95e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1.3e-07, + "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "supports_tool_choice": true }, - "openrouter/qwen/qwen3.5-397b-a17b": { - "cache_read_input_token_cost": 2.25e-07, - "input_cost_per_token": 5.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, + "ovhcloud/Mistral-Small-3.2-24B-Instruct-2506": { + "input_cost_per_token": 9e-08, + "litellm_provider": "ovhcloud", + "max_input_tokens": 128000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 2.8e-07, + "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "supports_vision": true }, - "openrouter/switchpoint/router": { - "input_cost_per_token": 8.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "ovhcloud/Mixtral-8x7B-Instruct-v0.1": { + "input_cost_per_token": 6.3e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 32000, + "max_output_tokens": 32000, "mode": "chat", - "output_cost_per_token": 3.4e-06, - "source": "https://openrouter.ai/switchpoint/router", - "supports_tool_choice": true + "output_cost_per_token": 6.3e-07, + "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false }, - "openrouter/undi95/remm-slerp-l2-13b": { - "input_cost_per_token": 3.5e-07, - "litellm_provider": "openrouter", - "max_tokens": 5529, + "ovhcloud/Qwen2.5-Coder-32B-Instruct": { + "input_cost_per_token": 8.7e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 32000, + "max_output_tokens": 32000, "mode": "chat", - "output_cost_per_token": 6.5e-07, - "supports_tool_choice": false, - "max_input_tokens": 6144, - "max_output_tokens": 5529, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 8.7e-07, + "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false + "supports_tool_choice": false }, - "openrouter/x-ai/grok-4": { - "input_cost_per_token": 3e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "ovhcloud/Qwen2.5-VL-72B-Instruct": { + "input_cost_per_token": 9.1e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 32000, + "max_output_tokens": 32000, "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://openrouter.ai/x-ai/grok-4", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_web_search": true + "output_cost_per_token": 9.1e-07, + "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": true }, - "openrouter/z-ai/glm-4.6": { - "input_cost_per_token": 4.3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 204800, - "max_output_tokens": 16384, - "max_tokens": 16384, + "ovhcloud/Qwen3-32B": { + "input_cost_per_token": 8e-08, + "litellm_provider": "ovhcloud", + "max_input_tokens": 32000, + "max_output_tokens": 32000, "mode": "chat", - "output_cost_per_token": 1.75e-06, - "source": "https://openrouter.ai/api/v1/models", + "output_cost_per_token": 2.3e-07, + "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": true, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true, - "cache_read_input_token_cost": 8e-08, - "supports_audio_input": false, - "supports_pdf_input": false, "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false + "supports_tool_choice": true }, - "openrouter/z-ai/glm-4.6:exacto": { - "input_cost_per_token": 4.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 202800, + "ovhcloud/gpt-oss-120b": { + "input_cost_per_token": 8e-08, + "litellm_provider": "ovhcloud", + "max_input_tokens": 131000, "max_output_tokens": 131000, - "max_tokens": 131000, "mode": "chat", - "output_cost_per_token": 1.9e-06, - "source": "https://openrouter.ai/z-ai/glm-4.6:exacto", - "supports_function_calling": true, - "supports_prompt_caching": true, + "output_cost_per_token": 4e-07, + "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", + "supports_function_calling": false, "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": false }, - "openrouter/xiaomi/mimo-v2-flash": { - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 1e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 16384, - "max_tokens": 16384, + "ovhcloud/gpt-oss-20b": { + "input_cost_per_token": 4e-08, + "litellm_provider": "ovhcloud", + "max_input_tokens": 131000, + "max_output_tokens": 131000, "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, + "output_cost_per_token": 1.5e-07, + "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", + "supports_function_calling": false, "supports_reasoning": true, - "supports_vision": false, - "supports_prompt_caching": true + "supports_response_schema": true, + "supports_tool_choice": false }, - "openrouter/xiaomi/mimo-v2.5-pro": { - "input_cost_per_token": 4.35e-07, - "output_cost_per_token": 8.7e-07, - "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 3.6e-09, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 131072, - "max_tokens": 131072, + "ovhcloud/llava-v1.6-mistral-7b-hf": { + "input_cost_per_token": 2.9e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 32000, + "max_output_tokens": 32000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": false, + "output_cost_per_token": 2.9e-07, + "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", + "supports_function_calling": false, "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/xiaomi/mimo-v2.5": { - "input_cost_per_token": 1.4e-07, - "output_cost_per_token": 2.8e-07, - "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 2.8e-09, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": true, - "supports_audio_input": true, - "supports_pdf_input": false, - "supports_video_input": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/z-ai/glm-4.7": { - "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 1.1e-07, - "input_cost_per_token": 6e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 204800, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_assistant_prefill": true, - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/z-ai/glm-4.7-flash": { - "input_cost_per_token": 6.05e-08, - "output_cost_per_token": 4e-07, - "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 1e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 117964, - "max_tokens": 117964, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": false, - "supports_prompt_caching": false, - "supports_response_schema": true, - "supports_web_search": false - }, - "openrouter/z-ai/glm-5": { - "cache_read_input_token_cost": 1.2e-07, - "input_cost_per_token": 6e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 204800, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.92e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/z-ai/glm-5.1": { - "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 2.6e-07, - "input_cost_per_token": 1.4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 204800, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 4.4e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/minimax/minimax-m2.1": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 3e-08, - "deprecation_date": "2026-10-08", - "litellm_provider": "openrouter", - "max_input_tokens": 204800, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_computer_use": false, - "supports_pdf_input": false, - "supports_response_schema": true, - "supports_web_search": false - }, - "openrouter/minimax/minimax-m2.5": { - "input_cost_per_token": 2.7e-07, - "output_cost_per_token": 1.08e-06, - "cache_read_input_token_cost": 2.7e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 204800, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_computer_use": false, - "supports_pdf_input": false, - "supports_response_schema": true, - "supports_web_search": false - }, - "openrouter/openrouter/auto": { - "input_cost_per_token": 0, - "output_cost_per_token": 0, - "litellm_provider": "openrouter", - "max_input_tokens": 2000000, - "max_tokens": 2000000, - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_audio_input": true, - "supports_video_input": true - }, - "openrouter/openrouter/free": { - "input_cost_per_token": 0, - "output_cost_per_token": 0, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_tokens": 200000, - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true - }, - "openrouter/openrouter/bodybuilder": { - "input_cost_per_token": 0, - "output_cost_per_token": 0, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_tokens": 128000, - "mode": "chat" - }, - "ovhcloud/DeepSeek-R1-Distill-Llama-70B": { - "input_cost_per_token": 6.7e-07, - "litellm_provider": "ovhcloud", - "max_input_tokens": 131000, - "max_output_tokens": 131000, - "max_tokens": 131000, - "mode": "chat", - "output_cost_per_token": 6.7e-07, - "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "ovhcloud/Llama-3.1-8B-Instruct": { - "input_cost_per_token": 1e-07, - "litellm_provider": "ovhcloud", - "max_input_tokens": 131000, - "max_output_tokens": 131000, - "max_tokens": 131000, - "mode": "chat", - "output_cost_per_token": 1e-07, - "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "ovhcloud/Meta-Llama-3_1-70B-Instruct": { - "input_cost_per_token": 6.7e-07, - "litellm_provider": "ovhcloud", - "max_input_tokens": 131000, - "max_output_tokens": 131000, - "max_tokens": 131000, - "mode": "chat", - "output_cost_per_token": 6.7e-07, - "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", - "supports_function_calling": false, - "supports_response_schema": false, - "supports_tool_choice": false - }, - "ovhcloud/Meta-Llama-3_3-70B-Instruct": { - "input_cost_per_token": 6.7e-07, - "litellm_provider": "ovhcloud", - "max_input_tokens": 131000, - "max_output_tokens": 131000, - "max_tokens": 131000, - "mode": "chat", - "output_cost_per_token": 6.7e-07, - "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "ovhcloud/Mistral-7B-Instruct-v0.3": { - "input_cost_per_token": 1e-07, - "litellm_provider": "ovhcloud", - "max_input_tokens": 127000, - "max_output_tokens": 127000, - "max_tokens": 127000, - "mode": "chat", - "output_cost_per_token": 1e-07, - "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "ovhcloud/Mistral-Nemo-Instruct-2407": { - "input_cost_per_token": 1.3e-07, - "litellm_provider": "ovhcloud", - "max_input_tokens": 118000, - "max_output_tokens": 118000, - "max_tokens": 118000, - "mode": "chat", - "output_cost_per_token": 1.3e-07, - "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "ovhcloud/Mistral-Small-3.2-24B-Instruct-2506": { - "input_cost_per_token": 9e-08, - "litellm_provider": "ovhcloud", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.8e-07, - "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "ovhcloud/Mixtral-8x7B-Instruct-v0.1": { - "input_cost_per_token": 6.3e-07, - "litellm_provider": "ovhcloud", - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 6.3e-07, - "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", - "supports_function_calling": false, - "supports_response_schema": true, - "supports_tool_choice": false - }, - "ovhcloud/Qwen2.5-Coder-32B-Instruct": { - "input_cost_per_token": 8.7e-07, - "litellm_provider": "ovhcloud", - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 8.7e-07, - "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", - "supports_function_calling": false, - "supports_response_schema": true, - "supports_tool_choice": false - }, - "ovhcloud/Qwen2.5-VL-72B-Instruct": { - "input_cost_per_token": 9.1e-07, - "litellm_provider": "ovhcloud", - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 9.1e-07, - "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", - "supports_function_calling": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true - }, - "ovhcloud/Qwen3-32B": { - "input_cost_per_token": 8e-08, - "litellm_provider": "ovhcloud", - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 2.3e-07, - "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "ovhcloud/gpt-oss-120b": { - "input_cost_per_token": 8e-08, - "litellm_provider": "ovhcloud", - "max_input_tokens": 131000, - "max_output_tokens": 131000, - "max_tokens": 131000, - "mode": "chat", - "output_cost_per_token": 4e-07, - "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", - "supports_function_calling": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": false - }, - "ovhcloud/gpt-oss-20b": { - "input_cost_per_token": 4e-08, - "litellm_provider": "ovhcloud", - "max_input_tokens": 131000, - "max_output_tokens": 131000, - "max_tokens": 131000, - "mode": "chat", - "output_cost_per_token": 1.5e-07, - "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", - "supports_function_calling": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": false - }, - "ovhcloud/llava-v1.6-mistral-7b-hf": { - "input_cost_per_token": 2.9e-07, - "litellm_provider": "ovhcloud", - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 2.9e-07, - "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", - "supports_function_calling": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true + "supports_tool_choice": false, + "supports_vision": true }, "ovhcloud/mamba-codestral-7B-v0.1": { "input_cost_per_token": 1.9e-07, "litellm_provider": "ovhcloud", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 1.9e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -44148,65 +47687,18 @@ "supports_response_schema": true, "supports_tool_choice": false }, - "palm/chat-bison": { - "input_cost_per_token": 1.25e-07, - "litellm_provider": "palm", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.25e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "palm/chat-bison-001": { - "input_cost_per_token": 1.25e-07, - "litellm_provider": "palm", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.25e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "palm/text-bison": { - "input_cost_per_token": 1.25e-07, - "litellm_provider": "palm", - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "max_tokens": 1024, - "mode": "completion", - "output_cost_per_token": 1.25e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "palm/text-bison-001": { - "input_cost_per_token": 1.25e-07, - "litellm_provider": "palm", - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "max_tokens": 1024, - "mode": "completion", - "output_cost_per_token": 1.25e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "palm/text-bison-safety-off": { - "input_cost_per_token": 1.25e-07, - "litellm_provider": "palm", - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "max_tokens": 1024, - "mode": "completion", - "output_cost_per_token": 1.25e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "palm/text-bison-safety-recitation-off": { - "input_cost_per_token": 1.25e-07, - "litellm_provider": "palm", - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "max_tokens": 1024, - "mode": "completion", - "output_cost_per_token": 1.25e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + "parallel_ai/decision": { + "input_cost_per_query": 0.001, + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "parallel_ai", + "max_input_tokens": 32000, + "mode": "evaluation", + "source": "https://docs.parallel.ai/getting-started/pricing#decisions-api", + "supported_endpoints": [ + "/v1/decisions", + "/v1/systemone" + ] }, "parallel_ai/search": { "input_cost_per_query": 0.005, @@ -44233,7 +47725,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.4e-06 }, @@ -44242,7 +47733,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.8e-06 }, @@ -44251,7 +47741,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-06 }, @@ -44260,7 +47749,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-06 }, @@ -44269,7 +47757,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07 }, @@ -44278,7 +47765,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-07 }, @@ -44287,7 +47773,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-07 }, @@ -44296,7 +47781,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-06 }, @@ -44306,7 +47790,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-06 }, @@ -44315,7 +47798,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.8e-07 }, @@ -44325,15 +47807,62 @@ "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-07 }, + "perplexity/pplx-decider-v1-27b": { + "input_cost_per_token": 2e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 262144, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.perplexity.ai/api-reference/decisions-post" + }, + "perplexity/pplx-decider-v1.1-27b": { + "input_cost_per_token": 2e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 262144, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.perplexity.ai/docs/getting-started/pricing" + }, + "perplexity/pplx-decider-v1.2": { + "input_cost_per_token": 2e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 262144, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.perplexity.ai/docs/decisions/quickstart" + }, + "perplexity/pplx-decider-latest": { + "input_cost_per_token": 2e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 262144, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.perplexity.ai/docs/decisions/quickstart" + }, + "perplexity/pplx-decider-flash-v1.2": { + "input_cost_per_token": 1e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 262144, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.perplexity.ai/docs/decisions/quickstart" + }, + "perplexity/pplx-decider-flash-latest": { + "input_cost_per_token": 1e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 262144, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.perplexity.ai/docs/decisions/quickstart" + }, "perplexity/sonar": { "input_cost_per_token": 1e-06, "litellm_provider": "perplexity", "max_input_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-06, "search_context_cost_per_query": { @@ -44348,7 +47877,7 @@ "input_cost_per_token": 2e-06, "litellm_provider": "perplexity", "max_input_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 128000, "mode": "chat", "output_cost_per_reasoning_token": 3e-06, "output_cost_per_token": 8e-06, @@ -44365,7 +47894,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.8e-06 }, @@ -44375,7 +47903,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 12000, "max_output_tokens": 12000, - "max_tokens": 12000, "mode": "chat", "output_cost_per_token": 1.8e-06 }, @@ -44384,7 +47911,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 200000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -44398,7 +47924,7 @@ "input_cost_per_token": 1e-06, "litellm_provider": "perplexity", "max_input_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-06, "search_context_cost_per_query": { @@ -44413,7 +47939,7 @@ "input_cost_per_token": 2e-06, "litellm_provider": "perplexity", "max_input_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 8e-06, "search_context_cost_per_query": { @@ -44429,7 +47955,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.8e-07 }, @@ -44439,7 +47964,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 12000, "max_output_tokens": 12000, - "max_tokens": 12000, "mode": "chat", "output_cost_per_token": 2.8e-07 }, @@ -44448,7 +47972,6 @@ "litellm_provider": "publicai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -44460,7 +47983,6 @@ "litellm_provider": "publicai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -44472,7 +47994,6 @@ "litellm_provider": "publicai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -44484,7 +48005,6 @@ "litellm_provider": "publicai", "max_input_tokens": 16384, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -44496,7 +48016,6 @@ "litellm_provider": "publicai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -44508,7 +48027,6 @@ "litellm_provider": "publicai", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -44695,6 +48213,14 @@ "supports_reasoning": true, "supports_function_calling": true }, + "perplexity/perplexity/deepseek-v4-pro-0813": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 1.32e-06, + "output_cost_per_token": 3.96e-06, + "cache_read_input_token_cost": 4.4e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, "perplexity/perplexity/glm-5.2": { "cache_read_input_token_cost": 1.4e-07, "input_cost_per_token": 1.4e-06, @@ -44740,7 +48266,6 @@ "input_cost_per_token": 4e-09, "litellm_provider": "perplexity", "max_input_tokens": 32768, - "max_tokens": 32768, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -44750,7 +48275,6 @@ "input_cost_per_token": 3e-08, "litellm_provider": "perplexity", "max_input_tokens": 32768, - "max_tokens": 32768, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 2560, @@ -44761,7 +48285,6 @@ "litellm_provider": "publicai", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -44773,7 +48296,6 @@ "litellm_provider": "publicai", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -44786,7 +48308,6 @@ "litellm_provider": "publicai", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -44795,42 +48316,51 @@ "supports_reasoning": true }, "qwen.qwen3-coder-480b-a35b-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-480b-a35b-instruct.html", "input_cost_per_token": 4.5e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 262000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 262144, + "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.8e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-west-2/index.json" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-480b-a35b-instruct.html" }, "qwen.qwen3-235b-a22b-2507-v1:0": { "input_cost_per_token": 2.2e-07, + "input_cost_per_token_flex": 1.1e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 262144, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 8.8e-07, + "output_cost_per_token_flex": 4.4e-07, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "input_cost_per_token_batches": 1.1e-07, - "output_cost_per_token_batches": 4.4e-07 + "output_cost_per_token_batches": 4.4e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-235b-a22b-2507.html" }, "qwen.qwen3-coder-30b-a3b-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 262144, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -44838,12 +48368,18 @@ }, "qwen.qwen3-32b-v1:0": { "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "input_cost_per_token_flex": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 32768, + "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_flex": 3e-07, + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -44851,13 +48387,16 @@ }, "qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 1.5e-07, + "input_cost_per_token_flex": 7e-08, + "input_cost_per_token_priority": 2.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.2e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_flex": 6e-07, + "output_cost_per_token_priority": 2.1e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, @@ -44867,13 +48406,16 @@ }, "bedrock/ap-northeast-1/qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 1.8e-07, + "input_cost_per_token_flex": 9e-08, + "input_cost_per_token_priority": 3.2e-07, "litellm_provider": "bedrock", - "max_input_tokens": 128000, + "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.45e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_flex": 7.2e-07, + "output_cost_per_token_priority": 2.54e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, @@ -44883,13 +48425,18 @@ }, "bedrock/ap-south-1/qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 1.8e-07, + "input_cost_per_token_batches": 9e-08, + "input_cost_per_token_flex": 9e-08, + "input_cost_per_token_priority": 3.2e-07, "litellm_provider": "bedrock", - "max_input_tokens": 128000, + "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.41e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 7.1e-07, + "output_cost_per_token_flex": 7.1e-07, + "output_cost_per_token_priority": 2.47e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, @@ -44900,12 +48447,11 @@ "bedrock/ap-southeast-2/qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 1.545e-07, "litellm_provider": "bedrock", - "max_input_tokens": 128000, + "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.236e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, @@ -44915,13 +48461,16 @@ }, "bedrock/eu-west-1/qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 1.8e-07, + "input_cost_per_token_flex": 9e-08, + "input_cost_per_token_priority": 3.2e-07, "litellm_provider": "bedrock", - "max_input_tokens": 128000, + "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.41e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_flex": 7.1e-07, + "output_cost_per_token_priority": 2.47e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, @@ -44931,13 +48480,16 @@ }, "bedrock/eu-west-2/qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 2.3e-07, + "input_cost_per_token_flex": 1.2e-07, + "input_cost_per_token_priority": 4e-07, "litellm_provider": "bedrock", - "max_input_tokens": 128000, + "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.86e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_flex": 9.3e-07, + "output_cost_per_token_priority": 3.26e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, @@ -44947,13 +48499,16 @@ }, "bedrock/sa-east-1/qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 1.8e-07, + "input_cost_per_token_flex": 9e-08, + "input_cost_per_token_priority": 3.2e-07, "litellm_provider": "bedrock", - "max_input_tokens": 128000, + "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.45e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_flex": 7.2e-07, + "output_cost_per_token_priority": 2.54e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, @@ -44963,13 +48518,16 @@ }, "qwen.qwen3-vl-235b-a22b": { "input_cost_per_token": 5.3e-07, + "input_cost_per_token_batches": 2.6e-07, + "input_cost_per_token_priority": 9.3e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.66e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 1.33e-06, + "output_cost_per_token_priority": 4.66e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, @@ -44979,16 +48537,21 @@ }, "qwen.qwen3-coder-next": { "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "input_cost_per_token_flex": 2.5e-07, + "input_cost_per_token_priority": 8.75e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 1.2e-06, + "output_cost_per_token_batches": 6e-07, + "output_cost_per_token_flex": 6e-07, + "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false @@ -45034,9 +48597,9 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5e-07, + "source": "https://replicate.com/meta/llama-2-13b", "supports_tool_choice": true }, "replicate/meta/llama-2-13b-chat": { @@ -45044,9 +48607,10 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5e-07, + "source": "https://replicate.com/meta/llama-2-13b-chat", + "supports_system_messages": true, "supports_tool_choice": true }, "replicate/meta/llama-2-70b": { @@ -45054,9 +48618,9 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.75e-06, + "source": "https://replicate.com/meta/llama-2-70b", "supports_tool_choice": true }, "replicate/meta/llama-2-70b-chat": { @@ -45064,9 +48628,10 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.75e-06, + "source": "https://replicate.com/meta/llama-2-70b-chat", + "supports_system_messages": true, "supports_tool_choice": true }, "replicate/meta/llama-2-7b": { @@ -45074,9 +48639,9 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/meta/llama-2-7b", "supports_tool_choice": true }, "replicate/meta/llama-2-7b-chat": { @@ -45084,9 +48649,10 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/meta/llama-2-7b-chat", + "supports_system_messages": true, "supports_tool_choice": true }, "replicate/meta/llama-3-70b": { @@ -45094,7 +48660,6 @@ "litellm_provider": "replicate", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.75e-06, "supports_tool_choice": true @@ -45104,7 +48669,6 @@ "litellm_provider": "replicate", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.75e-06, "supports_tool_choice": true @@ -45114,7 +48678,6 @@ "litellm_provider": "replicate", "max_input_tokens": 8086, "max_output_tokens": 8086, - "max_tokens": 8086, "mode": "chat", "output_cost_per_token": 2.5e-07, "supports_tool_choice": true @@ -45124,7 +48687,6 @@ "litellm_provider": "replicate", "max_input_tokens": 8086, "max_output_tokens": 8086, - "max_tokens": 8086, "mode": "chat", "output_cost_per_token": 2.5e-07, "supports_tool_choice": true @@ -45134,7 +48696,6 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.5e-07, "supports_tool_choice": true @@ -45144,9 +48705,9 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/mistralai/mistral-7b-v0.1", "supports_tool_choice": true }, "replicate/mistralai/mixtral-8x7b-instruct-v0.1": { @@ -45154,7 +48715,6 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-06, "supports_tool_choice": true @@ -45164,8 +48724,10 @@ "output_cost_per_token": 1e-05, "litellm_provider": "replicate", "mode": "chat", + "source": "https://replicate.com/openai/gpt-5", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_reasoning": true, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, @@ -45176,6 +48738,7 @@ "output_cost_per_token": 3.6e-07, "litellm_provider": "replicate", "mode": "chat", + "source": "https://replicate.com/openai/gpt-oss-20b", "supports_function_calling": true, "supports_system_messages": true }, @@ -45191,13 +48754,15 @@ "supports_tool_choice": true, "supports_response_schema": true, "supports_prompt_caching": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://replicate.com/anthropic/claude-4.5-haiku" }, "replicate/ibm-granite/granite-3.3-8b-instruct": { "input_cost_per_token": 3e-08, "output_cost_per_token": 2.5e-07, "litellm_provider": "replicate", "mode": "chat", + "source": "https://replicate.com/ibm-granite/granite-3.3-8b-instruct", "supports_function_calling": true, "supports_system_messages": true }, @@ -45206,6 +48771,7 @@ "output_cost_per_token": 1e-05, "litellm_provider": "replicate", "mode": "chat", + "source": "https://replicate.com/openai/gpt-4o", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, @@ -45247,6 +48813,7 @@ "output_cost_per_token": 6e-07, "litellm_provider": "replicate", "mode": "chat", + "source": "https://replicate.com/openai/gpt-4o-mini", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, @@ -45259,6 +48826,7 @@ "output_cost_per_token": 1.06e-06, "litellm_provider": "replicate", "mode": "chat", + "source": "https://replicate.com/qwen/qwen3-235b-a22b-instruct-2507", "supports_function_calling": true, "supports_system_messages": true }, @@ -45283,7 +48851,7 @@ "mode": "chat", "max_input_tokens": 65536, "max_output_tokens": 8192, - "max_tokens": 8192, + "source": "https://replicate.com/deepseek-ai/deepseek-v3", "supports_function_calling": true, "supports_system_messages": true }, @@ -45339,7 +48907,9 @@ "supports_response_schema": false, "input_cost_per_token_above_200k_tokens": 4e-06, "output_cost_per_token_above_200k_tokens": 1.8e-05, + "source": "https://replicate.com/google/gemini-3-pro", "supports_audio_input": true, + "supports_reasoning": true, "supports_video_input": true }, "replicate/anthropic/claude-4.5-sonnet": { @@ -45354,13 +48924,15 @@ "supports_tool_choice": true, "supports_response_schema": true, "supports_prompt_caching": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://replicate.com/anthropic/claude-4.5-sonnet" }, "replicate/openai/gpt-4.1": { "input_cost_per_token": 2e-06, "output_cost_per_token": 8e-06, "litellm_provider": "replicate", "mode": "chat", + "source": "https://replicate.com/openai/gpt-4.1", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, @@ -45381,6 +48953,7 @@ "output_cost_per_token": 1.6e-06, "litellm_provider": "replicate", "mode": "chat", + "source": "https://replicate.com/openai/gpt-4.1-mini", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, @@ -45393,16 +48966,21 @@ "output_cost_per_token": 4e-07, "litellm_provider": "replicate", "mode": "chat", + "source": "https://replicate.com/openai/gpt-5-nano", "supports_function_calling": true, - "supports_system_messages": true + "supports_reasoning": true, + "supports_system_messages": true, + "supports_vision": true }, "replicate/openai/gpt-5-mini": { "input_cost_per_token": 2.5e-07, "output_cost_per_token": 2e-06, "litellm_provider": "replicate", "mode": "chat", + "source": "https://replicate.com/openai/gpt-5-mini", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_reasoning": true, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, @@ -45413,6 +48991,7 @@ "output_cost_per_token": 2.5e-06, "litellm_provider": "replicate", "mode": "chat", + "source": "https://replicate.com/google/gemini-2.5-flash", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": true, @@ -45428,6 +49007,7 @@ "output_cost_per_token": 7.2e-07, "litellm_provider": "replicate", "mode": "chat", + "source": "https://replicate.com/openai/gpt-oss-120b", "supports_function_calling": true, "supports_system_messages": true }, @@ -45438,7 +49018,7 @@ "mode": "chat", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, + "source": "https://replicate.com/deepseek-ai/deepseek-v3.1", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true @@ -45459,7 +49039,7 @@ "mode": "chat", "max_input_tokens": 65536, "max_output_tokens": 8192, - "max_tokens": 8192, + "source": "https://replicate.com/deepseek-ai/deepseek-r1", "supports_reasoning": true, "supports_system_messages": true }, @@ -45469,7 +49049,6 @@ "litellm_provider": "cohere", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "rerank", "output_cost_per_token": 0.0 }, @@ -45479,7 +49058,6 @@ "litellm_provider": "cohere", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "rerank", "output_cost_per_token": 0.0 }, @@ -45489,7 +49067,6 @@ "litellm_provider": "cohere", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "rerank", "output_cost_per_token": 0.0 }, @@ -45499,7 +49076,6 @@ "litellm_provider": "cohere", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://cohere.com/pricing" @@ -45510,11 +49086,28 @@ "litellm_provider": "cohere", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://cohere.com/pricing" }, + "rerank-v5.0-fast": { + "input_cost_per_token": 2e-08, + "litellm_provider": "cohere", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://cohere.com/blog/rerank-5" + }, + "rerank-v5.0-pro": { + "input_cost_per_token": 5e-08, + "litellm_provider": "cohere", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://cohere.com/blog/rerank-5" + }, "nvidia_nim/nvidia/nv-rerankqa-mistral-4b-v3": { "input_cost_per_query": 0.0, "input_cost_per_token": 0.0, @@ -45541,7 +49134,6 @@ "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.0 }, @@ -45550,7 +49142,6 @@ "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -45559,7 +49150,6 @@ "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.0 }, @@ -45568,7 +49158,6 @@ "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -45577,7 +49166,6 @@ "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.0 }, @@ -45586,7 +49174,6 @@ "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -45595,7 +49182,6 @@ "litellm_provider": "sambanova", "max_input_tokens": 196608, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://cloud.sambanova.ai/plans/pricing", @@ -45608,7 +49194,6 @@ "litellm_provider": "sambanova", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7e-06, "source": "https://cloud.sambanova.ai/plans/pricing" @@ -45618,7 +49203,6 @@ "litellm_provider": "sambanova", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "metadata": { "notes": "For vision models, images are converted to 6432 input tokens and are billed at that amount" }, @@ -45635,7 +49219,6 @@ "litellm_provider": "sambanova", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://cloud.sambanova.ai/plans/pricing", @@ -45644,7 +49227,6 @@ "supports_tool_choice": true }, "sambanova/DeepSeek-V3.1": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3e-06, @@ -45657,7 +49239,6 @@ "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/gpt-oss-120b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2.2e-07, @@ -45670,7 +49251,6 @@ "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/DeepSeek-V3.2": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 3e-06, @@ -45682,7 +49262,6 @@ "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/gemma-4-31B-it": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3.8e-07, @@ -45692,13 +49271,56 @@ "supports_vision": true, "source": "https://cloud.sambanova.ai/plans/pricing" }, + "scx-ai/DeepSeek-V4.1-flash": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "scx-ai", + "max_input_tokens": 1000000, + "max_output_tokens": 375000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://scx.ai/models/deepseek-v4-1-flash", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true + }, + "scx-ai/GLM-5.3": { + "cache_read_input_token_cost": 1.8e-07, + "input_cost_per_token": 9.8e-07, + "litellm_provider": "scx-ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.08e-06, + "source": "https://scx.ai/models/glm-5-3", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, + "scx-ai/Kimi-K3": { + "cache_read_input_token_cost": 2.8e-07, + "input_cost_per_token": 2.83e-06, + "litellm_provider": "scx-ai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.413e-05, + "source": "https://scx.ai/models/kimi-k3", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, "scx-ai/GLM-5.2": { "cache_read_input_token_cost": 2.2e-07, "input_cost_per_token": 6.1e-07, "litellm_provider": "scx-ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.98e-06, "source": "https://scx.ai/pricing", @@ -45715,7 +49337,6 @@ "litellm_provider": "scx-ai", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.99e-06, "source": "https://scx.ai/pricing", @@ -45730,7 +49351,6 @@ "litellm_provider": "snowflake", "max_input_tokens": 200000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, @@ -45746,7 +49366,6 @@ "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "input_cost_per_token": 1.35e-06, "output_cost_per_token": 5.4e-06, @@ -45757,56 +49376,48 @@ "litellm_provider": "snowflake", "max_input_tokens": 8000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/jamba-1.5-large": { "litellm_provider": "snowflake", "max_input_tokens": 256000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/jamba-1.5-mini": { "litellm_provider": "snowflake", "max_input_tokens": 256000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/jamba-instruct": { "litellm_provider": "snowflake", "max_input_tokens": 256000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/llama2-70b-chat": { "litellm_provider": "snowflake", "max_input_tokens": 4096, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/llama3-70b": { "litellm_provider": "snowflake", "max_input_tokens": 8000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/llama3-8b": { "litellm_provider": "snowflake", "max_input_tokens": 8000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/llama3.1-405b": { "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "input_cost_per_token": 1.2e-06, "output_cost_per_token": 1.2e-06, @@ -45817,7 +49428,6 @@ "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "input_cost_per_token": 7.2e-07, "output_cost_per_token": 7.2e-07, @@ -45828,7 +49438,6 @@ "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "input_cost_per_token": 2.4e-07, "output_cost_per_token": 2.4e-07, @@ -45838,18 +49447,15 @@ "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/llama3.2-3b": { "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/llama3.3-70b": { - "max_tokens": 16384, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_token": 7.2e-07, @@ -45863,21 +49469,18 @@ "litellm_provider": "snowflake", "max_input_tokens": 32000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/mistral-large": { "litellm_provider": "snowflake", "max_input_tokens": 32000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/mistral-large2": { "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "input_cost_per_token": 2e-06, "output_cost_per_token": 6e-06, @@ -45889,39 +49492,33 @@ "litellm_provider": "snowflake", "max_input_tokens": 32000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/reka-core": { "litellm_provider": "snowflake", "max_input_tokens": 32000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/reka-flash": { "litellm_provider": "snowflake", "max_input_tokens": 100000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/snowflake-arctic": { "litellm_provider": "snowflake", "max_input_tokens": 4096, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/snowflake-llama-3.1-405b": { "litellm_provider": "snowflake", "max_input_tokens": 8000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/snowflake-llama-3.3-70b": { - "max_tokens": 16384, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_token": 7.2e-07, @@ -46118,21 +49715,18 @@ "stability.sd3-5-large-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.08 }, "stability.sd3-large-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.08 }, "stability.stable-image-core-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.04 }, @@ -46142,96 +49736,184 @@ "mode": "image_edit", "output_cost_per_image": 0.4 }, + "us.stability.stable-conservative-upscale-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.4, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-creative-upscale-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.6 }, + "us.stability.stable-creative-upscale-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.6, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-fast-upscale-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.03 }, + "us.stability.stable-fast-upscale-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.03, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-outpaint-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.06 }, + "us.stability.stable-outpaint-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.06, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-control-sketch-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-control-sketch-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-control-structure-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-control-structure-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-erase-object-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-erase-object-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-inpaint-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-inpaint-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-remove-background-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-remove-background-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-search-recolor-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-search-recolor-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-search-replace-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-search-replace-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-style-guide-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-style-guide-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-style-transfer-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.08 }, + "us.stability.stable-style-transfer-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.08, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-core-v1:1": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.04 }, "stability.stable-image-ultra-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.14 }, "stability.stable-image-ultra-v1:1": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.14 }, @@ -46261,11 +49943,12 @@ "mode": "search" }, "text-completion-codestral/codestral-2405": { + "deprecation_date": "2025-06-16", + "deprecation_source": "https://docs.mistral.ai/getting-started/models/", "input_cost_per_token": 0.0, "litellm_provider": "text-completion-codestral", "max_input_tokens": 32000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "completion", "output_cost_per_token": 0.0, "source": "https://docs.mistral.ai/capabilities/code_generation/" @@ -46275,18 +49958,17 @@ "litellm_provider": "text-completion-codestral", "max_input_tokens": 32000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "completion", "output_cost_per_token": 0.0, "source": "https://docs.mistral.ai/capabilities/code_generation/" }, "text-embedding-004": { "deprecation_date": "2027-04-01", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", "input_cost_per_character": 2.5e-08, "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, - "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, @@ -46294,11 +49976,11 @@ }, "text-embedding-005": { "deprecation_date": "2027-04-01", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", "input_cost_per_character": 2.5e-08, "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, - "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, @@ -46309,7 +49991,6 @@ "input_cost_per_token_batches": 6.5e-08, "litellm_provider": "openai", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, "output_cost_per_token_batches": 0.0, @@ -46321,7 +50002,6 @@ "input_cost_per_token_batches": 1e-08, "litellm_provider": "openai", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, "output_cost_per_token_batches": 0.0, @@ -46332,7 +50012,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "openai", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536, @@ -46343,7 +50022,6 @@ "input_cost_per_token_batches": 5e-08, "litellm_provider": "openai", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, "output_cost_per_token_batches": 0.0 @@ -46353,7 +50031,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, @@ -46363,7 +50040,6 @@ "input_cost_per_token": 6.25e-09, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 3072, - "max_tokens": 3072, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, @@ -46371,11 +50047,11 @@ }, "text-multilingual-embedding-002": { "deprecation_date": "2027-04-01", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", "input_cost_per_character": 2.5e-08, "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, - "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, @@ -46386,7 +50062,6 @@ "litellm_provider": "vertex_ai-text-models", "max_input_tokens": 8192, "max_output_tokens": 1024, - "max_tokens": 1024, "mode": "completion", "output_cost_per_token": 2.8e-05, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" @@ -46396,7 +50071,6 @@ "litellm_provider": "vertex_ai-text-models", "max_input_tokens": 8192, "max_output_tokens": 1024, - "max_tokens": 1024, "mode": "completion", "output_cost_per_token": 2.8e-05, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" @@ -46422,7 +50096,8 @@ "together-ai-8.1b-21b": { "input_cost_per_token": 3e-07, "litellm_provider": "together_ai", - "max_tokens": 1000, + "max_output_tokens": 1000, + "max_input_tokens": 1000, "mode": "chat", "output_cost_per_token": 3e-07 }, @@ -46444,14 +50119,6 @@ "mode": "embedding", "output_cost_per_token": 0.0 }, - "together_ai/baai/bge-base-en-v1.5": { - "input_cost_per_token": 8e-09, - "litellm_provider": "together_ai", - "max_input_tokens": 512, - "mode": "embedding", - "output_cost_per_token": 0.0, - "output_vector_size": 768 - }, "together_ai/BAAI/bge-base-en-v1.5": { "input_cost_per_token": 8e-09, "litellm_provider": "together_ai", @@ -46483,7 +50150,6 @@ "litellm_provider": "together_ai", "max_input_tokens": 65536, "max_output_tokens": 8192, - "max_tokens": 8192, "metadata": { "successor": "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813" }, @@ -46495,13 +50161,16 @@ "supports_tool_choice": true }, "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo": { + "deprecation_date": "2026-10-22", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1.04e-06, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.04e-06, "source": "https://api.together.ai/v1/models", + "successor_model": "together_ai/meta-models/Muse-Glimmer-30B", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -46525,7 +50194,7 @@ "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://api.together.ai/v1/models", @@ -46546,7 +50215,7 @@ "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 202752, - "max_tokens": 202752, + "max_output_tokens": 202752, "metadata": { "successor": "together_ai/zai-org/GLM-5.2" }, @@ -46560,13 +50229,16 @@ }, "together_ai/MiniMaxAI/MiniMax-M3": { "cache_read_input_token_cost": 6e-08, + "deprecation_date": "2026-11-06", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 3e-07, "litellm_provider": "together_ai", "max_input_tokens": 524288, - "max_tokens": 524288, + "max_output_tokens": 524288, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models", + "successor_model": "together_ai/MiniMaxAI/MiniMax-M3.1-Flash", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -46575,11 +50247,22 @@ "supports_tool_choice": true, "supports_vision": true }, + "together_ai/MiniMaxAI/MiniMax-M3.1-Flash": { + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://www.together.ai/pricing", + "supports_prompt_caching": true + }, "together_ai/Prism-ML/Ternary-Bonsai-27B": { "input_cost_per_token": 0.0, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://docs.together.ai/docs/serverless-models" @@ -46588,7 +50271,7 @@ "input_cost_per_token": 1.7e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://api.together.ai/v1/models", @@ -46603,62 +50286,67 @@ "input_cost_per_token": 5e-07, "litellm_provider": "together_ai", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://api.together.ai/v1/models", "supports_reasoning": true }, "together_ai/Qwen/Qwen3.7-Max": { - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 1.5e-06, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2.5e-06, "litellm_provider": "together_ai", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 4.5e-06, - "source": "https://api.together.ai/v1/models", + "output_cost_per_token": 7.5e-06, + "source": "https://www.together.ai/pricing", "supports_prompt_caching": true }, "together_ai/Qwen/Qwen3.7-Plus": { "input_cost_per_token": 3.2e-07, "litellm_provider": "together_ai", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.28e-06, "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3.8-2.4T-A95B": { "cache_read_input_token_cost": 2.5e-07, + "deprecation_date": "2026-11-04", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 2e-06, "litellm_provider": "together_ai", "max_input_tokens": 1010000, - "max_tokens": 1010000, + "max_output_tokens": 1010000, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://api.together.ai/v1/models", + "successor_model": "together_ai/Qwen/Qwen3.7-Max", "supports_prompt_caching": true }, "together_ai/arize-ai/qwen-2-1.5b-instruct": { "input_cost_per_token": 1e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-V4-Flash-0731": { "cache_read_input_token_cost": 3e-08, - "deprecation_date": "2026-09-29", + "deprecation_date": "2026-10-22", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1.4e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://api.together.ai/v1/models", + "successor_model": "together_ai/deepseek-ai/DeepSeek-V4.1-Flash-1017", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -46670,7 +50358,7 @@ "input_cost_per_token": 3e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models", @@ -46681,11 +50369,10 @@ }, "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813": { "cache_read_input_token_cost": 1.3e-07, - "deprecation_date": "2026-09-29", "input_cost_per_token": 1.32e-06, "litellm_provider": "together_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.96e-06, "source": "https://api.together.ai/v1/models", @@ -46695,23 +50382,39 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "together_ai/deepseek-pro-latest": { + "alias_of": "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813" + }, "together_ai/meta-models/Muse-Glimmer-30B": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 3.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://api.together.ai/v1/models", "supports_prompt_caching": true }, + "together_ai/meta-models/Muse-Spark-Open-816B-A42B": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 4.25e-06, + "source": "https://docs.together.ai/docs/serverless-models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true + }, "together_ai/moonshotai/Kimi-K3": { "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "together_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.5e-05, "reasoning_effort_levels": [ @@ -46728,15 +50431,21 @@ "supports_tool_choice": true, "supports_vision": true }, + "together_ai/kimi-latest": { + "alias_of": "together_ai/moonshotai/Kimi-K3" + }, "together_ai/thinkingmachines/Inkling": { "cache_read_input_token_cost": 1.7e-07, + "deprecation_date": "2026-11-06", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1e-06, "litellm_provider": "together_ai", "max_input_tokens": 524288, - "max_tokens": 524288, + "max_output_tokens": 524288, "mode": "chat", "output_cost_per_token": 4.05e-06, "source": "https://api.together.ai/v1/models", + "successor_model": "together_ai/meta-models/Muse-Spark-Open-816B-A42B", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -46749,7 +50458,6 @@ "litellm_provider": "together_ai", "max_input_tokens": 1048575, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://api.together.ai/v1/models", @@ -46766,7 +50474,6 @@ "litellm_provider": "together_ai", "max_input_tokens": 1048575, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://api.together.ai/v1/models", @@ -46777,13 +50484,15 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "together_ai/glm-latest": { + "alias_of": "together_ai/zai-org/GLM-5.3" + }, "together_ai/zai-org/GLM-5.3-Flash": { "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048575, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://api.together.ai/v1/models", @@ -46795,7 +50504,13 @@ "supports_tool_choice": true, "supports_vision": true }, + "together_ai/glm-flash-latest": { + "alias_of": "together_ai/zai-org/GLM-5.3-Flash" + }, "tts-1": { + "deprecation_date": "2027-01-06", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-realtime-2.1-mini", "input_cost_per_character": 1.5e-05, "litellm_provider": "openai", "mode": "audio_speech", @@ -46805,6 +50520,9 @@ ] }, "tts-1-hd": { + "deprecation_date": "2027-01-06", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-realtime-2.1-mini", "input_cost_per_character": 3e-05, "litellm_provider": "openai", "mode": "audio_speech", @@ -46862,12 +50580,14 @@ "us.amazon.nova-lite-v1:0": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 6e-08, + "input_cost_per_token_batches": 3e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 2.4e-07, + "output_cost_per_token_batches": 1.2e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -46878,12 +50598,14 @@ "us.amazon.nova-micro-v1:0": { "cache_read_input_token_cost": 8.75e-09, "input_cost_per_token": 3.5e-08, + "input_cost_per_token_batches": 1.75e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.4e-07, + "output_cost_per_token_batches": 7e-08, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, @@ -46891,13 +50613,21 @@ }, "us.amazon.nova-pro-v1:0": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_flex": 1e-07, + "cache_read_input_token_cost_priority": 3.5e-07, "input_cost_per_token": 8e-07, + "input_cost_per_token_batches": 4e-07, + "input_cost_per_token_flex": 4e-07, + "input_cost_per_token_priority": 1.4e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.2e-06, + "output_cost_per_token_batches": 1.6e-06, + "output_cost_per_token_flex": 1.6e-06, + "output_cost_per_token_priority": 5.6e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -46912,7 +50642,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-06, "supports_assistant_prefill": true, @@ -46932,7 +50661,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -46949,14 +50677,17 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5.5e-07, - "output_cost_per_token_batches": 2.75e-06 + "output_cost_per_token_batches": 2.75e-06, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "us.anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -46974,7 +50705,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -46993,7 +50723,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -47011,7 +50740,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_function_calling": true, @@ -47025,11 +50753,11 @@ "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, "deprecation_date": "2027-01-08", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 1.5e-05, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { @@ -47047,7 +50775,11 @@ "supports_tool_choice": true, "supports_vision": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-1-20250805-v1:0", + "litellm_provider": "bedrock" + } }, "us.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.125e-06, @@ -47059,11 +50791,13 @@ "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05, "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, + "deprecation_date": "2027-04-08", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "us.anthropic.claude-sonnet-5-5", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -47085,7 +50819,11 @@ "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.65e-06, "output_cost_per_token_batches": 8.25e-06, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, @@ -47097,11 +50835,13 @@ "cache_creation_input_token_cost_above_200k_tokens": 9e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.44e-05, "cache_read_input_token_cost_above_200k_tokens": 7.2e-07, + "deprecation_date": "2027-04-27", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "us-gov.anthropic.claude-sonnet-5-5", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -47116,7 +50856,11 @@ "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "us-gov.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -47129,18 +50873,19 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "prompt_cache_min_tokens": 1024, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -47150,7 +50895,12 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "us-gov.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -47163,7 +50913,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 1024, @@ -47175,6 +50924,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -47184,7 +50934,12 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "us-gov.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, @@ -47196,12 +50951,12 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-gov-west-1/index.json", "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -47217,7 +50972,14 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + }, + "input_cost_per_token_batches": 3e-06, + "output_cost_per_token_batches": 1.5e-05 }, "us-gov.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -47229,7 +50991,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.4e-05, "prompt_cache_min_tokens": 512, @@ -47241,6 +51002,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -47252,7 +51014,12 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "thinking_always_on": true, - "supports_forced_tool_use": false + "supports_forced_tool_use": false, + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "us-gov.anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.5e-05, @@ -47262,7 +51029,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-05, "supports_adaptive_thinking": true, @@ -47281,19 +51047,24 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-fable-5-1", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "us-gov.nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 7.2e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.88e-07, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -47306,13 +51077,15 @@ "supports_vision": false }, "us-gov.nvidia.nemotron-nano-12b-v2": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-12b-v2-vl-bf16.html", "input_cost_per_token": 2.4e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-12b-v2-vl-bf16.html", "supports_system_messages": true, "supports_vision": true, "supports_audio_input": false, @@ -47320,13 +51093,15 @@ "supports_response_schema": true }, "us-gov.nvidia.nemotron-nano-9b-v2": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-9b-v2.html", "input_cost_per_token": 7.2e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.76e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-9b-v2.html", "supports_system_messages": true, "supports_audio_input": false, "supports_function_calling": true, @@ -47338,7 +51113,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.8e-07, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -47351,39 +51125,56 @@ "supports_vision": false }, "us-gov.openai.gpt-oss-20b-1:0": { + "supports_vision": false, "input_cost_per_token": 8.4e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 3.6e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.html", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "us-gov.openai.gpt-oss-120b-1:0": { + "supports_vision": false, "input_cost_per_token": 1.8e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "us-gov.xai.grok-4.6": { + "supports_regex_lookaround": false, "input_cost_per_token": 2.64e-06, "output_cost_per_token": 7.92e-06, "cache_read_input_token_cost": 6.6e-07, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_response_format": true, "litellm_provider": "bedrock_converse", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", "supports_function_calling": true, "supports_prompt_caching": false, @@ -47400,7 +51191,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, "supports_assistant_prefill": true, @@ -47417,7 +51207,11 @@ "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5.5e-07, "output_cost_per_token_batches": 2.75e-06, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "us.anthropic.claude-opus-4-20250514-v1:0": { "cache_creation_input_token_cost": 1.875e-05, @@ -47426,7 +51220,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { @@ -47454,7 +51247,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -47476,7 +51268,11 @@ "bedrock_output_config_effort_ceiling": "high", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-5-20251101-v1:0", + "litellm_provider": "bedrock" + } }, "global.anthropic.claude-opus-4-5-20251101-v1:0": { "cache_creation_input_token_cost": 6.25e-06, @@ -47487,7 +51283,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -47509,7 +51304,11 @@ "bedrock_output_config_effort_ceiling": "high", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-5-20251101-v1:0", + "litellm_provider": "bedrock" + } }, "eu.anthropic.claude-opus-4-5-20251101-v1:0": { "cache_creation_input_token_cost": 6.875e-06, @@ -47520,7 +51319,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -47542,21 +51340,26 @@ "bedrock_output_config_effort_ceiling": "high", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-5-20251101-v1:0", + "litellm_provider": "bedrock" + } }, "us.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2026-10-14", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "us.anthropic.claude-sonnet-5", "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -47575,29 +51378,40 @@ "supports_vision": true, "bedrock_converse_supports_strict_tools": false, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-20250514-v1:0", + "litellm_provider": "bedrock" + } }, "us.deepseek.r1-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-r1.html", "input_cost_per_token": 1.35e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-r1.html", "supports_function_calling": false, "supports_reasoning": true, "supports_tool_choice": false }, "us.deepseek.v3.2": { "input_cost_per_token": 6.2e-07, + "input_cost_per_token_batches": 3.1e-07, + "input_cost_per_token_flex": 3.1e-07, + "input_cost_per_token_priority": 1.085e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.85e-06, + "output_cost_per_token_batches": 9.25e-07, + "output_cost_per_token_flex": 9.25e-07, + "output_cost_per_token_priority": 3.2375e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -47608,12 +51422,13 @@ }, "eu.deepseek.v3.2": { "input_cost_per_token": 7.4e-07, + "input_cost_per_token_flex": 3.7e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 2.22e-06, + "output_cost_per_token_flex": 1.11e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -47623,11 +51438,12 @@ "supports_vision": false }, "us.meta.llama3-1-405b-instruct-v1:0": { + "deprecation_date": "2026-07-07", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 2.4e-06, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", @@ -47635,34 +51451,42 @@ "supports_tool_choice": false }, "us.meta.llama3-1-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 7.2e-07, + "input_cost_per_token_batches": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, + "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.2e-07, - "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", + "output_cost_per_token_batches": 3.6e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_tool_choice": false }, "us.meta.llama3-1-8b-instruct-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 2.2e-07, + "input_cost_per_token_batches": 1.1e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, + "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.2e-07, + "output_cost_per_token_batches": 1.1e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_tool_choice": false }, "us.meta.llama3-2-11b-instruct-v1:0": { + "deprecation_date": "2026-07-07", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 1.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.6e-07, "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", @@ -47671,33 +51495,38 @@ "supports_vision": true }, "us.meta.llama3-2-1b-instruct-v1:0": { + "deprecation_date": "2026-07-07", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.md", "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.md", "supports_function_calling": true, "supports_tool_choice": false }, "us.meta.llama3-2-3b-instruct-v1:0": { + "deprecation_date": "2026-07-07", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.md", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.md", "supports_function_calling": true, "supports_tool_choice": false }, "us.meta.llama3-2-90b-instruct-v1:0": { + "deprecation_date": "2026-07-07", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 7.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", @@ -47706,26 +51535,32 @@ "supports_vision": true }, "us.meta.llama3-3-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 7.2e-07, + "input_cost_per_token_batches": 3.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.2e-07, + "output_cost_per_token_batches": 3.6e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_tool_choice": false }, "us.meta.llama4-maverick-17b-instruct-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-maverick-17b-instruct.md", "input_cost_per_token": 2.4e-07, "input_cost_per_token_batches": 1.2e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 9.7e-07, "output_cost_per_token_batches": 4.85e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-maverick-17b-instruct.md", "supported_modalities": [ "text", "image" @@ -47738,15 +51573,17 @@ "supports_tool_choice": false }, "us.meta.llama4-scout-17b-instruct-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-scout-17b-instruct.md", "input_cost_per_token": 1.7e-07, "input_cost_per_token_batches": 8.5e-08, "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_input_tokens": 10000000, + "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.6e-07, "output_cost_per_token_batches": 3.3e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-scout-17b-instruct.md", "supported_modalities": [ "text", "image" @@ -47762,11 +51599,10 @@ "input_cost_per_token": 2e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-pixtral-large.md", "supports_function_calling": true, "supports_tool_choice": false }, @@ -47775,7 +51611,6 @@ "litellm_provider": "v0", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -47789,7 +51624,6 @@ "litellm_provider": "v0", "max_input_tokens": 512000, "max_output_tokens": 512000, - "max_tokens": 512000, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_function_calling": true, @@ -47803,7 +51637,6 @@ "litellm_provider": "v0", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -47817,7 +51650,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 40960, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.4e-07 }, @@ -47826,7 +51658,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 40960, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07 }, @@ -47835,7 +51666,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 40960, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3e-07 }, @@ -47844,7 +51674,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 40960, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -47855,7 +51684,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 262144, "max_output_tokens": 66536, - "max_tokens": 66536, "mode": "chat", "output_cost_per_token": 1.6e-06, "supports_function_calling": true, @@ -47866,7 +51694,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 300000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.4e-07, "supports_vision": true, @@ -47878,7 +51705,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.4e-07, "supports_function_calling": true, @@ -47889,7 +51715,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 300000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3.2e-06, "supports_vision": true, @@ -47901,7 +51726,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -47912,7 +51736,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.25e-06, "supports_vision": true, @@ -47927,7 +51750,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_vision": true, @@ -47942,7 +51764,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-06, "supports_vision": true, @@ -47957,7 +51778,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_vision": true, @@ -47972,7 +51792,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_vision": true, @@ -47987,7 +51806,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_vision": true, @@ -48002,7 +51820,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -48015,7 +51832,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -48033,7 +51849,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -48051,7 +51866,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -48070,7 +51884,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "supports_assistant_prefill": true, @@ -48090,7 +51903,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_assistant_prefill": true, @@ -48110,7 +51922,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_assistant_prefill": true, @@ -48130,7 +51941,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "supports_assistant_prefill": true, @@ -48153,10 +51963,9 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, @@ -48174,7 +51983,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -48194,7 +52002,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -48211,7 +52018,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 256000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, @@ -48223,7 +52029,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -48234,7 +52039,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, @@ -48245,7 +52049,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -48254,7 +52057,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.19e-06, "supports_tool_choice": true @@ -48264,7 +52066,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 9.9e-07, "supports_function_calling": true, @@ -48276,7 +52077,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 9e-07, "supports_tool_choice": true @@ -48286,7 +52086,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1000000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 2.5e-06, "supports_vision": true, @@ -48305,7 +52104,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1e-05, "supports_vision": true, @@ -48326,7 +52124,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -48335,7 +52132,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-07, "supports_vision": true, @@ -48347,7 +52143,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -48356,7 +52151,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -48365,7 +52159,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-06 }, @@ -48374,7 +52167,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.9e-07, "supports_tool_choice": true @@ -48384,7 +52176,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 8e-08, "supports_tool_choice": true @@ -48394,7 +52185,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "supports_tool_choice": true @@ -48404,7 +52194,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-08, "supports_function_calling": true, @@ -48415,7 +52204,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.6e-07, "supports_vision": true, @@ -48427,7 +52215,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-07 }, @@ -48436,7 +52223,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-07, "supports_function_calling": true, @@ -48447,7 +52233,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "supports_vision": true, @@ -48459,7 +52244,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "supports_function_calling": true, @@ -48470,7 +52254,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-07, "supports_tool_choice": true @@ -48480,7 +52263,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3e-07, "supports_vision": true, @@ -48492,7 +52274,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 256000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 9e-07, "supports_function_calling": true, @@ -48503,7 +52284,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -48512,7 +52292,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.8e-07, "supports_function_calling": true, @@ -48524,7 +52303,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "supports_function_calling": true, @@ -48536,7 +52314,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-06, "supports_function_calling": true @@ -48546,7 +52323,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 4e-08, "supports_function_calling": true, @@ -48557,7 +52333,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1e-07, "supports_vision": true, @@ -48569,7 +52344,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -48578,7 +52352,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 6e-06, "supports_function_calling": true, @@ -48589,7 +52362,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.9e-07 }, @@ -48598,7 +52370,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -48610,7 +52381,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 65536, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 1.2e-06, "supports_function_calling": true @@ -48620,7 +52390,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.5e-07, "supports_vision": true, @@ -48633,7 +52402,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 6e-06, "supports_vision": true, @@ -48646,7 +52414,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.2e-06, "supports_function_calling": true, @@ -48657,7 +52424,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06 }, @@ -48666,7 +52432,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.9e-06 }, @@ -48675,7 +52440,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-06, "supports_function_calling": true, @@ -48686,7 +52450,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-06 }, @@ -48695,7 +52458,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-05, "supports_vision": true, @@ -48709,7 +52471,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "supports_vision": true, @@ -48724,7 +52485,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "supports_vision": true, @@ -48739,7 +52499,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "supports_vision": true, @@ -48754,7 +52513,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "supports_vision": true, @@ -48769,7 +52527,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, "supports_vision": true, @@ -48784,7 +52541,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6e-05, "supports_vision": true, @@ -48799,7 +52555,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_vision": true, @@ -48814,7 +52569,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "supports_function_calling": true, @@ -48828,7 +52582,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "supports_vision": true, @@ -48841,7 +52594,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -48850,7 +52602,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -48859,7 +52610,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -48868,7 +52618,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 127000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1e-06 }, @@ -48877,7 +52626,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.5e-05 }, @@ -48886,7 +52634,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 127000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 5e-06 }, @@ -48895,7 +52642,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 127000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 8e-06 }, @@ -48904,7 +52650,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_vision": true, @@ -48916,7 +52661,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_vision": true, @@ -48928,7 +52672,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, @@ -48939,7 +52682,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1e-05, "supports_vision": true, @@ -48951,7 +52693,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -48962,7 +52703,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-05, "supports_function_calling": true @@ -48972,7 +52712,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "supports_function_calling": true, @@ -48983,7 +52722,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-06, "supports_function_calling": true, @@ -48994,7 +52732,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -49005,7 +52742,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.2e-06, "supports_function_calling": true, @@ -49016,7 +52752,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 96000, - "max_tokens": 96000, "mode": "chat", "output_cost_per_token": 1.1e-06, "supports_function_calling": true, @@ -49028,7 +52763,6 @@ "input_cost_per_token": 4.5e-07, "max_input_tokens": 200000, "max_output_tokens": 200000, - "max_tokens": 200000, "mode": "chat", "output_cost_per_token": 1.8e-06, "source": "https://vercel.com/ai-gateway/models/glm-4.6", @@ -49079,7 +52813,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5e-06, "supports_assistant_prefill": true, @@ -49093,7 +52826,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5e-06, "supports_assistant_prefill": true, @@ -49103,6 +52835,7 @@ }, "vertex_ai/claude-haiku-4-5": { "deprecation_date": "2026-10-15", + "successor_model": "vertex_ai/claude-haiku-5-5", "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, "cache_creation_input_token_cost_batches": 6.25e-07, @@ -49113,8 +52846,12 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, "regional_endpoint_uplift_multiplier": 1.1, @@ -49142,8 +52879,12 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, "regional_endpoint_uplift_multiplier": 1.1, @@ -49165,7 +52906,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -49181,7 +52921,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -49196,7 +52935,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.25e-06, "supports_assistant_prefill": true, @@ -49210,7 +52948,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.25e-06, "supports_assistant_prefill": true, @@ -49218,40 +52955,11 @@ "supports_tool_choice": true, "supports_vision": true }, - "vertex_ai/claude-3-opus": { - "deprecation_date": "2025-08-01", - "input_cost_per_token": 1.5e-05, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "vertex_ai/claude-3-opus@20240229": { - "deprecation_date": "2025-08-01", - "input_cost_per_token": 1.5e-05, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, "vertex_ai/claude-3-sonnet": { "input_cost_per_token": 3e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -49264,7 +52972,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -49274,6 +52981,7 @@ }, "vertex_ai/claude-opus-4-5": { "deprecation_date": "2026-11-24", + "successor_model": "vertex_ai/claude-opus-5-5", "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, @@ -49284,7 +52992,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -49319,7 +53026,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -49358,7 +53064,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -49396,7 +53101,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -49433,7 +53137,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -49471,7 +53174,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -49509,7 +53211,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, @@ -49547,7 +53248,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "search_context_cost_per_query": { @@ -49577,6 +53277,91 @@ "output_cost_per_token_batches": 2.5e-05, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, + "vertex_ai/claude-fable-5-2": { + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_creation_input_token_cost_batches": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "prompt_cache_min_tokens": 512, + "deprecation_date": "2027-11-09", + "input_cost_per_token_batches": 4e-06, + "output_cost_per_token_batches": 2e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/claude-mythos-5-2": { + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_creation_input_token_cost_batches": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "prompt_cache_min_tokens": 512, + "deprecation_date": "2027-11-09", + "input_cost_per_token_batches": 4e-06, + "output_cost_per_token_batches": 2e-05, + "source": "https://platform.claude.com/docs/en/models/mythos-5-2/overview" + }, + "vertex_ai/claude-fable-latest": { + "alias_of": "vertex_ai/claude-fable-5-2" + }, "vertex_ai/claude-fable-5@default": { "deprecation_date": "2027-06-08", "regional_endpoint_uplift_multiplier": 1.1, @@ -49591,7 +53376,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, @@ -49629,7 +53413,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "search_context_cost_per_query": { @@ -49659,11 +53442,94 @@ "output_cost_per_token_batches": 2.5e-05, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, + "vertex_ai/claude-fable-5-2@default": { + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_creation_input_token_cost_batches": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "prompt_cache_min_tokens": 512, + "deprecation_date": "2027-11-09", + "input_cost_per_token_batches": 4e-06, + "output_cost_per_token_batches": 2e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/claude-mythos-5-2@default": { + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_creation_input_token_cost_batches": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "prompt_cache_min_tokens": 512, + "deprecation_date": "2027-11-09", + "input_cost_per_token_batches": 4e-06, + "output_cost_per_token_batches": 2e-05, + "source": "https://platform.claude.com/docs/en/models/mythos-5-2/overview" + }, "vertex_ai/claude-opus-5": { "deprecation_date": "2027-01-24", "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, @@ -49674,7 +53540,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -49703,6 +53568,7 @@ "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, @@ -49713,7 +53579,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -49750,7 +53615,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_batches": 1.25e-05, @@ -49778,6 +53642,9 @@ "prompt_cache_min_tokens": 512, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, + "vertex_ai/claude-opus-latest": { + "alias_of": "vertex_ai/claude-opus-5-5" + }, "vertex_ai/claude-opus-5-5@default": { "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, @@ -49791,7 +53658,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_batches": 1.25e-05, @@ -49834,7 +53700,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -49873,7 +53738,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -49899,6 +53763,7 @@ }, "vertex_ai/claude-sonnet-4-5": { "deprecation_date": "2026-09-29", + "successor_model": "vertex_ai/claude-sonnet-5-5", "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05, @@ -49913,8 +53778,12 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, "regional_endpoint_uplift_multiplier": 1.1, @@ -49943,7 +53812,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -49953,6 +53821,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -49982,11 +53851,10 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -50021,8 +53889,12 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, "regional_endpoint_uplift_multiplier": 1.1, @@ -50045,7 +53917,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -50057,7 +53928,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -50069,7 +53939,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -50081,7 +53950,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -50093,7 +53961,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -50104,7 +53971,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -50115,7 +53981,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -50129,7 +53994,6 @@ "litellm_provider": "vertex_ai-deepseek_models", "max_input_tokens": 163840, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.7e-06, "output_cost_per_token_batches": 8.5e-07, @@ -50151,7 +54015,6 @@ "litellm_provider": "vertex_ai-deepseek_models", "max_input_tokens": 163840, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.68e-06, "output_cost_per_token_batches": 8.4e-07, @@ -50159,8 +54022,9 @@ "supported_regions": [ "global" ], - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true @@ -50172,7 +54036,6 @@ "litellm_provider": "vertex_ai-deepseek_models", "max_input_tokens": 65336, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, "output_cost_per_token_batches": 2.7e-06, @@ -50180,14 +54043,17 @@ "supported_regions": [ "us-central1" ], - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "vertex_ai/gemini-2.5-flash-image": { "deprecation_date": "2027-03-15", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "successor_model": "vertex_ai/gemini-3.1-flash-lite-image", "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, @@ -50195,10 +54061,10 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.039, "output_cost_per_image_token": 3e-05, + "output_cost_per_image_token_batches": 1.5e-05, "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 1.25e-06, @@ -50207,7 +54073,8 @@ "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", + "/v1/images/generations", + "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ @@ -50242,7 +54109,6 @@ "cache_read_input_token_cost_batches": 1e-07, "cache_read_input_token_cost_flex": 1e-07, "cache_read_input_token_cost_priority": 3.6e-07, - "deprecation_date": "2027-05-28", "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, @@ -50253,18 +54119,25 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, + "output_cost_per_image_token_batches": 6e-05, + "output_cost_per_image_token_priority": 0.000216, "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "output_cost_per_token_batches": 6e-06, "output_cost_per_token_flex": 6e-06, "output_cost_per_token_priority": 2.16e-05, - "supports_reasoning": false, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/images/generations", + "/v1/images/edits", + "/v1/batch" + ], + "supports_reasoning": false }, "vertex_ai/gemini-3-pro-image-preview": { "input_cost_per_image": 0.0011, @@ -50281,39 +54154,57 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, + "output_cost_per_image_token_batches": 6e-05, + "output_cost_per_image_token_priority": 0.000216, "output_cost_per_token": 1.2e-05, "output_cost_per_token_priority": 2.16e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "output_cost_per_token_batches": 6e-06, "supports_reasoning": false, - "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image" + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/images/generations", + "/v1/images/edits", + "/v1/batch" + ] + }, "vertex_ai/gemini-3.1-flash-image": { "cache_read_input_token_cost": 5e-08, "cache_read_input_token_cost_batches": 2.5e-08, "cache_read_input_token_cost_flex": 2.5e-08, - "deprecation_date": "2027-05-28", + "cache_read_input_token_cost_priority": 9e-08, "input_cost_per_image": 0.00056, "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "input_cost_per_token_flex": 2.5e-07, + "input_cost_per_token_priority": 9e-07, "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 65536, + "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.0672, "output_cost_per_image_token": 6e-05, + "output_cost_per_image_token_batches": 3e-05, + "output_cost_per_image_token_priority": 0.000108, "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, - "supports_reasoning": false, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "output_cost_per_token_priority": 5.4e-06, + "regional_endpoint_uplift_multiplier": 1.1, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/images/generations", + "/v1/images/edits", + "/v1/batch" + ], + "supports_reasoning": false }, "vertex_ai/gemini-3.1-flash-image-preview": { "input_cost_per_image": 0.00056, @@ -50324,37 +54215,50 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.0672, "output_cost_per_image_token": 6e-05, + "output_cost_per_image_token_batches": 3e-05, + "output_cost_per_image_token_priority": 0.000108, "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, "supports_reasoning": false, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models" + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/images/generations", + "/v1/images/edits", + "/v1/batch" + ] + }, "vertex_ai/gemini-3.1-flash-lite-image": { "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, + "cache_read_input_token_cost_priority": 4.5e-08, "input_cost_per_image": 0.00028, "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_flex": 1.25e-07, + "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "image_generation", "output_cost_per_image": 0.0336, "output_cost_per_image_token": 3e-05, + "output_cost_per_image_token_batches": 1.5e-05, + "output_cost_per_image_token_priority": 5.4e-05, "output_cost_per_token": 1.5e-06, "output_cost_per_token_batches": 7.5e-07, "output_cost_per_token_flex": 7.5e-07, + "output_cost_per_token_priority": 2.7e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", + "/v1/images/generations", + "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ @@ -50382,7 +54286,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 1.5e-06, "output_cost_per_token": 1.5e-06, @@ -50421,26 +54324,35 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, "vertex_ai/gemini-3.1-flash-lite": { "cache_read_input_audio_token_cost": 5e-08, - "deprecation_date": "2027-05-07", + "cache_read_input_audio_token_cost_batches": 2.5e-08, + "cache_read_input_audio_token_cost_flex": 2.5e-08, + "cache_read_input_audio_token_cost_priority": 9e-08, "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 5e-07, + "input_cost_per_audio_token_above_200k_tokens": 5e-07, + "input_cost_per_audio_token_above_200k_tokens_batches": 2.5e-07, + "input_cost_per_audio_token_above_200k_tokens_flex": 2.5e-07, + "input_cost_per_audio_token_above_200k_tokens_priority": 9e-07, + "input_cost_per_audio_token_batches": 2.5e-07, + "input_cost_per_audio_token_flex": 2.5e-07, + "input_cost_per_audio_token_priority": 9e-07, "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_flex": 1.25e-07, "input_cost_per_token_priority": 4.5e-07, - "input_cost_per_audio_token_priority": 9e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 1.5e-06, "output_cost_per_token": 1.5e-06, @@ -50448,7 +54360,10 @@ "output_cost_per_token_flex": 7.5e-07, "output_cost_per_token_priority": 2.7e-06, "regional_endpoint_uplift_multiplier": 1.1, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "successor_model": "vertex_ai/gemini-3.5-flash-lite", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -50466,6 +54381,7 @@ "supports_audio_input": true, "supports_audio_output": false, "supports_function_calling": true, + "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -50477,22 +54393,14 @@ "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_audio_token_batches": 2.5e-07 + "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-3.5-flash-lite": { - "deprecation_date": "2027-07-21", "cache_read_input_token_cost": 3e-08, "cache_read_input_token_cost_batches": 1.5e-08, "cache_read_input_token_cost_flex": 1.5e-08, "cache_read_input_token_cost_priority": 5.4e-08, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, @@ -50500,7 +54408,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -50508,6 +54415,8 @@ "output_cost_per_token_flex": 1.25e-06, "output_cost_per_token_priority": 4.5e-06, "regional_endpoint_uplift_multiplier": 1.1, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -50525,26 +54434,22 @@ ], "supports_audio_input": true, "supports_audio_output": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "web_search_billing_unit": "per_query" }, "vertex_ai/deep-research-pro-preview-12-2025": { "cache_read_input_token_cost": 2e-07, @@ -50555,8 +54460,7 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "image_generation", + "mode": "chat", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_token": 1.2e-05, @@ -50569,7 +54473,6 @@ "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true @@ -50580,7 +54483,6 @@ "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_tool_choice": true @@ -50591,7 +54493,6 @@ "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_tool_choice": true @@ -50602,7 +54503,6 @@ "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true @@ -50613,7 +54513,6 @@ "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true @@ -50643,7 +54542,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "audio_speech", "output_cost_per_image": 0.04, "output_cost_per_token": 0, @@ -50679,7 +54577,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "audio_speech", "output_cost_per_image": 0.08, "output_cost_per_token": 0, @@ -50716,7 +54613,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 1.6e-05, "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", @@ -50729,7 +54625,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", @@ -50742,7 +54637,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, "max_output_tokens": 2048, - "max_tokens": 2048, "metadata": { "notes": "VertexAI states that The Llama 3.1 API service for llama-3.1-70b-instruct-maas and llama-3.1-8b-instruct-maas are in public preview and at no cost." }, @@ -50758,7 +54652,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, "max_output_tokens": 2048, - "max_tokens": 2048, "metadata": { "notes": "VertexAI states that The Llama 3.2 API service is at no cost during public preview, and will be priced as per dollar-per-1M-tokens at GA." }, @@ -50775,7 +54668,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.15e-06, "output_cost_per_token_batches": 5.75e-07, @@ -50793,12 +54685,13 @@ }, "vertex_ai/meta/llama-4-maverick-17b-16e-instruct-maas": { "input_cost_per_token": 3.5e-07, + "input_cost_per_token_batches": 1.75e-07, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.15e-06, + "output_cost_per_token_batches": 5.75e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_modalities": [ "text", @@ -50813,12 +54706,13 @@ }, "vertex_ai/meta/llama-4-scout-17b-128e-instruct-maas": { "input_cost_per_token": 2.5e-07, + "input_cost_per_token_batches": 1.25e-07, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 10000000, "max_output_tokens": 10000000, - "max_tokens": 10000000, "mode": "chat", "output_cost_per_token": 7e-07, + "output_cost_per_token_batches": 3.5e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_modalities": [ "text", @@ -50837,7 +54731,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 10000000, "max_output_tokens": 10000000, - "max_tokens": 10000000, "mode": "chat", "output_cost_per_token": 7e-07, "output_cost_per_token_batches": 3.5e-07, @@ -50858,7 +54751,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", @@ -50869,7 +54761,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", @@ -50880,7 +54771,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", @@ -50893,7 +54783,6 @@ "litellm_provider": "vertex_ai-minimax_models", "max_input_tokens": 196608, "max_output_tokens": 196608, - "max_tokens": 196608, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -50907,22 +54796,22 @@ "litellm_provider": "vertex_ai-moonshot_models", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_web_search": true }, "vertex_ai/zai-org/glm-4.7-maas": { "cache_read_input_token_cost": 6e-08, "deprecation_date": "2026-10-21", + "successor_model": "vertex_ai/zai-org/glm-5.2-maas", "input_cost_per_token": 6e-07, "litellm_provider": "vertex_ai-zai_models", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -50930,17 +54819,18 @@ "global" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_reasoning": true, "supports_tool_choice": true }, "vertex_ai/zai-org/glm-5-maas": { "cache_read_input_token_cost": 1e-07, "deprecation_date": "2026-10-21", + "successor_model": "vertex_ai/zai-org/glm-5.2-maas", "input_cost_per_token": 1e-06, "litellm_provider": "vertex_ai-zai_models", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -50948,6 +54838,7 @@ "global" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true @@ -50957,7 +54848,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -50969,7 +54859,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -50981,7 +54870,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -50993,7 +54881,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -51005,7 +54892,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 6e-06, "supports_function_calling": true, @@ -51016,7 +54902,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 6e-06, "supports_function_calling": true, @@ -51027,7 +54912,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 6e-06, "supports_function_calling": true, @@ -51038,7 +54922,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 6e-06, "supports_function_calling": true, @@ -51049,7 +54932,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-06, "supports_function_calling": true, @@ -51060,7 +54942,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-07, "supports_function_calling": true, @@ -51071,7 +54952,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -51084,7 +54964,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 32000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -51118,7 +54997,6 @@ "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 262144, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/maas/google/gemma-4-26b-a4b-it", @@ -51135,11 +55013,11 @@ "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3.6e-07, "output_cost_per_token_batches": 1.8e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supports_pdf_input": false, "supports_reasoning": true }, "vertex_ai/openai/gpt-oss-20b-maas": { @@ -51148,10 +55026,10 @@ "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supports_pdf_input": false, "supports_reasoning": true, "cache_read_input_token_cost": 7e-09, "input_cost_per_token_batches": 3.5e-08, @@ -51163,7 +55041,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -51180,7 +55057,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -51200,7 +55076,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 2000000, "max_output_tokens": 2000000, - "max_tokens": 2000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, @@ -51220,7 +55095,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 2000000, "max_output_tokens": 2000000, - "max_tokens": 2000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, @@ -51241,7 +55115,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 200000, "max_output_tokens": 200000, - "max_tokens": 200000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, @@ -51261,7 +55134,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 524288, "max_output_tokens": 524288, - "max_tokens": 524288, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, @@ -51280,7 +55152,6 @@ "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 8.8e-07, "output_cost_per_token_batches": 4.4e-07, @@ -51290,6 +55161,7 @@ "us-south1" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true }, "vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas": { @@ -51300,7 +55172,6 @@ "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.8e-06, "output_cost_per_token_batches": 9e-07, @@ -51309,6 +55180,7 @@ "global" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true }, "vertex_ai/qwen/qwen3-next-80b-a3b-instruct-maas": { @@ -51317,7 +55189,6 @@ "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -51325,6 +55196,7 @@ "global" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true }, "vertex_ai/qwen/qwen3-next-80b-a3b-thinking-maas": { @@ -51333,7 +55205,6 @@ "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -51341,12 +55212,12 @@ "global" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true }, "vertex_ai/veo-3.1-generate-preview": { "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, "output_cost_per_second_4k": 0.6, @@ -51361,7 +55232,6 @@ "vertex_ai/veo-3.1-fast-generate-preview": { "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.12, @@ -51375,14 +55245,13 @@ ] }, "vertex_ai/veo-3.1-generate-001": { - "deprecation_date": "2026-11-17", "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, "output_cost_per_second_4k": 0.6, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "successor_model": "vertex_ai/gemini-omni-1.2-flash", "supported_modalities": [ "text" ], @@ -51391,15 +55260,14 @@ ] }, "vertex_ai/veo-3.1-fast-generate-001": { - "deprecation_date": "2026-11-17", "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.12, "output_cost_per_second_4k": 0.3, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "successor_model": "vertex_ai/gemini-omni-1.2-flash", "supported_modalities": [ "text" ], @@ -51410,7 +55278,6 @@ "vertex_ai/veo-3.1-lite-generate-001": { "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.05, "output_cost_per_second_1080p": 0.08, @@ -51428,7 +55295,6 @@ "litellm_provider": "voyage", "max_input_tokens": 16000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "rerank", "output_cost_per_token": 0.0 }, @@ -51437,16 +55303,32 @@ "litellm_provider": "voyage", "max_input_tokens": 8000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "rerank", "output_cost_per_token": 0.0 }, + "voyage/rerank-1": { + "input_cost_per_token": 5e-08, + "litellm_provider": "voyage", + "max_input_tokens": 8000, + "max_output_tokens": 8000, + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://docs.voyageai.com/docs/pricing" + }, + "voyage/rerank-lite-1": { + "input_cost_per_token": 2e-08, + "litellm_provider": "voyage", + "max_input_tokens": 4000, + "max_output_tokens": 4000, + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://docs.voyageai.com/docs/pricing" + }, "voyage/rerank-2.5": { "input_cost_per_token": 5e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "rerank", "output_cost_per_token": 0.0 }, @@ -51455,7 +55337,6 @@ "litellm_provider": "voyage", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "rerank", "output_cost_per_token": 0.0 }, @@ -51464,7 +55345,6 @@ "litellm_provider": "voyage", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://docs.voyageai.com/docs/pricing" @@ -51474,7 +55354,6 @@ "litellm_provider": "voyage", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://docs.voyageai.com/docs/pricing" @@ -51483,7 +55362,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "voyage", "max_input_tokens": 4000, - "max_tokens": 4000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -51491,7 +55369,6 @@ "input_cost_per_token": 6e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -51499,7 +55376,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -51509,7 +55385,6 @@ "input_cost_per_token": 1.8e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -51517,7 +55392,6 @@ "input_cost_per_token": 2e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -51525,7 +55399,6 @@ "input_cost_per_token": 6e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -51533,7 +55406,6 @@ "input_cost_per_token": 2e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -51541,7 +55413,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 16000, - "max_tokens": 16000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -51549,7 +55420,6 @@ "input_cost_per_token": 1.8e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -51557,7 +55427,6 @@ "input_cost_per_token": 1.8e-07, "litellm_provider": "voyage", "max_input_tokens": 120000, - "max_tokens": 120000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -51565,7 +55434,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -51573,23 +55441,29 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 16000, - "max_tokens": 16000, "mode": "embedding", "output_cost_per_token": 0.0 }, + "voyage/voyage-large-2-instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "voyage", + "max_input_tokens": 16000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://docs.voyageai.com/docs/pricing" + }, "voyage/voyage-law-2": { "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 16000, - "max_tokens": 16000, "mode": "embedding", "output_cost_per_token": 0.0 }, "voyage/voyage-lite-01": { "input_cost_per_token": 1e-07, "litellm_provider": "voyage", - "max_input_tokens": 4096, - "max_tokens": 4096, + "max_input_tokens": 4000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -51597,7 +55471,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "voyage", "max_input_tokens": 4000, - "max_tokens": 4000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -51605,13 +55478,12 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "supports_embedding_image_input": true }, "wandb/openai/gpt-oss-120b": { "supports_reasoning": true, - "max_tokens": 131072, "max_input_tokens": 131000, "max_output_tokens": 131072, "input_cost_per_token": 3e-08, @@ -51622,7 +55494,6 @@ }, "wandb/openai/gpt-oss-20b": { "supports_reasoning": true, - "max_tokens": 131072, "max_input_tokens": 131000, "max_output_tokens": 131072, "input_cost_per_token": 3e-08, @@ -51632,7 +55503,6 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/moonshotai/Kimi-K2.5": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "cache_read_input_token_cost": 1e-07, @@ -51647,28 +55517,27 @@ "supports_vision": true }, "wandb/meta-llama/Llama-3.1-8B-Instruct": { - "max_tokens": 128000, - "max_input_tokens": 131000, + "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2.2e-07, "output_cost_per_token": 2.2e-07, "litellm_provider": "wandb", "mode": "chat", - "source": "https://wandb.ai/site/pricing/tokens/" + "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference" }, "wandb/deepseek-ai/DeepSeek-V3.1": { + "cache_read_input_token_cost": 2e-07, "supports_reasoning": true, - "max_tokens": 128000, - "max_input_tokens": 161000, + "max_input_tokens": 128000, "max_output_tokens": 128000, - "input_cost_per_token": 5.5e-07, - "output_cost_per_token": 1.65e-06, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 1.5e-06, "litellm_provider": "wandb", "mode": "chat", - "source": "https://wandb.ai/site/pricing/tokens/" + "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference", + "supports_prompt_caching": true }, "wandb/meta-llama/Llama-3.3-70B-Instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 7.1e-07, @@ -51682,7 +55551,6 @@ "litellm_provider": "watsonx", "max_input_tokens": 8192, "max_output_tokens": 1024, - "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 2e-07, "supports_audio_input": false, @@ -51700,7 +55568,6 @@ "litellm_provider": "watsonx", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "supports_audio_input": false, @@ -51714,7 +55581,6 @@ "supports_vision": false }, "watsonx/bigscience/mt0-xxl-13b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.908e-06, @@ -51727,7 +55593,6 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/bigscience/mt0-xxl": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.908e-06, @@ -51740,11 +55605,10 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/core42/jais-13b-chat": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, - "input_cost_per_token": 0.0005, - "output_cost_per_token": 0.002, + "input_cost_per_token": 1.8e-06, + "output_cost_per_token": 1.8e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, @@ -51752,7 +55616,6 @@ "supports_vision": false }, "watsonx/google/flan-t5-xl-3b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 6e-07, @@ -51764,7 +55627,6 @@ "supports_vision": false }, "watsonx/ibm/granite-13b-chat-v2": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 6e-07, @@ -51776,7 +55638,6 @@ "supports_vision": false }, "watsonx/ibm/granite-13b-instruct-v2": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 6e-07, @@ -51788,7 +55649,6 @@ "supports_vision": false }, "watsonx/ibm/granite-3-3-8b-instruct": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -51800,7 +55660,6 @@ "supports_vision": false }, "watsonx/ibm/granite-4-h-small": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 6.36e-08, @@ -51813,7 +55672,6 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/ibm/granite-guardian-3-2-2b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 1e-07, @@ -51825,7 +55683,6 @@ "supports_vision": false }, "watsonx/ibm/granite-guardian-3-3-8b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -51837,7 +55694,6 @@ "supports_vision": false }, "watsonx/ibm/granite-ttm-1024-96-r2": { - "max_tokens": 512, "max_input_tokens": 512, "max_output_tokens": 512, "input_cost_per_token": 3.8e-07, @@ -51849,7 +55705,6 @@ "supports_vision": false }, "watsonx/ibm/granite-ttm-1536-96-r2": { - "max_tokens": 512, "max_input_tokens": 512, "max_output_tokens": 512, "input_cost_per_token": 3.8e-07, @@ -51861,7 +55716,6 @@ "supports_vision": false }, "watsonx/ibm/granite-ttm-512-96-r2": { - "max_tokens": 512, "max_input_tokens": 512, "max_output_tokens": 512, "input_cost_per_token": 3.8e-07, @@ -51873,7 +55727,6 @@ "supports_vision": false }, "watsonx/ibm/granite-vision-3-2-2b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 1e-07, @@ -51885,7 +55738,6 @@ "supports_vision": true }, "watsonx/meta-llama/llama-3-2-11b-vision-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 3.5e-07, @@ -51897,7 +55749,6 @@ "supports_vision": true }, "watsonx/meta-llama/llama-3-2-1b-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1e-07, @@ -51909,7 +55760,6 @@ "supports_vision": false }, "watsonx/meta-llama/llama-3-2-3b-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1.5e-07, @@ -51921,7 +55771,6 @@ "supports_vision": false }, "watsonx/meta-llama/llama-3-2-90b-vision-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-06, @@ -51933,7 +55782,6 @@ "supports_vision": true }, "watsonx/meta-llama/llama-3-3-70b-instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 7.526e-07, @@ -51946,7 +55794,6 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/meta-llama/llama-4-maverick-17b": { - "max_tokens": 8192, "max_input_tokens": 131072, "max_output_tokens": 8192, "input_cost_per_token": 3.71e-07, @@ -51959,7 +55806,6 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8": { - "max_tokens": 8192, "max_input_tokens": 131072, "max_output_tokens": 8192, "input_cost_per_token": 3.71e-07, @@ -51972,7 +55818,6 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/meta-llama/llama-guard-3-11b-vision": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 3.5e-07, @@ -51984,7 +55829,6 @@ "supports_vision": true }, "watsonx/mistralai/mistral-medium-2505": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 3e-06, @@ -51996,7 +55840,6 @@ "supports_vision": false }, "watsonx/mistralai/mistral-small-2503": { - "max_tokens": 32000, "max_input_tokens": 32000, "max_output_tokens": 32000, "input_cost_per_token": 1e-07, @@ -52008,7 +55851,6 @@ "supports_vision": false }, "watsonx/mistralai/mistral-small-3-1-24b-instruct-2503": { - "max_tokens": 16384, "max_input_tokens": 131072, "max_output_tokens": 16384, "input_cost_per_token": 1.06e-07, @@ -52021,7 +55863,6 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/mistralai/pixtral-12b-2409": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 3.5e-07, @@ -52033,7 +55874,6 @@ "supports_vision": true }, "watsonx/openai/gpt-oss-120b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.59e-07, @@ -52046,7 +55886,6 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/sdaia/allam-1-13b-instruct": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 1.8e-06, @@ -52075,6 +55914,8 @@ "/v1/audio/transcriptions" ], "deprecation_date": "2027-02-26", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-live-transcribe", "source": "https://developers.openai.com/api/docs/pricing" }, "xai/grok-4.20-multi-agent-beta-0309": { @@ -52083,7 +55924,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -52108,7 +55948,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -52132,7 +55971,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, @@ -52158,7 +55996,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -52184,9 +56021,10 @@ "input_cost_per_token_above_200k_tokens_batches": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", + "token_count_framing": 185, + "token_count_tool_framing": 214, "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, @@ -52214,7 +56052,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, @@ -52238,7 +56075,6 @@ "litellm_provider": "xai", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, @@ -52260,7 +56096,6 @@ "litellm_provider": "xai", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, @@ -52282,7 +56117,6 @@ "litellm_provider": "xai", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, @@ -52304,7 +56138,6 @@ "litellm_provider": "xai", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, @@ -52320,16 +56153,21 @@ "xai/grok-4.7": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "cache_read_input_token_cost_above_200k_tokens_batches": 8e-07, + "cache_read_input_token_cost_batches": 4e-07, "input_cost_per_image_token": 2e-06, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, + "input_cost_per_token_above_200k_tokens_batches": 3.2e-06, + "input_cost_per_token_batches": 1.6e-06, "litellm_provider": "xai", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, + "output_cost_per_token_above_200k_tokens_batches": 9.6e-06, + "output_cost_per_token_batches": 4.8e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, @@ -52339,54 +56177,77 @@ "supports_vision": true, "supports_web_search": true }, + "xai/grok-latest": { + "alias_of": "xai/grok-4.7" + }, "zai.glm-4.7": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "zai.glm-5", "input_cost_per_token": 6e-07, + "input_cost_per_token_batches": 3e-07, + "input_cost_per_token_flex": 3e-07, + "input_cost_per_token_priority": 1.05e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 203000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-06, + "output_cost_per_token_batches": 1.1e-06, + "output_cost_per_token_flex": 1.1e-06, + "output_cost_per_token_priority": 3.85e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "zai.glm-5": { "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, + "input_cost_per_token_flex": 5e-07, + "input_cost_per_token_priority": 1.75e-06, "output_cost_per_token": 3.2e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", + "output_cost_per_token_batches": 1.6e-06, + "output_cost_per_token_flex": 1.6e-06, + "output_cost_per_token_priority": 5.6e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "zai.glm-4.7-flash": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 7e-08, + "input_cost_per_token_batches": 3.5e-08, + "input_cost_per_token_flex": 3.5e-08, + "input_cost_per_token_priority": 1.225e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 203000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07, + "output_cost_per_token_flex": 2e-07, + "output_cost_per_token_priority": 7e-07, "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false @@ -52419,8 +56280,12 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true }, + "zai/glm-latest": { + "alias_of": "zai/glm-5.3" + }, "zai/glm-5.3-flash": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 3e-08, @@ -52433,10 +56298,29 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing", "supports_vision": true }, + "zai/glm-flash-latest": { + "alias_of": "zai/glm-5.3-flash" + }, + "zai/glm-5v-turbo": { + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 1.2e-06, + "litellm_provider": "zai", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://vercel.com/ai-gateway/models/glm-5v-turbo", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, "zai/glm-5.1": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 2.6e-07, @@ -52595,6 +56479,70 @@ "litellm_provider": "vertex_ai", "mode": "vector_store" }, + "vertex_ai/semantic-ranker-default": { + "input_cost_per_query": 0.001, + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai", + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/generative-ai-app-builder/pricing" + }, + "vertex_ai/semantic-ranker-default-002": { + "input_cost_per_query": 0.001, + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai", + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/generative-ai-app-builder/pricing" + }, + "vertex_ai/semantic-ranker-default-003": { + "input_cost_per_query": 0.001, + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai", + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/generative-ai-app-builder/pricing" + }, + "vertex_ai/semantic-ranker-default-004": { + "input_cost_per_query": 0.001, + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai", + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/generative-ai-app-builder/pricing" + }, + "vertex_ai/semantic-ranker-default@latest": { + "input_cost_per_query": 0.001, + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai", + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/generative-ai-app-builder/pricing" + }, + "vertex_ai/semantic-ranker-fast": { + "input_cost_per_query": 0.001, + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai", + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/generative-ai-app-builder/pricing" + }, + "vertex_ai/semantic-ranker-fast-004": { + "input_cost_per_query": 0.001, + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai", + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/generative-ai-app-builder/pricing" + }, + "vertex_ai/semantic-ranker-fast@latest": { + "input_cost_per_query": 0.001, + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai", + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/generative-ai-app-builder/pricing" + }, "openai/container": { "code_interpreter_cost_per_session": 0.03, "litellm_provider": "openai", @@ -52602,6 +56550,7 @@ }, "openai/sora-2": { "deprecation_date": "2026-09-24", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "litellm_provider": "openai", "mode": "video_generation", "output_cost_per_video_per_second": 0.1, @@ -52616,6 +56565,7 @@ }, "openai/sora-2-pro": { "deprecation_date": "2026-09-24", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "litellm_provider": "openai", "mode": "video_generation", "output_cost_per_video_per_second": 0.3, @@ -52631,6 +56581,7 @@ "openai/sora-2-pro-high-res": { "litellm_provider": "openai", "deprecation_date": "2026-09-24", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "mode": "video_generation", "output_cost_per_video_per_second": 0.5, "source": "https://platform.openai.com/docs/api-reference/videos", @@ -52643,7 +56594,7 @@ ] }, "azure/sora-2": { - "deprecation_date": "2026-10-15", + "deprecation_date": "2026-11-02", "litellm_provider": "azure", "mode": "video_generation", "output_cost_per_video_per_second": 0.1, @@ -52730,7 +56681,7 @@ "runwayml/seedance2": { "litellm_provider": "runwayml", "mode": "video_generation", - "output_cost_per_second": 0.36, + "output_cost_per_second": 0.3, "output_cost_per_second_1080p": 0.4, "output_cost_per_second_4k": 1.5, "source": "https://docs.dev.runwayml.com/guides/pricing/", @@ -52742,14 +56693,13 @@ "supported_output_modalities": [ "video" ], - "metadata": { - "comment": "36 credits per second at 480p/720p, 40 at 1080p, 150 at 4K @ $0.01 per credit" - } + "metadata": {"comment":"14/30/40/150 credits per second at 480p/720p/1080p/4K @ $0.01 per credit; 56 credit minimum per generation not modeled"}, + "output_cost_per_second_480p": 0.14 }, "runwayml/seedance2_fast": { "litellm_provider": "runwayml", "mode": "video_generation", - "output_cost_per_second": 0.29, + "output_cost_per_second": 0.24, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", @@ -52759,14 +56709,13 @@ "supported_output_modalities": [ "video" ], - "metadata": { - "comment": "29 credits per second at 480p/720p @ $0.01 per credit = $0.29 per second" - } + "metadata": {"comment":"11 credits per second at 480p, 24 at 720p @ $0.01 per credit; 44 credit minimum per generation not modeled"}, + "output_cost_per_second_480p": 0.11 }, "runwayml/seedance2_mini": { "litellm_provider": "runwayml", "mode": "video_generation", - "output_cost_per_second": 0.16, + "output_cost_per_second": 0.15, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", @@ -52776,9 +56725,8 @@ "supported_output_modalities": [ "video" ], - "metadata": { - "comment": "16 credits per second @ $0.01 per credit = $0.16 per second; 64 credit minimum per task not modeled" - } + "metadata": {"comment":"7 credits per second at 480p, 15 at 720p @ $0.01 per credit; 28 credit minimum per generation not modeled"}, + "output_cost_per_second_480p": 0.07 }, "runwayml/seedance2_5": { "litellm_provider": "runwayml", @@ -52903,14 +56851,11 @@ "runwayml/eleven_multilingual_v2": { "litellm_provider": "runwayml", "mode": "audio_speech", - "input_cost_per_character": 3e-07, + "input_cost_per_character": 0.0002, "source": "https://docs.dev.runwayml.com/guides/pricing/", - "metadata": { - "comment": "Estimated cost based on standard TTS pricing. RunwayML uses ElevenLabs models." - } + "metadata": {"comment":"1 credit per 50 characters @ $0.01 per credit = $0.0002 per character"} }, "fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-a35b-instruct": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 4.5e-07, @@ -52920,7 +56865,6 @@ "supports_reasoning": true }, "fireworks_ai/accounts/fireworks/models/flux-kontext-pro": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 4e-08, @@ -52929,7 +56873,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/SSD-1B": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.3e-10, @@ -52938,7 +56881,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/chronos-hermes-13b-v2": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -52947,7 +56889,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-13b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -52956,7 +56897,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-13b-instruct": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -52965,7 +56905,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-13b-python": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -52974,7 +56913,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-34b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -52983,7 +56921,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-34b-instruct": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -52992,7 +56929,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-34b-python": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -53001,7 +56937,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-70b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -53010,7 +56945,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-70b-instruct": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -53019,7 +56953,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-70b-python": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -53028,7 +56961,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-7b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -53037,7 +56969,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-7b-instruct": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -53046,7 +56977,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-7b-python": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -53055,7 +56985,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-qwen-1p5-7b": { - "max_tokens": 65536, "max_input_tokens": 65536, "max_output_tokens": 65536, "input_cost_per_token": 2e-07, @@ -53064,7 +56993,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/codegemma-2b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 1e-07, @@ -53073,7 +57001,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/codegemma-7b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -53082,7 +57009,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-671b-v2-p1": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 1.2e-06, @@ -53091,7 +57017,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-3b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -53100,7 +57025,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-70b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -53109,7 +57033,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-8b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -53118,7 +57041,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-14b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -53127,7 +57049,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-32b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -53136,7 +57057,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/flux-kontext-max": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 8e-08, @@ -53145,7 +57065,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/dbrx-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1.2e-06, @@ -53154,7 +57073,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-1b-base": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 1e-07, @@ -53163,7 +57081,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-33b-instruct": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -53172,7 +57089,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -53181,7 +57097,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base-v1p5": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -53190,7 +57105,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-instruct-v1p5": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -53199,7 +57113,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-base": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 5e-07, @@ -53208,7 +57121,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-instruct": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 5e-07, @@ -53217,7 +57129,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-prover-v2": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 1.2e-06, @@ -53226,7 +57137,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528-distill-qwen3-8b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -53235,7 +57145,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-70b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -53244,7 +57153,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-8b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -53253,7 +57161,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-14b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -53262,7 +57169,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-1p5b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -53271,7 +57177,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-32b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -53280,7 +57185,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-7b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -53289,7 +57193,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-v2-lite-chat": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 5e-07, @@ -53298,7 +57201,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-v2p5": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1.2e-06, @@ -53307,7 +57209,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/devstral-small-2505": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -53316,7 +57217,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/dobby-mini-unhinged-plus-llama-3-1-8b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -53325,7 +57225,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/dobby-unhinged-llama-3-3-70b-new": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -53334,7 +57233,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/dolphin-2-9-2-qwen2-72b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -53343,7 +57241,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/dolphin-2p6-mixtral-8x7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-07, @@ -53352,8 +57249,7 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/ernie-4p5-21b-a3b-pt": { - "max_tokens": 4096, - "max_input_tokens": 4096, + "max_input_tokens": 131072, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, @@ -53361,8 +57257,7 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/ernie-4p5-300b-a47b-pt": { - "max_tokens": 4096, - "max_input_tokens": 4096, + "max_input_tokens": 131072, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, @@ -53370,7 +57265,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/fare-20b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -53379,7 +57273,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/firefunction-v1": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-07, @@ -53388,7 +57281,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/firellava-13b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -53397,7 +57289,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/firesearch-ocr-v6": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -53406,7 +57297,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/fireworks-asr-large": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 0.0, @@ -53415,7 +57305,6 @@ "mode": "audio_transcription" }, "fireworks_ai/accounts/fireworks/models/fireworks-asr-v2": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 0.0, @@ -53424,7 +57313,6 @@ "mode": "audio_transcription" }, "fireworks_ai/accounts/fireworks/models/flux-1-dev": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -53433,7 +57321,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/flux-1-dev-controlnet-union": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-09, @@ -53442,7 +57329,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/flux-1-dev-fp8": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 5e-10, @@ -53451,7 +57337,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/flux-1-schnell": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -53460,7 +57345,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/flux-1-schnell-fp8": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 3.5e-10, @@ -53469,7 +57353,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/gemma-2b-it": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 1e-07, @@ -53478,7 +57361,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/gemma-3-27b-it": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -53487,7 +57369,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/gemma-7b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -53496,7 +57377,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/gemma-7b-it": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -53505,7 +57385,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/gemma2-9b-it": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -53514,7 +57393,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/glm-4p5v": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.2e-06, @@ -53524,7 +57402,6 @@ "supports_reasoning": true }, "fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-120b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.2e-06, @@ -53533,7 +57410,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-20b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5e-07, @@ -53542,7 +57418,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/hermes-2-pro-mistral-7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -53551,7 +57426,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/internvl3-38b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -53560,7 +57434,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/internvl3-78b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -53569,7 +57442,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/internvl3-8b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -53578,7 +57450,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/japanese-stable-diffusion-xl": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.3e-10, @@ -53587,7 +57458,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/kat-coder": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9e-07, @@ -53596,7 +57466,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/kat-dev-32b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -53605,7 +57474,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/kat-dev-72b-exp": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -53614,7 +57482,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-guard-2-8b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -53623,7 +57490,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-guard-3-1b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -53632,7 +57498,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-guard-3-8b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -53641,7 +57506,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-13b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -53650,7 +57514,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-13b-chat": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -53659,7 +57522,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-70b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -53668,7 +57530,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-70b-chat": { - "max_tokens": 2048, "max_input_tokens": 2048, "max_output_tokens": 2048, "input_cost_per_token": 9e-07, @@ -53677,7 +57538,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-7b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -53686,7 +57546,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-7b-chat": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -53695,7 +57554,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 9e-07, @@ -53704,7 +57562,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct-hf": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 9e-07, @@ -53713,7 +57570,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3-8b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -53722,7 +57578,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3-8b-instruct-hf": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -53731,7 +57586,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct-long": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -53740,7 +57594,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -53749,7 +57602,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct-1b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -53758,7 +57610,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p1-nemotron-70b-instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -53767,7 +57618,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -53776,7 +57626,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -53785,7 +57634,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p3-70b-instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -53794,7 +57642,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llamaguard-7b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -53803,7 +57650,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llava-yi-34b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -53812,7 +57658,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/minimax-m1-80k": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -53821,8 +57666,7 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/minimax-m2": { - "max_tokens": 4096, - "max_input_tokens": 4096, + "max_input_tokens": 196608, "max_output_tokens": 4096, "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, @@ -53830,7 +57674,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/ministral-3-14b-instruct-2512": { - "max_tokens": 256000, "max_input_tokens": 256000, "max_output_tokens": 256000, "input_cost_per_token": 2e-07, @@ -53839,7 +57682,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/ministral-3-3b-instruct-2512": { - "max_tokens": 256000, "max_input_tokens": 256000, "max_output_tokens": 256000, "input_cost_per_token": 1e-07, @@ -53848,7 +57690,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/ministral-3-8b-instruct-2512": { - "max_tokens": 256000, "max_input_tokens": 256000, "max_output_tokens": 256000, "input_cost_per_token": 2e-07, @@ -53857,7 +57698,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -53866,7 +57706,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-4k": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -53875,7 +57714,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v0p2": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -53884,7 +57722,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v3": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -53893,7 +57730,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-7b-v0p2": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -53902,7 +57738,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-large-3-fp8": { - "max_tokens": 256000, "max_input_tokens": 256000, "max_output_tokens": 256000, "input_cost_per_token": 1.2e-06, @@ -53911,7 +57746,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-nemo-base-2407": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-07, @@ -53920,7 +57754,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-nemo-instruct-2407": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-07, @@ -53929,7 +57762,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-small-24b-instruct-2501": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -53938,7 +57770,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x22b": { - "max_tokens": 65536, "max_input_tokens": 65536, "max_output_tokens": 65536, "input_cost_per_token": 1.2e-06, @@ -53947,7 +57778,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct": { - "max_tokens": 65536, "max_input_tokens": 65536, "max_output_tokens": 65536, "input_cost_per_token": 1.2e-06, @@ -53956,7 +57786,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-07, @@ -53965,7 +57794,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-07, @@ -53974,7 +57802,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct-hf": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-07, @@ -53983,7 +57810,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mythomax-l2-13b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -53992,8 +57818,7 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nemotron-nano-v2-12b-vl": { - "max_tokens": 4096, - "max_input_tokens": 4096, + "max_input_tokens": 131072, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, @@ -54001,7 +57826,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-capybara-7b-v1p9": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -54010,7 +57834,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-hermes-2-mixtral-8x7b-dpo": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-07, @@ -54019,7 +57842,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-hermes-2-yi-34b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -54028,7 +57850,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-13b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -54037,7 +57858,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-70b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -54046,7 +57866,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-7b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -54055,8 +57874,7 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-12b-v2": { - "max_tokens": 131072, - "max_input_tokens": 131072, + "max_input_tokens": 128000, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, @@ -54064,8 +57882,7 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-9b-v2": { - "max_tokens": 131072, - "max_input_tokens": 131072, + "max_input_tokens": 128000, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, @@ -54073,7 +57890,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/openchat-3p5-0106-7b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -54082,7 +57898,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/openhermes-2-mistral-7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -54091,7 +57906,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/openhermes-2p5-mistral-7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -54100,7 +57914,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/openorca-7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -54109,7 +57922,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phi-2-3b": { - "max_tokens": 2048, "max_input_tokens": 2048, "max_output_tokens": 2048, "input_cost_per_token": 1e-07, @@ -54118,7 +57930,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phi-3-mini-128k-instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -54127,7 +57938,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phi-3-vision-128k-instruct": { - "max_tokens": 32064, "max_input_tokens": 32064, "max_output_tokens": 32064, "input_cost_per_token": 2e-07, @@ -54136,7 +57946,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-python-v1": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -54145,7 +57954,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v1": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -54154,7 +57962,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v2": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -54163,7 +57970,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/playground-v2-1024px-aesthetic": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.3e-10, @@ -54172,7 +57978,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/playground-v2-5-1024px-aesthetic": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.3e-10, @@ -54181,7 +57986,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/pythia-12b": { - "max_tokens": 2048, "max_input_tokens": 2048, "max_output_tokens": 2048, "input_cost_per_token": 2e-07, @@ -54190,7 +57994,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen-qwq-32b-preview": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -54199,7 +58002,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen-v2p5-14b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -54208,7 +58010,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen-v2p5-7b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -54217,7 +58018,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen1p5-72b-chat": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -54226,7 +58026,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2-7b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -54235,7 +58034,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2-vl-2b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -54244,7 +58042,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2-vl-72b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -54253,7 +58050,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2-vl-7b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -54262,7 +58058,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-0p5b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -54271,7 +58066,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-14b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -54280,7 +58074,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-1p5b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -54289,7 +58082,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-32b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -54298,7 +58090,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-32b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -54307,7 +58098,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-72b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -54316,7 +58106,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-72b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -54325,7 +58114,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-7b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -54334,7 +58122,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -54343,7 +58130,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -54352,7 +58138,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -54361,7 +58146,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -54370,7 +58154,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -54379,7 +58162,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -54388,7 +58170,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -54397,7 +58178,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-128k": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -54406,7 +58186,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-32k-rope": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -54415,7 +58194,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-64k": { - "max_tokens": 65536, "max_input_tokens": 65536, "max_output_tokens": 65536, "input_cost_per_token": 9e-07, @@ -54424,7 +58202,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -54433,7 +58210,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -54442,7 +58218,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -54451,7 +58226,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -54460,7 +58234,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-math-72b-instruct": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -54469,7 +58242,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-32b-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 9e-07, @@ -54478,7 +58250,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-3b-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-07, @@ -54487,7 +58258,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-72b-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 9e-07, @@ -54496,7 +58266,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-7b-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-07, @@ -54505,7 +58274,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-0p6b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1e-07, @@ -54514,7 +58282,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-14b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 2e-07, @@ -54523,7 +58290,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-1p7b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -54532,7 +58298,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1e-07, @@ -54541,7 +58306,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-131072": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -54550,7 +58314,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-40960": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1e-07, @@ -54559,7 +58322,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2.2e-07, @@ -54568,7 +58330,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-instruct-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.2e-07, @@ -54577,7 +58338,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-thinking-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.2e-07, @@ -54586,7 +58346,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.5e-07, @@ -54595,7 +58354,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-instruct-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 5e-07, @@ -54604,7 +58362,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-thinking-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9e-07, @@ -54613,7 +58370,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-32b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -54623,7 +58379,6 @@ "supports_reasoning": true }, "fireworks_ai/accounts/fireworks/models/qwen3-4b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 2e-07, @@ -54632,7 +58387,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-4b-instruct-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2e-07, @@ -54641,7 +58395,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-8b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 2e-07, @@ -54651,7 +58404,6 @@ "supports_reasoning": true }, "fireworks_ai/accounts/fireworks/models/qwen3-coder-30b-a3b-instruct": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -54660,8 +58412,7 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-instruct-bf16": { - "max_tokens": 4096, - "max_input_tokens": 4096, + "max_input_tokens": 262144, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, @@ -54669,7 +58420,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-embedding-0p6b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 0.0, @@ -54678,7 +58428,6 @@ "mode": "embedding" }, "fireworks_ai/accounts/fireworks/models/qwen3-embedding-4b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 0.0, @@ -54686,17 +58435,7 @@ "litellm_provider": "fireworks_ai", "mode": "embedding" }, - "fireworks_ai/accounts/fireworks/models/": { - "max_tokens": 40960, - "max_input_tokens": 40960, - "max_output_tokens": 40960, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "fireworks_ai", - "mode": "embedding" - }, "fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-instruct": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -54705,7 +58444,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-thinking": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -54714,7 +58452,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-reranker-0p6b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 0.0, @@ -54723,7 +58460,6 @@ "mode": "rerank" }, "fireworks_ai/accounts/fireworks/models/qwen3-reranker-4b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 0.0, @@ -54732,17 +58468,15 @@ "mode": "rerank" }, "fireworks_ai/accounts/fireworks/models/qwen3-reranker-8b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 2e-07, "output_cost_per_token": 0.0, "litellm_provider": "fireworks_ai", "mode": "rerank", - "source": "https://api.fireworks.ai/v1/serverless/models" + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-instruct": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.2e-07, @@ -54751,7 +58485,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-thinking": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.2e-07, @@ -54760,7 +58493,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-instruct": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -54769,7 +58501,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-thinking": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -54778,7 +58509,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-32b-instruct": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -54787,8 +58517,7 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-8b-instruct": { - "max_tokens": 4096, - "max_input_tokens": 4096, + "max_input_tokens": 262144, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, @@ -54801,7 +58530,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://api.fireworks.ai/v1/serverless/models", @@ -54812,7 +58540,6 @@ "supports_vision": true }, "fireworks_ai/accounts/fireworks/models/qwq-32b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -54821,7 +58548,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/rolm-ocr": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-07, @@ -54830,7 +58556,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/snorkel-mistral-7b-pairrm-dpo": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -54839,7 +58564,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/stable-diffusion-xl-1024-v1-0": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.3e-10, @@ -54848,7 +58572,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/stablecode-3b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -54857,7 +58580,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/starcoder-16b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -54866,7 +58588,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/starcoder-7b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -54875,7 +58596,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/starcoder2-15b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -54884,7 +58604,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/starcoder2-3b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 1e-07, @@ -54893,7 +58612,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/starcoder2-7b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -54902,7 +58620,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/toppy-m-7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -54911,7 +58628,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/yi-34b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -54920,7 +58636,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/yi-34b-200k-capybara": { - "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 9e-07, @@ -54929,7 +58644,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/yi-34b-chat": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -54938,7 +58652,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/yi-6b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -54947,7 +58660,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/zephyr-7b-beta": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -54961,7 +58673,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 202800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8.8e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -54974,14 +58685,15 @@ "fireworks_ai/accounts/fireworks/routers/kimi-k2p6-fast": { "cache_read_input_token_cost": 3e-07, "deprecation_date": "2026-08-27", + "deprecation_source": "https://docs.fireworks.ai/changelog.md", "input_cost_per_token": 2e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://docs.fireworks.ai/changelog.md", + "successor_model": "fireworks_ai/accounts/fireworks/models/kimi-k2p6", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -54991,14 +58703,15 @@ "fireworks_ai/accounts/fireworks/routers/kimi-k2p7-code-fast": { "cache_read_input_token_cost": 3.8e-07, "deprecation_date": "2026-08-27", + "deprecation_source": "https://docs.fireworks.ai/changelog.md", "input_cost_per_token": 1.9e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://docs.fireworks.ai/changelog.md", + "successor_model": "fireworks_ai/accounts/fireworks/models/kimi-k2p7-code", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -55010,7 +58723,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3.6e-06, "supports_function_calling": true, @@ -55022,7 +58734,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-06, "supports_function_calling": true, @@ -55034,7 +58745,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.25e-06, "supports_function_calling": true @@ -55050,7 +58760,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 128000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-07, "supports_function_calling": true, @@ -55061,7 +58770,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 128000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true @@ -55077,7 +58785,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 5e-07, "supports_function_calling": true, @@ -55089,7 +58796,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 7.5e-06, "supports_reasoning": true, @@ -55102,7 +58808,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 128000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3.5e-07, "supports_function_calling": true, @@ -55113,7 +58818,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-07, "supports_vision": true, @@ -55131,7 +58835,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 9e-07, "supports_function_calling": true @@ -55143,7 +58846,6 @@ "output_cost_per_token": 4e-07, "max_input_tokens": 163840, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55160,7 +58862,6 @@ "output_cost_per_token": 1.2e-06, "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55176,7 +58877,6 @@ "output_cost_per_token": 2.2e-06, "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55193,7 +58893,6 @@ "output_cost_per_token": 3.3e-07, "max_input_tokens": 262144, "max_output_tokens": 32000, - "max_tokens": 32000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55210,7 +58909,6 @@ "output_cost_per_token": 1.38e-07, "max_input_tokens": 65536, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_vision": true, "supports_system_messages": true }, @@ -55221,7 +58919,6 @@ "output_cost_per_token": 2.5e-06, "max_input_tokens": 262144, "max_output_tokens": 100352, - "max_tokens": 100352, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55238,7 +58935,6 @@ "output_cost_per_token": 1.2e-06, "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55255,7 +58951,6 @@ "output_cost_per_token": 2e-08, "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_vision": true, "supports_system_messages": true }, @@ -55266,7 +58961,6 @@ "output_cost_per_token": 4.1e-07, "max_input_tokens": 163840, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55281,7 +58975,6 @@ "output_cost_per_token": 3.95e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_vision": true, "supports_system_messages": true, "supports_reasoning": true, @@ -55295,7 +58988,6 @@ "output_cost_per_token": 9e-07, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55313,7 +59005,6 @@ "output_cost_per_token": 2.2e-06, "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55330,7 +59021,6 @@ "output_cost_per_token": 1.2e-06, "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55346,7 +59036,6 @@ "output_cost_per_token": 1.5e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55361,7 +59050,6 @@ "output_cost_per_token": 1.5e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55376,7 +59064,6 @@ "output_cost_per_token": 3e-08, "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, @@ -55389,7 +59076,6 @@ "output_cost_per_token": 1e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55406,7 +59092,6 @@ "output_cost_per_token": 1.5e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55421,7 +59106,6 @@ "output_cost_per_token": 8.45e-06, "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55435,7 +59119,6 @@ "output_cost_per_token": 6e-07, "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, @@ -55448,7 +59131,6 @@ "output_cost_per_token": 1e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55465,7 +59147,6 @@ "output_cost_per_token": 2.5e-06, "max_input_tokens": 262144, "max_output_tokens": 100352, - "max_tokens": 100352, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55479,7 +59160,6 @@ "output_cost_per_token": 1.55e-06, "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55493,7 +59173,6 @@ "output_cost_per_token": 2.7e-07, "max_input_tokens": 160000, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55507,7 +59186,6 @@ "output_cost_per_token": 2.5e-07, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55523,7 +59201,6 @@ "output_cost_per_token": 2.3e-06, "max_input_tokens": 131072, "max_output_tokens": 100352, - "max_tokens": 100352, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55537,7 +59214,6 @@ "output_cost_per_token": 1.12e-06, "max_input_tokens": 163840, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55553,7 +59229,6 @@ "output_cost_per_token": 2.2e-06, "max_input_tokens": 131072, "max_output_tokens": 98304, - "max_tokens": 98304, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55569,7 +59244,6 @@ "output_cost_per_token": 3e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55583,7 +59257,6 @@ "output_cost_per_token": 5e-08, "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_system_messages": true, "supports_response_schema": true }, @@ -55594,7 +59267,6 @@ "output_cost_per_token": 1e-07, "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, @@ -55607,7 +59279,6 @@ "output_cost_per_token": 1.8e-06, "max_input_tokens": 65536, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55625,7 +59296,6 @@ "output_cost_per_token": 1.5e-07, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_tool_choice": true, "supports_vision": false, "supports_system_messages": true, @@ -55639,7 +59309,6 @@ "output_cost_per_token": 5.8e-07, "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55653,7 +59322,6 @@ "output_cost_per_token": 1.5e-07, "max_input_tokens": 32768, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, @@ -55666,7 +59334,6 @@ "output_cost_per_token": 4e-07, "max_input_tokens": 12288, "max_output_tokens": 12288, - "max_tokens": 12288, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55680,7 +59347,6 @@ "output_cost_per_token": 4e-07, "max_input_tokens": 32000, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55694,7 +59360,6 @@ "output_cost_per_token": 1.7e-07, "max_input_tokens": 60288, "max_output_tokens": 16000, - "max_tokens": 16000, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true @@ -55706,7 +59371,6 @@ "output_cost_per_token": 2.2e-06, "max_input_tokens": 1000000, "max_output_tokens": 40000, - "max_tokens": 40000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55721,7 +59385,6 @@ "output_cost_per_token": 2.5e-06, "max_input_tokens": 163840, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55738,7 +59401,6 @@ "output_cost_per_token": 3e-07, "max_input_tokens": 64000, "max_output_tokens": 32000, - "max_tokens": 32000, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, @@ -55751,7 +59413,6 @@ "output_cost_per_token": 4e-08, "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_system_messages": true, "supports_response_schema": true }, @@ -55762,7 +59423,6 @@ "output_cost_per_token": 6.2e-07, "max_input_tokens": 65535, "max_output_tokens": 8000, - "max_tokens": 8000, "supports_system_messages": true, "supports_response_schema": true }, @@ -55773,7 +59433,6 @@ "output_cost_per_token": 9e-08, "max_input_tokens": 128000, "max_output_tokens": 32000, - "max_tokens": 32000, "supports_system_messages": true, "supports_reasoning": true }, @@ -55784,7 +59443,6 @@ "output_cost_per_token": 8e-07, "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, @@ -55797,7 +59455,6 @@ "output_cost_per_token": 7.4e-07, "max_input_tokens": 8192, "max_output_tokens": 8000, - "max_tokens": 8000, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true @@ -55809,7 +59466,6 @@ "output_cost_per_token": 8e-07, "max_input_tokens": 40960, "max_output_tokens": 20000, - "max_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true, "supports_response_schema": true @@ -55821,7 +59477,6 @@ "output_cost_per_token": 8.5e-07, "max_input_tokens": 1048576, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true @@ -55833,7 +59488,6 @@ "output_cost_per_token": 5.9e-07, "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "supports_vision": true, "supports_system_messages": true }, @@ -55844,7 +59498,6 @@ "output_cost_per_token": 1.4e-07, "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true @@ -55856,7 +59509,6 @@ "output_cost_per_token": 8e-07, "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_vision": true, "supports_system_messages": true }, @@ -55867,7 +59519,6 @@ "output_cost_per_token": 1.48e-06, "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55880,7 +59531,6 @@ "output_cost_per_token": 2.8e-07, "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_system_messages": true, "supports_reasoning": true }, @@ -55891,7 +59541,6 @@ "output_cost_per_token": 5e-08, "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true @@ -55903,7 +59552,6 @@ "output_cost_per_token": 7e-08, "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "supports_system_messages": true }, "novita/baidu/ernie-4.5-vl-424b-a47b": { @@ -55913,7 +59561,6 @@ "output_cost_per_token": 1.25e-06, "max_input_tokens": 123000, "max_output_tokens": 16000, - "max_tokens": 16000, "supports_vision": true, "supports_system_messages": true, "supports_reasoning": true @@ -55925,7 +59572,6 @@ "output_cost_per_token": 1.1e-06, "max_input_tokens": 123000, "max_output_tokens": 12000, - "max_tokens": 12000, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true @@ -55937,7 +59583,6 @@ "output_cost_per_token": 2.5e-06, "max_input_tokens": 160000, "max_output_tokens": 160000, - "max_tokens": 160000, "supports_system_messages": true }, "novita/qwen/qwen3-32b-fp8": { @@ -55947,7 +59592,6 @@ "output_cost_per_token": 4.5e-07, "max_input_tokens": 40960, "max_output_tokens": 20000, - "max_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true }, @@ -55958,7 +59602,6 @@ "output_cost_per_token": 4.5e-07, "max_input_tokens": 40960, "max_output_tokens": 20000, - "max_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true, "supports_function_calling": true, @@ -55971,7 +59614,6 @@ "output_cost_per_token": 2e-07, "max_input_tokens": 98304, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_vision": true, "supports_system_messages": true }, @@ -55982,7 +59624,6 @@ "output_cost_per_token": 1.3e-06, "max_input_tokens": 64000, "max_output_tokens": 16000, - "max_tokens": 16000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55995,7 +59636,6 @@ "output_cost_per_token": 2.5e-06, "max_input_tokens": 64000, "max_output_tokens": 16000, - "max_tokens": 16000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -56010,7 +59650,6 @@ "output_cost_per_token": 5e-08, "max_input_tokens": 8192, "max_output_tokens": 32000, - "max_tokens": 32000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -56023,7 +59662,6 @@ "output_cost_per_token": 9e-08, "max_input_tokens": 4096, "max_output_tokens": 3200, - "max_tokens": 3200, "supports_system_messages": true }, "novita/baidu/ernie-4.5-vl-28b-a3b-thinking": { @@ -56033,7 +59671,6 @@ "output_cost_per_token": 3.9e-07, "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -56049,7 +59686,6 @@ "output_cost_per_token": 5e-07, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -56064,7 +59700,6 @@ "output_cost_per_token": 8.5e-07, "max_input_tokens": 131072, "max_output_tokens": 98304, - "max_tokens": 98304, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -56080,7 +59715,6 @@ "output_cost_per_token": 7e-07, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -56095,7 +59729,6 @@ "output_cost_per_token": 1e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -56110,7 +59743,6 @@ "output_cost_per_token": 9.7e-07, "max_input_tokens": 65536, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -56127,7 +59759,6 @@ "output_cost_per_token": 9.7e-07, "max_input_tokens": 65536, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -56144,7 +59775,6 @@ "output_cost_per_token": 7.5e-07, "max_input_tokens": 16384, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_system_messages": true }, "novita/baidu/ernie-4.5-vl-28b-a3b": { @@ -56154,7 +59784,6 @@ "output_cost_per_token": 5.6e-07, "max_input_tokens": 30000, "max_output_tokens": 8000, - "max_tokens": 8000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -56169,7 +59798,6 @@ "output_cost_per_token": 2.8e-07, "max_input_tokens": 120000, "max_output_tokens": 8000, - "max_tokens": 8000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -56182,7 +59810,6 @@ "output_cost_per_token": 1.38e-07, "max_input_tokens": 128000, "max_output_tokens": 20000, - "max_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true }, @@ -56193,7 +59820,6 @@ "output_cost_per_token": 3e-08, "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_system_messages": true, "supports_reasoning": true, "supports_function_calling": true, @@ -56206,7 +59832,6 @@ "output_cost_per_token": 7e-08, "max_input_tokens": 32000, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -56220,7 +59845,6 @@ "output_cost_per_token": 5e-08, "max_input_tokens": 32768, "max_output_tokens": 32000, - "max_tokens": 32000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -56233,7 +59857,6 @@ "output_cost_per_token": 1.48e-06, "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -56245,8 +59868,7 @@ "input_cost_per_token": 7e-08, "output_cost_per_token": 0, "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768 + "max_output_tokens": 32768 }, "novita/qwen/qwen3-embedding-8b": { "litellm_provider": "novita", @@ -56254,8 +59876,7 @@ "input_cost_per_token": 7e-08, "output_cost_per_token": 0, "max_input_tokens": 32768, - "max_output_tokens": 4096, - "max_tokens": 4096 + "max_output_tokens": 4096 }, "novita/baai/bge-m3": { "litellm_provider": "novita", @@ -56263,8 +59884,7 @@ "input_cost_per_token": 1e-08, "output_cost_per_token": 1e-08, "max_input_tokens": 8192, - "max_output_tokens": 96000, - "max_tokens": 96000 + "max_output_tokens": 96000 }, "novita/qwen/qwen3-reranker-8b": { "litellm_provider": "novita", @@ -56272,8 +59892,7 @@ "input_cost_per_token": 5e-08, "output_cost_per_token": 5e-08, "max_input_tokens": 32768, - "max_output_tokens": 4096, - "max_tokens": 4096 + "max_output_tokens": 4096 }, "novita/baai/bge-reranker-v2-m3": { "litellm_provider": "novita", @@ -56281,11 +59900,9 @@ "input_cost_per_token": 1e-08, "output_cost_per_token": 1e-08, "max_input_tokens": 8000, - "max_output_tokens": 8000, - "max_tokens": 8000 + "max_output_tokens": 8000 }, "llamagate/llama-3.1-8b": { - "max_tokens": 8192, "max_input_tokens": 131072, "max_output_tokens": 8192, "input_cost_per_token": 3e-08, @@ -56296,7 +59913,6 @@ "supports_response_schema": true }, "llamagate/llama-3.2-3b": { - "max_tokens": 8192, "max_input_tokens": 131072, "max_output_tokens": 8192, "input_cost_per_token": 4e-08, @@ -56307,7 +59923,6 @@ "supports_response_schema": true }, "llamagate/mistral-7b-v0.3": { - "max_tokens": 8192, "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_token": 1e-07, @@ -56318,7 +59933,6 @@ "supports_response_schema": true }, "llamagate/qwen3-8b": { - "max_tokens": 8192, "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_token": 4e-08, @@ -56329,7 +59943,6 @@ "supports_response_schema": true }, "llamagate/dolphin3-8b": { - "max_tokens": 8192, "max_input_tokens": 128000, "max_output_tokens": 8192, "input_cost_per_token": 8e-08, @@ -56340,7 +59953,6 @@ "supports_response_schema": true }, "llamagate/deepseek-r1-8b": { - "max_tokens": 16384, "max_input_tokens": 65536, "max_output_tokens": 16384, "input_cost_per_token": 1e-07, @@ -56352,7 +59964,6 @@ "supports_reasoning": true }, "llamagate/deepseek-r1-7b-qwen": { - "max_tokens": 16384, "max_input_tokens": 131072, "max_output_tokens": 16384, "input_cost_per_token": 8e-08, @@ -56364,7 +59975,6 @@ "supports_reasoning": true }, "llamagate/openthinker-7b": { - "max_tokens": 8192, "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_token": 8e-08, @@ -56376,7 +59986,6 @@ "supports_reasoning": true }, "llamagate/qwen2.5-coder-7b": { - "max_tokens": 8192, "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_token": 6e-08, @@ -56387,7 +59996,6 @@ "supports_response_schema": true }, "llamagate/deepseek-coder-6.7b": { - "max_tokens": 4096, "max_input_tokens": 16384, "max_output_tokens": 4096, "input_cost_per_token": 6e-08, @@ -56398,7 +60006,6 @@ "supports_response_schema": true }, "llamagate/codellama-7b": { - "max_tokens": 4096, "max_input_tokens": 16384, "max_output_tokens": 4096, "input_cost_per_token": 6e-08, @@ -56409,7 +60016,6 @@ "supports_response_schema": true }, "llamagate/qwen3-vl-8b": { - "max_tokens": 8192, "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_token": 1.5e-07, @@ -56421,7 +60027,6 @@ "supports_vision": true }, "llamagate/llava-7b": { - "max_tokens": 2048, "max_input_tokens": 4096, "max_output_tokens": 2048, "input_cost_per_token": 1e-07, @@ -56432,7 +60037,6 @@ "supports_vision": true }, "llamagate/gemma3-4b": { - "max_tokens": 8192, "max_input_tokens": 128000, "max_output_tokens": 8192, "input_cost_per_token": 3e-08, @@ -56444,7 +60048,6 @@ "supports_vision": true }, "llamagate/nomic-embed-text": { - "max_tokens": 8192, "max_input_tokens": 8192, "input_cost_per_token": 2e-08, "output_cost_per_token": 0, @@ -56452,7 +60055,6 @@ "mode": "embedding" }, "llamagate/qwen3-embedding-8b": { - "max_tokens": 40960, "max_input_tokens": 40960, "input_cost_per_token": 2e-08, "output_cost_per_token": 0, @@ -56460,7 +60062,6 @@ "mode": "embedding" }, "libertai/hermes-3-8b-tee": { - "max_tokens": 16000, "max_input_tokens": 16000, "max_output_tokens": 16000, "input_cost_per_token": 1.5e-07, @@ -56474,7 +60075,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/gemma-4-31b-it": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -56488,7 +60088,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/gemma-4-31b-it-thinking": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -56503,7 +60102,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/qwen3.6-27b": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -56517,7 +60115,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/qwen3.6-27b-thinking": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -56532,7 +60129,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/qwen3.6-35b-a3b": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -56546,7 +60142,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/qwen3.6-35b-a3b-thinking": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -56561,7 +60156,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/qwen3.5-122b-a10b": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.5e-07, @@ -56575,7 +60169,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/qwen3.5-122b-a10b-thinking": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.5e-07, @@ -56590,7 +60183,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/deepseek-v4-flash": { - "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 2.5e-07, @@ -56604,7 +60196,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/deepseek-v4-flash-thinking": { - "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 2.5e-07, @@ -56619,7 +60210,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/bge-m3": { - "max_tokens": 8192, "max_input_tokens": 8192, "input_cost_per_token": 1e-08, "output_cost_per_token": 0.0, @@ -56635,7 +60225,6 @@ "litellm_provider": "sarvam", "max_input_tokens": 8192, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0, "supports_reasoning": true @@ -56657,6 +60246,9 @@ ] }, "gpt-4o-mini-tts-2025-12-15": { + "deprecation_date": "2027-01-06", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-realtime-2.1-mini", "input_cost_per_token": 6e-07, "litellm_provider": "openai", "mode": "audio_speech", @@ -56677,6 +60269,8 @@ }, "gpt-4o-mini-transcribe-2025-03-20": { "deprecation_date": "2027-01-20", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-4o-mini-transcribe-2025-12-15", "input_cost_per_audio_token": 1.25e-06, "input_cost_per_second": 5e-05, "input_cost_per_token": 1.25e-06, @@ -56691,6 +60285,9 @@ ] }, "gpt-4o-mini-transcribe-2025-12-15": { + "deprecation_date": "2027-02-26", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-live-transcribe", "input_cost_per_audio_token": 1.25e-06, "input_cost_per_second": 5e-05, "input_cost_per_token": 1.25e-06, @@ -56710,9 +60307,9 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -56738,9 +60335,9 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -56770,7 +60367,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -56793,6 +60389,8 @@ "supports_system_messages": true, "supports_tool_choice": true, "deprecation_date": "2027-01-20", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-realtime-2.1-mini", "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-realtime-whisper": { @@ -56814,6 +60412,7 @@ }, "sora-2": { "deprecation_date": "2026-09-24", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "litellm_provider": "openai", "mode": "video_generation", "output_cost_per_video_per_second": 0.1, @@ -56828,6 +60427,7 @@ }, "sora-2-pro": { "deprecation_date": "2026-09-24", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "litellm_provider": "openai", "mode": "video_generation", "output_cost_per_video_per_second": 0.3, @@ -56843,6 +60443,7 @@ "sora-2-pro-high-res": { "litellm_provider": "openai", "deprecation_date": "2026-09-24", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "mode": "video_generation", "output_cost_per_video_per_second": 0.5, "source": "https://developers.openai.com/api/docs/pricing", @@ -56856,9 +60457,12 @@ }, "chatgpt-image-latest": { "cache_read_input_image_token_cost": 2e-06, + "cache_read_input_image_token_cost_batches": 1e-06, "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_batches": 6.3e-07, "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image_token": 8e-06, "input_cost_per_image_token_batches": 4e-06, "input_cost_per_token": 5e-06, @@ -56866,6 +60470,7 @@ "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_image_token": 3.2e-05, + "output_cost_per_image_token_batches": 1.6e-05, "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "source": "https://developers.openai.com/api/docs/pricing", @@ -56874,55 +60479,12 @@ "/v1/images/edits" ] }, - "gemini-2.0-flash-exp-image-generation": { - "input_cost_per_token": 0.0, - "litellm_provider": "gemini", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "image_generation", - "output_cost_per_image": 0.039, - "output_cost_per_token": 0.0, - "source": "https://ai.google.dev/pricing", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_vision": true - }, - "gemini/gemini-2.0-flash-exp-image-generation": { - "input_cost_per_token": 0.0, - "litellm_provider": "gemini", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "image_generation", - "output_cost_per_image": 0.039, - "output_cost_per_token": 0.0, - "source": "https://ai.google.dev/pricing", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_vision": true, - "tpm": 250000, - "rpm": 10 - }, "gemini-2.5-flash-native-audio-latest": { "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -56948,7 +60510,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -56969,12 +60530,14 @@ "gemini_native_audio": true }, "gemini-2.5-flash-native-audio-preview-12-2025": { + "deprecation_date": "2026-11-17", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-3.8-live", "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -56993,12 +60556,16 @@ "supports_audio_input": true, "supports_audio_output": true, "gemini_native_audio": true, + "input_cost_per_video_token": 3e-06, "supports_function_calling": true, "supports_response_schema": false, "supports_vision": true, "supports_web_search": true }, "gemini-3.1-flash-live-preview": { + "deprecation_date": "2026-11-17", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-3.8-live", "input_cost_per_audio_token": 3e-06, "input_cost_per_image_token": 1e-06, "input_cost_per_token": 7.5e-07, @@ -57007,7 +60574,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, @@ -57042,7 +60608,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, @@ -57076,7 +60641,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, @@ -57109,7 +60673,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -57137,7 +60700,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -57160,12 +60722,14 @@ "gemini_native_audio": true }, "gemini/gemini-2.5-flash-native-audio-preview-12-2025": { + "deprecation_date": "2026-11-17", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-3.8-live", "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -57186,12 +60750,17 @@ "tpm": 250000, "rpm": 10, "gemini_native_audio": true, + "input_cost_per_video_token": 3e-06, "supports_function_calling": true, "supports_response_schema": false, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "supports_reasoning": true }, "gemini/gemini-3.1-flash-live-preview": { + "deprecation_date": "2026-11-17", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-3.8-live", "input_cost_per_audio_token": 3e-06, "input_cost_per_image_token": 1e-06, "input_cost_per_token": 7.5e-07, @@ -57200,7 +60769,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, @@ -57227,15 +60795,19 @@ "rpm": 10, "gemini_audio_only_live": true, "input_cost_per_second": 8.33333333333e-05, - "supports_response_schema": false + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "supports_response_schema": false, + "supports_reasoning": true }, "gemini/gemini-3.1-flash-tts-preview": { + "deprecation_date": "2026-11-17", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-3.8-flash-tts", "input_cost_per_token": 1e-06, "input_cost_per_token_batches": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 8192, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "audio_speech", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2e-05, @@ -57262,7 +60834,6 @@ "litellm_provider": "gemini", "max_input_tokens": 8192, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "audio_speech", "output_cost_per_audio_token": 9e-06, "output_cost_per_token": 9e-06, @@ -57272,7 +60843,8 @@ "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/audio/speech" - ] + ], + "supports_prompt_caching": true }, "gemini/gemini-3.8-flash-lite-tts": { "cache_read_input_token_cost": 1.25e-07, @@ -57286,7 +60858,6 @@ "litellm_provider": "gemini", "max_input_tokens": 8192, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "audio_speech", "output_cost_per_audio_token": 6e-06, "output_cost_per_token": 6e-06, @@ -57296,15 +60867,18 @@ "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/audio/speech" - ] + ], + "supports_prompt_caching": true }, "gemini-2.5-flash-preview-tts": { + "deprecation_date": "2026-11-17", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-3.8-flash-tts", "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "gemini", "max_input_tokens": 8192, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "audio_speech", "output_cost_per_audio_token": 1e-05, "output_cost_per_token": 1e-05, @@ -57320,11 +60894,11 @@ }, "gemini-flash-latest": { "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_batches": 3.75e-08, "input_cost_per_token": 7.5e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -57379,11 +60953,11 @@ }, "gemini-flash-lite-latest": { "cache_read_input_token_cost": 3e-08, + "cache_read_input_token_cost_batches": 1.5e-08, "input_cost_per_token": 3e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -57438,12 +61012,13 @@ "gemini-pro-latest": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_flex": 4e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, @@ -57482,6 +61057,7 @@ }, "google_maps_grounding_cost_per_query": 0.014, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_batches": 2e-07, "cache_read_input_token_cost_priority": 3.6e-07, "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, "input_cost_per_token_batches": 1e-06, @@ -57494,18 +61070,23 @@ "supports_url_context": true, "web_search_billing_unit": "per_query", "cache_read_input_token_cost_flex": 2e-07, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "input_cost_per_token_above_200k_tokens_flex": 2e-06, "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_above_200k_tokens_batches": 9e-06, + "output_cost_per_token_above_200k_tokens_flex": 9e-06, "output_cost_per_token_flex": 6e-06 }, "gemini/gemini-pro-latest": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_flex": 4e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, @@ -57544,6 +61125,7 @@ }, "google_maps_grounding_cost_per_query": 0.014, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_batches": 2e-07, "cache_read_input_token_cost_priority": 3.6e-07, "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, "input_cost_per_token_batches": 1e-06, @@ -57556,7 +61138,11 @@ "supports_url_context": true, "web_search_billing_unit": "per_query", "cache_read_input_token_cost_flex": 2e-07, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "input_cost_per_token_above_200k_tokens_flex": 2e-06, "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_above_200k_tokens_batches": 9e-06, + "output_cost_per_token_above_200k_tokens_flex": 9e-06, "output_cost_per_token_flex": 6e-06 }, "gemini-exp-1206": { @@ -57566,7 +61152,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -57617,7 +61202,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -57627,6 +61211,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -57656,11 +61241,10 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -57688,13 +61272,20 @@ } }, "bedrock_mantle/openai.gpt-oss-120b": { + "supports_vision": false, "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "input_cost_per_token_flex": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, "output_cost_per_token": 6e-07, + "output_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 16384, "mode": "chat", + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -57706,13 +61297,20 @@ "supports_tool_choice": true }, "bedrock_mantle/openai.gpt-oss-20b": { + "supports_vision": false, "input_cost_per_token": 7e-08, + "input_cost_per_token_batches": 3.5e-08, + "input_cost_per_token_flex": 3.5e-08, + "input_cost_per_token_priority": 1.225e-07, "output_cost_per_token": 3e-07, + "output_cost_per_token_flex": 1.5e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 16384, "mode": "chat", + "output_cost_per_token_batches": 1.5e-07, + "output_cost_per_token_priority": 5.25e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -57724,13 +61322,20 @@ "supports_tool_choice": true }, "bedrock_mantle/openai.gpt-oss-safeguard-120b": { + "supports_vision": false, "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7e-08, + "input_cost_per_token_flex": 7e-08, + "input_cost_per_token_priority": 2.6e-07, "output_cost_per_token": 6e-07, + "output_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_output_tokens": 16000, "mode": "chat", + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions" ], @@ -57740,13 +61345,20 @@ "supports_tool_choice": true }, "bedrock_mantle/openai.gpt-oss-safeguard-20b": { + "supports_vision": false, "input_cost_per_token": 7e-08, + "input_cost_per_token_batches": 3e-08, + "input_cost_per_token_flex": 3e-08, + "input_cost_per_token_priority": 1.2e-07, "output_cost_per_token": 2e-07, + "output_cost_per_token_flex": 1e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_output_tokens": 16000, "mode": "chat", + "output_cost_per_token_batches": 1e-07, + "output_cost_per_token_priority": 3.5e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions" ], @@ -57770,9 +61382,8 @@ "search_context_size_medium": 0.012 }, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -57790,6 +61401,7 @@ "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, + "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -57813,9 +61425,8 @@ "search_context_size_medium": 0.012 }, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -57833,6 +61444,7 @@ "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, + "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -57847,12 +61459,14 @@ "cache_read_input_token_cost": 1.375e-06, "output_cost_per_token": 8.25e-05, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 272000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", + "search_context_cost_per_query": {"search_context_size_high":0.012,"search_context_size_low":0.012,"search_context_size_medium":0.012}, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-cyber.html", "use_openai_responses_path": true, "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ @@ -57865,11 +61479,13 @@ "supports_function_calling": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, + "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true }, "bedrock_mantle/openai.gpt-daybreak-blue-5.6-sol": { "input_cost_per_token": 4.4e-06, @@ -57881,10 +61497,10 @@ "output_cost_per_token": 2.2e-05, "output_cost_per_token_above_272k_tokens": 3.3e-05, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", + "search_context_cost_per_query": {"search_context_size_high":0.012,"search_context_size_low":0.012,"search_context_size_medium":0.012}, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/responses" @@ -57904,7 +61520,8 @@ "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-daybreak-blue-56-sol.html" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-daybreak-blue-56-sol.html", + "supports_web_search": true }, "bedrock_mantle/openai.gpt-5.6-luna": { "input_cost_per_token": 2.2e-07, @@ -57921,9 +61538,8 @@ "search_context_size_medium": 0.012 }, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -57941,6 +61557,7 @@ "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, + "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -57950,6 +61567,7 @@ "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html" }, "us.openai.gpt-5.6-sol": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 4.4e-06, "input_cost_per_token_above_272k_tokens": 8.8e-06, "cache_creation_input_token_cost": 5.5e-06, @@ -57959,11 +61577,11 @@ "output_cost_per_token": 2.2e-05, "output_cost_per_token_above_272k_tokens": 3.3e-05, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-sol.html", "supported_modalities": [ "text", "image" @@ -57980,10 +61598,12 @@ "supports_vision": true, "supports_sampling_params": false, "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, "global.openai.gpt-5.6-sol": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 4e-06, "input_cost_per_token_above_272k_tokens": 8e-06, "cache_creation_input_token_cost": 5e-06, @@ -57993,11 +61613,11 @@ "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-sol.html", "supported_modalities": [ "text", "image" @@ -58014,10 +61634,12 @@ "supports_vision": true, "supports_sampling_params": false, "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, "us.openai.gpt-5.6-terra": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 2.2e-06, "input_cost_per_token_above_272k_tokens": 4.4e-06, "cache_creation_input_token_cost": 2.75e-06, @@ -58027,11 +61649,11 @@ "output_cost_per_token": 1.32e-05, "output_cost_per_token_above_272k_tokens": 1.98e-05, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-terra.html", "supported_modalities": [ "text", "image" @@ -58048,10 +61670,12 @@ "supports_vision": true, "supports_sampling_params": false, "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, "global.openai.gpt-5.6-terra": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, "cache_creation_input_token_cost": 2.5e-06, @@ -58061,11 +61685,11 @@ "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-terra.html", "supported_modalities": [ "text", "image" @@ -58082,10 +61706,12 @@ "supports_vision": true, "supports_sampling_params": false, "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, "us.openai.gpt-5.6-luna": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 2.2e-07, "input_cost_per_token_above_272k_tokens": 4.4e-07, "cache_creation_input_token_cost": 2.75e-07, @@ -58095,11 +61721,11 @@ "output_cost_per_token": 1.32e-06, "output_cost_per_token_above_272k_tokens": 1.98e-06, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html", "supported_modalities": [ "text", "image" @@ -58116,6 +61742,7 @@ "supports_vision": true, "supports_sampling_params": false, "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, @@ -58127,9 +61754,9 @@ "output_cost_per_token": 1.65e-05, "output_cost_per_token_above_272k_tokens": 2.475e-05, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-54.html", "supported_modalities": [ @@ -58158,9 +61785,9 @@ "output_cost_per_token": 1.5e-05, "output_cost_per_token_above_272k_tokens": 2.25e-05, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-54.html", "supported_modalities": [ @@ -58189,9 +61816,9 @@ "output_cost_per_token": 3.3e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-55.html", "supported_modalities": [ @@ -58220,9 +61847,9 @@ "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-55.html", "supported_modalities": [ @@ -58244,6 +61871,7 @@ ] }, "global.openai.gpt-5.6-luna": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 2e-07, "input_cost_per_token_above_272k_tokens": 4e-07, "cache_creation_input_token_cost": 2.5e-07, @@ -58253,11 +61881,11 @@ "output_cost_per_token": 1.2e-06, "output_cost_per_token_above_272k_tokens": 1.8e-06, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html", "supported_modalities": [ "text", "image" @@ -58274,6 +61902,7 @@ "supports_vision": true, "supports_sampling_params": false, "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, @@ -58282,15 +61911,23 @@ "input_cost_per_token_above_272k_tokens": 2.2e-05, "cache_creation_input_token_cost": 1.375e-05, "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05, + "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 0.000165, + "cache_creation_input_token_cost_ultrafast": 8.25e-05, "cache_read_input_token_cost": 1.1e-06, "cache_read_input_token_cost_above_272k_tokens": 2.2e-06, + "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.32e-05, + "cache_read_input_token_cost_ultrafast": 6.6e-06, + "input_cost_per_token_above_272k_tokens_ultrafast": 0.000132, + "input_cost_per_token_ultrafast": 6.6e-05, "output_cost_per_token": 5.5e-05, "output_cost_per_token_above_272k_tokens": 8.25e-05, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", + "output_cost_per_token_above_272k_tokens_ultrafast": 0.000495, + "output_cost_per_token_ultrafast": 0.00033, + "search_context_cost_per_query": {"search_context_size_high":0.012,"search_context_size_low":0.012,"search_context_size_medium":0.012}, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", @@ -58308,12 +61945,17 @@ "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": false, "supports_prompt_caching": true, + "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html", + "supports_web_search": true + }, + "bedrock_mantle/gpt-astra-latest": { + "alias_of": "bedrock_mantle/openai.gpt-6-astra" }, "bedrock_mantle/openai.gpt-6-sol": { "input_cost_per_token": 2.2e-06, @@ -58325,10 +61967,10 @@ "output_cost_per_token": 1.1e-05, "output_cost_per_token_above_272k_tokens": 1.65e-05, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", + "search_context_cost_per_query": {"search_context_size_high":0.012,"search_context_size_low":0.012,"search_context_size_medium":0.012}, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", @@ -58344,14 +61986,16 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_prompt_caching": true, + "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards-openai.html" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards-openai.html", + "supports_web_search": true }, "bedrock_mantle/openai.gpt-6-luna": { "input_cost_per_token": 1.1e-07, @@ -58363,10 +62007,10 @@ "output_cost_per_token": 5.5e-07, "output_cost_per_token_above_272k_tokens": 8.25e-07, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", + "search_context_cost_per_query": {"search_context_size_high":0.012,"search_context_size_low":0.012,"search_context_size_medium":0.012}, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", @@ -58382,29 +62026,43 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_prompt_caching": true, + "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards-openai.html" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards-openai.html", + "supports_web_search": true + }, + "bedrock_mantle/gpt-luna-latest": { + "alias_of": "bedrock_mantle/openai.gpt-6-luna" }, "us.openai.gpt-6-astra": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 1.1e-05, "input_cost_per_token_above_272k_tokens": 2.2e-05, "cache_creation_input_token_cost": 1.375e-05, "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05, + "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 0.000165, + "cache_creation_input_token_cost_ultrafast": 8.25e-05, "cache_read_input_token_cost": 1.1e-06, "cache_read_input_token_cost_above_272k_tokens": 2.2e-06, + "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.32e-05, + "cache_read_input_token_cost_ultrafast": 6.6e-06, + "input_cost_per_token_above_272k_tokens_ultrafast": 0.000132, + "input_cost_per_token_ultrafast": 6.6e-05, "output_cost_per_token": 5.5e-05, "output_cost_per_token_above_272k_tokens": 8.25e-05, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1050000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", + "output_cost_per_token_above_272k_tokens_ultrafast": 0.000495, + "output_cost_per_token_ultrafast": 0.00033, "supported_modalities": [ "text", "image" @@ -58421,12 +62079,15 @@ "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_sampling_params": false, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html", "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, "us.openai.gpt-6-sol": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 2.2e-06, "input_cost_per_token_above_272k_tokens": 4.4e-06, "cache_creation_input_token_cost": 2.75e-06, @@ -58436,9 +62097,9 @@ "output_cost_per_token": 1.1e-05, "output_cost_per_token_above_272k_tokens": 1.65e-05, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1050000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_modalities": [ "text", @@ -58450,18 +62111,21 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, + "supports_sampling_params": false, "source": "https://aws.amazon.com/bedrock/pricing/", "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, "us.openai.gpt-6-luna": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 1.1e-07, "input_cost_per_token_above_272k_tokens": 2.2e-07, "cache_creation_input_token_cost": 1.375e-07, @@ -58471,9 +62135,9 @@ "output_cost_per_token": 5.5e-07, "output_cost_per_token_above_272k_tokens": 8.25e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1050000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_modalities": [ "text", @@ -58485,31 +62149,42 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, + "supports_sampling_params": false, "source": "https://aws.amazon.com/bedrock/pricing/", "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, "global.openai.gpt-6-astra": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 1e-05, "input_cost_per_token_above_272k_tokens": 2e-05, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, + "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 0.00015, + "cache_creation_input_token_cost_ultrafast": 7.5e-05, "cache_read_input_token_cost": 1e-06, "cache_read_input_token_cost_above_272k_tokens": 2e-06, + "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.2e-05, + "cache_read_input_token_cost_ultrafast": 6e-06, + "input_cost_per_token_above_272k_tokens_ultrafast": 0.00012, + "input_cost_per_token_ultrafast": 6e-05, "output_cost_per_token": 5e-05, "output_cost_per_token_above_272k_tokens": 7.5e-05, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1050000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", + "output_cost_per_token_above_272k_tokens_ultrafast": 0.00045, + "output_cost_per_token_ultrafast": 0.0003, "supported_modalities": [ "text", "image" @@ -58526,11 +62201,16 @@ "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_sampling_params": false, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html", "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, + "bedrock/gpt-astra-latest": { + "alias_of": "global.openai.gpt-6-astra" + }, "openai.gpt-6-sol": { "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, @@ -58541,9 +62221,9 @@ "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1050000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_modalities": [ "text", @@ -58555,15 +62235,17 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, + "supports_sampling_params": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "global.openai.gpt-6-sol": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, "cache_creation_input_token_cost": 2.5e-06, @@ -58573,9 +62255,9 @@ "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1050000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_modalities": [ "text", @@ -58587,14 +62269,16 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, + "supports_sampling_params": false, "source": "https://aws.amazon.com/bedrock/pricing/", "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, @@ -58608,9 +62292,9 @@ "output_cost_per_token": 5e-07, "output_cost_per_token_above_272k_tokens": 7.5e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1050000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_modalities": [ "text", @@ -58622,15 +62306,17 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, + "supports_sampling_params": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "global.openai.gpt-6-luna": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 1e-07, "input_cost_per_token_above_272k_tokens": 2e-07, "cache_creation_input_token_cost": 1.25e-07, @@ -58640,9 +62326,9 @@ "output_cost_per_token": 5e-07, "output_cost_per_token_above_272k_tokens": 7.5e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1050000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_modalities": [ "text", @@ -58654,17 +62340,22 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, + "supports_sampling_params": false, "source": "https://aws.amazon.com/bedrock/pricing/", "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, + "bedrock/gpt-luna-latest": { + "alias_of": "global.openai.gpt-6-luna" + }, "bedrock_mantle/openai.gpt-5.5": { "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, @@ -58678,9 +62369,8 @@ "search_context_size_medium": 0.012 }, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -58718,9 +62408,8 @@ "search_context_size_medium": 0.012 }, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -58747,12 +62436,18 @@ }, "bedrock_mantle/google.gemma-4-31b": { "input_cost_per_token": 1.4e-07, + "input_cost_per_token_batches": 7e-08, + "input_cost_per_token_flex": 7e-08, + "input_cost_per_token_priority": 2.45e-07, "output_cost_per_token": 4e-07, + "output_cost_per_token_flex": 2e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", + "output_cost_per_token_batches": 2e-07, + "output_cost_per_token_priority": 7e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", @@ -58766,12 +62461,18 @@ }, "bedrock_mantle/google.gemma-4-26b-a4b": { "input_cost_per_token": 1.3e-07, + "input_cost_per_token_batches": 6.5e-08, + "input_cost_per_token_flex": 6.5e-08, + "input_cost_per_token_priority": 2.275e-07, "output_cost_per_token": 4e-07, + "output_cost_per_token_flex": 2e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", + "output_cost_per_token_batches": 2e-07, + "output_cost_per_token_priority": 7e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", @@ -58785,12 +62486,18 @@ }, "bedrock_mantle/google.gemma-4-e2b": { "input_cost_per_token": 4e-08, + "input_cost_per_token_batches": 2e-08, + "input_cost_per_token_flex": 2e-08, + "input_cost_per_token_priority": 7e-08, "output_cost_per_token": 8e-08, + "output_cost_per_token_flex": 4e-08, "litellm_provider": "bedrock_mantle", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", + "output_cost_per_token_batches": 4e-08, + "output_cost_per_token_priority": 1.4e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", @@ -58807,11 +62514,19 @@ "input_cost_per_token": 1.25e-06, "output_cost_per_token": 2.5e-06, "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "cache_read_input_token_cost_flex": 1e-07, + "cache_read_input_token_cost_priority": 3.5e-07, + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_flex": 6.25e-07, + "input_cost_per_token_priority": 2.1875e-06, "litellm_provider": "bedrock_mantle", "max_input_tokens": 1048576, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_priority": 4.375e-06, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -58821,18 +62536,23 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/xai.grok-4.6": { "use_openai_responses_path": true, "input_cost_per_token": 2.2e-06, "output_cost_per_token": 6.6e-06, "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_flex": 2.75e-07, + "cache_read_input_token_cost_priority": 9.625e-07, + "input_cost_per_token_flex": 1.1e-06, + "input_cost_per_token_priority": 3.85e-06, "litellm_provider": "bedrock_mantle", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", + "output_cost_per_token_flex": 3.3e-06, + "output_cost_per_token_priority": 1.155e-05, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -58854,7 +62574,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", @@ -58871,7 +62590,8 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5e-07, - "output_cost_per_token_batches": 2.5e-06 + "output_cost_per_token_batches": 2.5e-06, + "token_count_model": {"model":"anthropic.claude-haiku-4-5-20251001-v1:0","litellm_provider":"bedrock"} }, "bedrock_mantle/anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -58885,7 +62605,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "search_context_cost_per_query": { @@ -58911,19 +62630,22 @@ "prompt_cache_min_tokens": 512, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-5-5.html", "thinking_always_on": true, - "supports_forced_tool_use": false + "supports_forced_tool_use": false, + "token_count_model": {"model":"anthropic.claude-opus-5-5","litellm_provider":"bedrock_mantle","region":"us-east-1"} + }, + "bedrock_mantle/claude-opus-latest": { + "alias_of": "bedrock_mantle/anthropic.claude-opus-5-5" }, "bedrock_mantle/anthropic.claude-sonnet-5-5": { "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 2.75e-06, "cache_creation_input_token_cost_above_1hr": 4.4e-06, - "cache_read_input_token_cost": 2.2e-07, + "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token": 2.2e-06, "litellm_provider": "bedrock_mantle", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "search_context_cost_per_query": { @@ -58952,17 +62674,31 @@ "supports_forced_tool_use": false, "thinking_always_on": true, "prompt_cache_min_tokens": 512, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-5-5.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "bedrock_mantle/claude-sonnet-latest": { + "alias_of": "bedrock_mantle/anthropic.claude-sonnet-5-5" }, "us.xai.grok-4.6": { + "supports_regex_lookaround": false, "input_cost_per_token": 2.2e-06, "output_cost_per_token": 6.6e-06, "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_flex": 2.75e-07, + "cache_read_input_token_cost_priority": 9.625e-07, + "input_cost_per_token_flex": 1.1e-06, + "input_cost_per_token_priority": 3.85e-06, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_response_format": true, "litellm_provider": "bedrock_converse", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", + "output_cost_per_token_flex": 3.3e-06, + "output_cost_per_token_priority": 1.155e-05, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_prompt_caching": false, @@ -58971,14 +62707,25 @@ "supports_vision": true }, "global.xai.grok-4.6": { + "supports_regex_lookaround": false, "input_cost_per_token": 2e-06, "output_cost_per_token": 6e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_flex": 2.5e-07, + "cache_read_input_token_cost_priority": 8.75e-07, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.5e-06, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_response_format": true, "litellm_provider": "bedrock_converse", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", + "output_cost_per_token_flex": 3e-06, + "output_cost_per_token_priority": 1.05e-05, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_prompt_caching": false, @@ -58990,7 +62737,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.volcengine.com/docs/82379/1330310", "supports_function_calling": true, @@ -59030,7 +62776,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4.3125e-06, "source": "https://www.volcengine.com/docs/82379/1544106", @@ -59040,13 +62785,45 @@ "supports_tool_choice": false, "supports_vision": true }, + "volcengine/doubao-seed-2-1-pro-260915": { + "cache_read_input_token_cost": 1.725e-07, + "input_cost_per_token": 8.625e-07, + "litellm_provider": "volcengine", + "max_input_tokens": 1024000, + "max_output_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4.3125e-06, + "source": "https://www.volcengine.com/docs/82379/1544106", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "volcengine/doubao-seed-2-1-lite-260915": { + "cache_read_input_audio_token_cost": 3.45e-07, + "cache_read_input_token_cost": 2.3e-08, + "input_cost_per_audio_token": 1.725e-06, + "input_cost_per_token": 1.15e-07, + "litellm_provider": "volcengine", + "max_input_tokens": 1024000, + "max_output_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 3.88126e-07, + "source": "https://www.volcengine.com/docs/82379/1544106", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": false, + "supports_vision": true + }, "volcengine/doubao-seed-2-1-turbo-260628": { "cache_read_input_token_cost": 8.625e-08, "input_cost_per_token": 4.3125e-07, "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2.15625e-06, "source": "https://www.volcengine.com/docs/82379/1544106", @@ -59060,7 +62837,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.volcengine.com/docs/82379/1330310", "supports_function_calling": true, @@ -59098,7 +62874,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.volcengine.com/docs/82379/1330310", "supports_function_calling": true, @@ -59136,7 +62911,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.volcengine.com/docs/82379/1330310", "supports_function_calling": true, @@ -59170,14 +62944,74 @@ } ] }, + "volcengine/doubao-seedance-2-5-260628": { + "litellm_provider": "volcengine", + "mode": "video_generation", + "source": "https://www.volcengine.com/docs/82379/1544106", + "output_cost_per_second": 0.216, + "output_cost_per_second_480p": 0.096075, + "output_cost_per_second_720p": 0.216, + "output_cost_per_second_1080p": 0.5346, + "supported_modalities": ["text", "image", "video", "audio"], + "supported_output_modalities": ["video"], + "supported_endpoints": ["/v1/videos"], + "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "854x480", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "480x854", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}}, + "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s). List 70 CNY per million tokens at 480p and 720p and 77 at 1080p without a video input, matching Ark's per-resolution table and its 1080p 16:9 example of 3.74 CNY/s, converted at 7.0 CNY/USD like the other volcengine entries. Accepts up to 50 reference assets (30 images, 10 videos, 10 audios) and clips of 4-30s; per-asset billing beyond the free allowance is not encoded. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."} + }, + "volcengine/doubao-seedance-2-0-260128": { + "litellm_provider": "volcengine", + "mode": "video_generation", + "source": "https://www.volcengine.com/docs/82379/1544106", + "output_cost_per_second": 0.141942857, + "output_cost_per_second_480p": 0.066003429, + "output_cost_per_second_720p": 0.141942857, + "output_cost_per_second_1080p": 0.354085714, + "output_cost_per_second_4k": 0.722057143, + "supported_modalities": ["text", "image", "video", "audio"], + "supported_output_modalities": ["video"], + "supported_endpoints": ["/v1/videos"], + "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "864x496", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "496x864", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}}, + "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 46 CNY per million tokens at 480p and 720p, 51 at 1080p, and 26 at 4k without a video input, matching Ark's per-resolution table and its 1080p and 4k 16:9 examples of 2.48 and 5.05 CNY/s, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s; 4k is exclusive to this tier. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."} + }, + "volcengine/doubao-seedance-2-0-fast-260128": { + "litellm_provider": "volcengine", + "mode": "video_generation", + "source": "https://www.volcengine.com/docs/82379/1544106", + "output_cost_per_second": 0.114171429, + "output_cost_per_second_480p": 0.053089714, + "output_cost_per_second_720p": 0.114171429, + "supported_modalities": ["text", "image", "video", "audio"], + "supported_output_modalities": ["video"], + "supported_endpoints": ["/v1/videos"], + "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "864x496", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "496x864", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}}, + "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 37 CNY per million tokens without a video input, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s at 480p or 720p. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."} + }, + "volcengine/doubao-seedance-2-0-mini-260615": { + "litellm_provider": "volcengine", + "mode": "video_generation", + "source": "https://www.volcengine.com/docs/82379/1544106", + "output_cost_per_second": 0.070971429, + "output_cost_per_second_480p": 0.033001714, + "output_cost_per_second_720p": 0.070971429, + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["video"], + "supported_endpoints": ["/v1/videos"], + "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "864x496", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "496x864", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}}, + "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 23 CNY per million tokens without a video input, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s at 480p or 720p. Only text and image inputs are declared; the mini tier's reference video and audio caps were not verified. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."} + }, "bedrock/us-east-1/zai.glm-5": { "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, + "input_cost_per_token_flex": 5e-07, + "input_cost_per_token_priority": 1.75e-06, "output_cost_per_token": 3.2e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", + "output_cost_per_token_batches": 1.6e-06, + "output_cost_per_token_flex": 1.6e-06, + "output_cost_per_token_priority": 5.6e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -59186,16 +63020,21 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-west-2/zai.glm-5": { "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, + "input_cost_per_token_flex": 5e-07, + "input_cost_per_token_priority": 1.75e-06, "output_cost_per_token": 3.2e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", + "output_cost_per_token_batches": 1.6e-06, + "output_cost_per_token_flex": 1.6e-06, + "output_cost_per_token_priority": 5.6e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -59204,7 +63043,7 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-gov-east-1/anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.5e-06, @@ -59215,7 +63054,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", @@ -59230,7 +63068,11 @@ "supports_native_structured_output": true, "supports_pdf_input": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "bedrock/us-gov-west-1/anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.5e-06, @@ -59241,7 +63083,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", @@ -59256,10 +63097,13 @@ "supports_native_structured_output": true, "supports_pdf_input": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "snowflake/claude-sonnet-4-5": { - "max_tokens": 16384, "max_input_tokens": 200000, "max_output_tokens": 16384, "input_cost_per_token": 3e-06, @@ -59277,7 +63121,6 @@ "snowflake/claude-sonnet-4-6": { "supports_adaptive_thinking": true, "supports_legacy_thinking": true, - "max_tokens": 16384, "max_input_tokens": 200000, "max_output_tokens": 16384, "input_cost_per_token": 3e-06, @@ -59293,7 +63136,6 @@ "prompt_cache_min_tokens": 1024 }, "snowflake/claude-4-sonnet": { - "max_tokens": 16384, "max_input_tokens": 200000, "max_output_tokens": 16384, "input_cost_per_token": 3e-06, @@ -59309,7 +63151,6 @@ "prompt_cache_min_tokens": 1024 }, "snowflake/claude-4-opus": { - "max_tokens": 16384, "max_input_tokens": 200000, "max_output_tokens": 16384, "input_cost_per_token": 5e-06, @@ -59326,7 +63167,6 @@ "prompt_cache_min_tokens": 1024 }, "snowflake/claude-haiku-4-5": { - "max_tokens": 16384, "max_input_tokens": 200000, "max_output_tokens": 16384, "input_cost_per_token": 1e-06, @@ -59342,7 +63182,6 @@ "prompt_cache_min_tokens": 4096 }, "snowflake/claude-3-7-sonnet": { - "max_tokens": 16384, "max_input_tokens": 200000, "max_output_tokens": 16384, "input_cost_per_token": 3e-06, @@ -59358,7 +63197,6 @@ "supports_response_schema": true }, "snowflake/openai-gpt-4.1": { - "max_tokens": 16384, "max_input_tokens": 300000, "max_output_tokens": 16384, "input_cost_per_token": 2e-06, @@ -59373,7 +63211,6 @@ "supports_response_schema": true }, "snowflake/openai-gpt-5": { - "max_tokens": 16384, "max_input_tokens": 300000, "max_output_tokens": 16384, "input_cost_per_token": 1.25e-06, @@ -59389,7 +63226,6 @@ "supports_response_schema": true }, "snowflake/openai-gpt-5-mini": { - "max_tokens": 16384, "max_input_tokens": 1000000, "max_output_tokens": 16384, "input_cost_per_token": 3e-07, @@ -59401,7 +63237,6 @@ "supports_response_schema": true }, "snowflake/openai-gpt-5-nano": { - "max_tokens": 16384, "max_input_tokens": 5000000, "max_output_tokens": 16384, "input_cost_per_token": 1.5e-07, @@ -59413,7 +63248,6 @@ "supports_response_schema": true }, "snowflake/llama4-maverick": { - "max_tokens": 16384, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_token": 2.4e-07, @@ -59424,7 +63258,6 @@ "supports_system_messages": true }, "snowflake/snowflake-arctic-embed-l-v2.0": { - "max_tokens": 8192, "max_input_tokens": 8192, "input_cost_per_token": 7e-08, "output_cost_per_token": 0.0, @@ -59432,7 +63265,6 @@ "mode": "embedding" }, "snowflake/snowflake-arctic-embed-m-v2.0": { - "max_tokens": 8192, "max_input_tokens": 8192, "input_cost_per_token": 7e-08, "output_cost_per_token": 0.0, @@ -59442,7 +63274,7 @@ "soniox/stt-async-v4": { "litellm_provider": "soniox", "max_output_tokens": 8000, - "max_tokens": 8000, + "max_input_tokens": 8000, "input_cost_per_second": 0.0, "output_cost_per_second": 2.77778e-05, "mode": "audio_transcription", @@ -59455,7 +63287,7 @@ "soniox/stt-async-v5": { "litellm_provider": "soniox", "max_output_tokens": 8000, - "max_tokens": 8000, + "max_input_tokens": 8000, "input_cost_per_second": 0.0, "output_cost_per_second": 2.77778e-05, "mode": "audio_transcription", @@ -59465,6 +63297,126 @@ ], "supports_audio_input": true }, + "soniox/stt-rt-v5": { + "input_cost_per_second": 3.333e-05, + "litellm_provider": "soniox", + "metadata": { + "calculation": "$0.12/3600 seconds = $0.00003333 per second", + "original_pricing_per_hour": 0.12 + }, + "mode": "audio_transcription", + "source": "https://soniox.com/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, + "soniox/stt-rt-preview": { + "input_cost_per_second": 3.333e-05, + "litellm_provider": "soniox", + "metadata": { + "calculation": "$0.12/3600 seconds = $0.00003333 per second", + "original_pricing_per_hour": 0.12 + }, + "mode": "audio_transcription", + "source": "https://soniox.com/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, + "soniox/stt-rt-preview-v2": { + "input_cost_per_second": 3.333e-05, + "litellm_provider": "soniox", + "metadata": { + "calculation": "$0.12/3600 seconds = $0.00003333 per second", + "original_pricing_per_hour": 0.12 + }, + "mode": "audio_transcription", + "source": "https://soniox.com/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, + "soniox/stt-rt-v3": { + "input_cost_per_second": 3.333e-05, + "litellm_provider": "soniox", + "metadata": { + "calculation": "$0.12/3600 seconds = $0.00003333 per second", + "original_pricing_per_hour": 0.12 + }, + "mode": "audio_transcription", + "source": "https://soniox.com/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, + "soniox/stt-rt-v3-preview": { + "input_cost_per_second": 3.333e-05, + "litellm_provider": "soniox", + "metadata": { + "calculation": "$0.12/3600 seconds = $0.00003333 per second", + "original_pricing_per_hour": 0.12 + }, + "mode": "audio_transcription", + "source": "https://soniox.com/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, + "soniox/stt-rt-v4": { + "input_cost_per_second": 3.333e-05, + "litellm_provider": "soniox", + "metadata": { + "calculation": "$0.12/3600 seconds = $0.00003333 per second", + "original_pricing_per_hour": 0.12 + }, + "mode": "audio_transcription", + "source": "https://soniox.com/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, "tensormesh/Qwen/Qwen3.5-397B-A17B-FP8": { "litellm_provider": "tensormesh", "mode": "chat", @@ -59632,7 +63584,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 3e-09, @@ -59678,6 +63629,359 @@ "supports_tool_choice": true, "supports_vision": true }, + "streamlake/deepseek-v4-flash-0731": { + "cache_read_input_token_cost": 1.4e-08, + "input_cost_per_token": 4.4e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 1.32e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/DeepSeek-V4-Pro-0813": { + "cache_read_input_token_cost": 4.4e-08, + "input_cost_per_token": 1.32e-06, + "litellm_provider": "streamlake", + "max_input_tokens": 1048566, + "max_output_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 3.96e-06, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/DeepSeek-V3": { + "cache_read_input_token_cost": 1.14e-07, + "input_cost_per_token": 2.86e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 56000, + "max_output_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 1.143e-06, + "supports_function_calling": true, + "supports_reasoning": false, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/GLM-5.3": { + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "streamlake", + "max_input_tokens": 1048576, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_assistant_prefill": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/GLM-5.3-Flash": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 1048576, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_assistant_prefill": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/Kimi-K2-Instruct-0905": { + "cache_read_input_token_cost": 1.43e-07, + "input_cost_per_token": 5.71e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 224000, + "max_output_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 2.286e-06, + "supports_function_calling": true, + "supports_reasoning": false, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/deepseek-r1": { + "cache_read_input_token_cost": 2.29e-07, + "input_cost_per_token": 5.71e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 98304, + "max_output_tokens": 16000, + "mode": "chat", + "output_cost_per_token": 2.286e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/deepseek-v3.1": { + "cache_read_input_token_cost": 2.29e-07, + "input_cost_per_token": 5.71e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 98304, + "max_output_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 1.714e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/deepseek-v4-flash": { + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 1.4e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/deepseek-v4-pro": { + "cache_read_input_token_cost": 1.45e-07, + "input_cost_per_token": 1.74e-06, + "litellm_provider": "streamlake", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 3.48e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/deepseek-v4.1-flash-1017": { + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/deepseek-v4.1-flash-260910": { + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 1048568, + "max_output_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/glm-5": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "streamlake", + "max_input_tokens": 202752, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.2e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/glm-5.1": { + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "streamlake", + "max_input_tokens": 202752, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/glm-5.2": { + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "streamlake", + "max_input_tokens": 1048566, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/kimi-k2.6": { + "cache_read_input_token_cost": 1.6e-07, + "input_cost_per_token": 9.5e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 262144, + "max_output_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-06, + "supports_function_calling": true, + "supports_vision": true, + "supports_reasoning": false, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/kimi-k2.7-code": { + "cache_read_input_token_cost": 1.9e-07, + "input_cost_per_token": 9.5e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 262144, + "max_output_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 4e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/mimo-v2.6-flash": { + "cache_read_input_token_cost": 2.8e-09, + "input_cost_per_token": 1.4e-07, + "litellm_provider": "streamlake", + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "supports_vision": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/mimo-v2.6-pro": { + "cache_read_input_token_cost": 3.6e-09, + "input_cost_per_token": 4.35e-07, + "litellm_provider": "streamlake", + "mode": "chat", + "output_cost_per_token": 8.7e-07, + "supports_vision": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/minimax-m2.5": { + "cache_creation_input_token_cost": 3.75e-07, + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 196608, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/minimax-m3": { + "cache_read_input_token_cost": 1.2e-07, + "cache_read_input_token_cost_above_512k_tokens": 2.4e-07, + "input_cost_per_token": 6e-07, + "input_cost_per_token_above_512k_tokens": 1.2e-06, + "litellm_provider": "streamlake", + "max_input_tokens": 1000000, + "max_output_tokens": 512000, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "output_cost_per_token_above_512k_tokens": 4.8e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/qwen3.5-397b-a17b": { + "cache_read_input_token_cost": 1.2e-07, + "input_cost_per_token": 6e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 258048, + "max_output_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 3.6e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/qwen3.6-27b": { + "input_cost_per_token": 6e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 229376, + "max_output_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 3.6e-06, + "supports_function_calling": true, + "supports_vision": true, + "supports_reasoning": false, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/qwen3.6-35b-a3b": { + "input_cost_per_token": 3.75e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 229376, + "max_output_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 2.25e-06, + "supports_function_calling": true, + "supports_vision": true, + "supports_reasoning": false, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/qwen3.8-2.4t-a95b": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "streamlake", + "max_input_tokens": 983616, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "cache_creation_input_token_cost": 2.5e-06, + "explicit_cache_read_input_token_cost": 1.7e-07, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/qwen3.8-27b": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 5e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 983616, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "cache_creation_input_token_cost": 6.25e-07, + "explicit_cache_read_input_token_cost": 5e-08, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, "deepseek-v4-flash": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 6e-09, @@ -59686,7 +63990,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 3e-09, @@ -59740,7 +64043,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 3e-09, @@ -59794,7 +64096,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 2.2e-08, @@ -59848,7 +64149,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 3e-09, @@ -59902,7 +64202,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 3e-09, @@ -59946,7 +64245,12 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "token_count_framing": 23, + "token_count_tool_framing": 12 + }, + "deepseek/deepseek-flash-latest": { + "alias_of": "deepseek/deepseek-v4-flash" }, "deepseek/deepseek-v4-flash-vision-exp": { "cache_creation_input_token_cost": 0.0, @@ -59956,7 +64260,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 3e-09, @@ -60010,7 +64313,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 2.2e-08, @@ -60054,20 +64356,24 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": false, + "token_count_framing": 76, + "token_count_tool_framing": 75 + }, + "deepseek/deepseek-pro-latest": { + "alias_of": "deepseek/deepseek-v4-pro" }, "tencent/deepseek-v4-pro": { "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 3.625e-09, - "input_cost_per_token": 4.35e-07, - "input_cost_per_token_cache_hit": 3.625e-09, + "cache_read_input_token_cost": 1.45e-07, + "input_cost_per_token": 1.74e-06, + "input_cost_per_token_cache_hit": 1.45e-07, "litellm_provider": "tencent", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", - "output_cost_per_token": 8.7e-07, - "source": "https://www.tencentcloud.com/products/tokenhub", + "output_cost_per_token": 3.48e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", "supported_endpoints": [ "/v1/chat/completions" ], @@ -60090,10 +64396,9 @@ "litellm_provider": "tencent", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 2.8e-07, - "source": "https://www.tencentcloud.com/products/tokenhub", + "source": "https://www.tencentcloud.com/document/product/1300/78937", "supported_endpoints": [ "/v1/chat/completions" ], @@ -60108,6 +64413,333 @@ "supports_reasoning": true, "supports_vision": false }, + "tencent/deepseek-v4-pro-0813": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 4.4e-08, + "input_cost_per_token": 1.32e-06, + "input_cost_per_token_cache_hit": 4.4e-08, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "mode": "chat", + "off_peak_pricing": { + "cache_read_input_token_cost": 2.2e-08, + "input_cost_per_token": 6.6e-07, + "output_cost_per_token": 1.98e-06, + "weekday_timezone": "Asia/Shanghai", + "windows": [ + { + "hours_utc": [ + "00:00-01:00", + "04:00-06:00", + "10:00-00:00" + ], + "weekdays": [ + 1, + 2, + 3, + 4, + 5 + ] + }, + { + "hours_utc": "00:00-00:00", + "weekdays": [ + 6, + 7 + ] + } + ] + }, + "output_cost_per_token": 3.96e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false + }, + "tencent/deepseek-v4.1-flash": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "input_cost_per_token_cache_hit": 6e-09, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "mode": "chat", + "off_peak_pricing": { + "cache_read_input_token_cost": 3e-09, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "weekday_timezone": "Asia/Shanghai", + "windows": [ + { + "hours_utc": [ + "00:00-01:00", + "04:00-06:00", + "10:00-00:00" + ], + "weekdays": [ + 1, + 2, + 3, + 4, + 5 + ] + }, + { + "hours_utc": "00:00-00:00", + "weekdays": [ + 6, + 7 + ] + } + ] + }, + "output_cost_per_token": 1.2e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": true + }, + "tencent/glm-5.3-flashx": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 3.7e-07, + "input_cost_per_token_cache_hit": 7.5e-08, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true + }, + "tencent/glm-5.3-flash": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_cache_hit": 3e-08, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true + }, + "tencent/glm-5.3": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "input_cost_per_token_cache_hit": 2.6e-07, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "tencent/glm-5.2": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "input_cost_per_token_cache_hit": 2.6e-07, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "tencent/kimi-k3": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_cache_hit": 3e-07, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "tencent/kimi-k2.8-preview": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_cache_hit": 2.5e-07, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "tencent/kimi-k2.7-code-highspeed": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 3.8e-07, + "input_cost_per_token": 1.9e-06, + "input_cost_per_token_cache_hit": 3.8e-07, + "litellm_provider": "tencent", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "tencent/kimi-k2.7-code": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 1.9e-07, + "input_cost_per_token": 9.5e-07, + "input_cost_per_token_cache_hit": 1.9e-07, + "litellm_provider": "tencent", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "tencent/hy4": { + "cache_read_input_token_cost": 2.1e-08, + "comment": "These are the 50% promotional rates. Update on 2026-12-31 when the promotion ends at 23:59:59 Beijing time. List rates per 1M tokens are $0.834 input, $2.501 output and $0.042 cached input.", + "input_cost_per_token": 4.17e-07, + "input_cost_per_token_cache_hit": 2.1e-08, + "litellm_provider": "tencent", + "max_input_tokens": 960000, + "max_output_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.2505e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "tencent/hy4-preview": { + "cache_read_input_token_cost": 2.1e-08, + "comment": "These are the 50% promotional rates. Update on 2026-12-31 when the promotion ends at 23:59:59 Beijing time. List rates per 1M tokens are $0.834 input, $2.501 output and $0.042 cached input.", + "input_cost_per_token": 4.17e-07, + "input_cost_per_token_cache_hit": 2.1e-08, + "litellm_provider": "tencent", + "max_input_tokens": 960000, + "max_output_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.2505e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true + }, "tencent/minimax-m3": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 6e-08, @@ -60117,7 +64749,7 @@ "max_input_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.2e-06, - "source": "https://www.tencentcloud.com/products/tokenhub", + "source": "https://www.tencentcloud.com/document/product/1300/78937", "supported_endpoints": [ "/v1/chat/completions" ], @@ -60128,6 +64760,39 @@ "supports_reasoning": true, "supports_vision": false }, + "tencent/seedream-image-v5.0-flash": { + "litellm_provider": "tencent", + "mode": "image_generation", + "output_cost_per_image": 0.018, + "output_cost_per_image_token": 1.6e-06, + "source": "https://cloud.tencent.com/document/product/1823/130055", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ] + }, + "tencent/seedream-image-v5.0-lite": { + "litellm_provider": "tencent", + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_image_token": 1.6e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ] + }, + "tencent/seedream-image-v5.0-pro": { + "litellm_provider": "tencent", + "mode": "image_generation", + "output_cost_per_image": 0.09, + "output_cost_per_image_token": 1.6e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ] + }, "cognition/swe-1.6": { "input_cost_per_token": 5e-07, "output_cost_per_token": 2.5e-06, @@ -60159,7 +64824,6 @@ "source": "https://docs.devin.ai/desktop/models" }, "pinstripes/ps/glm-4.5-air": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1.25e-07, @@ -60172,7 +64836,6 @@ "source": "https://pinstripes.io/" }, "pinstripes/ps/qwen3.6-35b-a3b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.4e-07, @@ -60185,7 +64848,6 @@ "source": "https://pinstripes.io/" }, "pinstripes/ps/qwen3-30b-a3b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-08, @@ -60198,7 +64860,6 @@ "source": "https://pinstripes.io/" }, "pinstripes/ps/qwen3-coder-30b-a3b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3e-07, @@ -60211,7 +64872,6 @@ "source": "https://pinstripes.io/" }, "pinstripes/ps/deepseek-v4-flash": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 1e-07, @@ -60224,7 +64884,6 @@ "source": "https://pinstripes.io/" }, "pinstripes/ps/minimax-m2.7": { - "max_tokens": 1000192, "max_input_tokens": 1000192, "max_output_tokens": 1000192, "input_cost_per_token": 2.55e-07, @@ -60241,7 +64900,6 @@ "litellm_provider": "darkbloom", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.65e-07, "source": "https://www.darkbloom.dev/", @@ -60258,7 +64916,6 @@ "litellm_provider": "darkbloom", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7e-08, "source": "https://www.darkbloom.dev/", @@ -60278,7 +64935,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, @@ -60305,7 +64961,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, @@ -60334,7 +64989,6 @@ "litellm_provider": "xai", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://api.x.ai/v1/language-models", @@ -60353,6 +65007,10 @@ "input_cost_per_second": 7.5e-05, "litellm_provider": "openai", "mode": "audio_transcription", + "provider_specific_entry": { + "transcription_json_or_text_only": 1, + "transcription_usage_duration": 1 + }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/audio/transcriptions", @@ -60365,7 +65023,8 @@ "supported_output_modalities": [ "text" ], - "supports_audio_input": true + "supports_audio_input": true, + "supports_native_streaming": true }, "gpt-live-transcribe": { "input_cost_per_second": 0.000283333333333, @@ -60383,7 +65042,8 @@ "supported_output_modalities": [ "text" ], - "supports_audio_input": true + "supports_audio_input": true, + "supports_native_streaming": true }, "gpt-live-1": { "input_cost_per_second": 0.000833333333333, @@ -60407,7 +65067,6 @@ "litellm_provider": "openai", "max_input_tokens": 16000, "max_output_tokens": 2000, - "max_tokens": 2000, "mode": "realtime", "source": "https://developers.openai.com/api/docs/pricing", "supported_modalities": [ @@ -60418,7 +65077,8 @@ "audio" ], "supports_audio_input": true, - "supports_audio_output": true + "supports_audio_output": true, + "supports_native_streaming": true }, "claude-mythos-5": { "supports_anthropic_compaction": true, @@ -60432,7 +65092,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, @@ -60476,7 +65135,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, @@ -60509,8 +65167,56 @@ "supports_native_structured_output": true, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, + "claude-mythos-5-2": { + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_creation_input_token_cost_batches": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "input_cost_per_token": 8e-06, + "input_cost_per_token_batches": 4e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "output_cost_per_token_batches": 2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "fast": 2, + "us": 1.1 + }, + "supports_output_config": true, + "prompt_cache_min_tokens": 512, + "supports_native_structured_output": true, + "source": "https://platform.claude.com/docs/en/about-claude/pricing", + "supports_fast_mode": true, + "supports_speed": true + }, "claude-mythos-preview": { "deprecation_date": "2026-06-09", + "deprecation_source": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, @@ -60519,7 +65225,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "prompt_cache_min_tokens": 512, @@ -60555,7 +65260,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 5e-06, "search_context_cost_per_query": { @@ -60590,7 +65294,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 6e-07, "reasoning_effort_levels": [ @@ -60606,17 +65309,19 @@ "supports_vision": true }, "mistral/labs-leanstral-1-5": { + "deprecation_date": "2026-09-30", "input_cost_per_token": 0.0, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://docs.mistral.ai/models/model-cards/leanstral-1-5", "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true }, "mistral/mistral-moderation-2603": { "input_cost_per_token": 0.0, @@ -60627,6 +65332,7 @@ "source": "https://docs.mistral.ai/models/model-cards/mistral-moderation-26-03" }, "mistral/voxtral-mini-2602": { + "deprecation_date": "2027-04-30", "input_cost_per_second": 5e-05, "litellm_provider": "mistral", "mode": "audio_transcription", @@ -60643,6 +65349,7 @@ "supports_audio_input": true }, "mistral/voxtral-mini-transcribe-realtime-2602": { + "deprecation_date": "2027-04-30", "input_cost_per_second": 0.0001, "litellm_provider": "mistral", "mode": "audio_transcription", @@ -60659,6 +65366,7 @@ "supports_audio_input": true }, "mistral/voxtral-mini-tts-2603": { + "deprecation_date": "2027-04-30", "input_cost_per_character": 1.6e-05, "litellm_provider": "mistral", "mode": "audio_speech", @@ -60692,15 +65400,23 @@ "litellm_provider": "anthropic" } }, + { + "name": "typesafe-jev-ids", + "pattern": "^jev-(?:latest|preview|1\\.13\\.0|1\\.14\\.0)$", + "description": "A bare Jev id that has a typesafe/ price entry (jev-latest, jev-preview, jev-1.13.0, jev-1.14.0), the name the /typesafe pass-through forwards to TypeSafe. Listed by name, matched case-insensitively like every rule here, so foo/jev-latest or a model group named like a Jev id TypeSafe does not serve, such as jev-1.0 or jev-internal-router, never resolves to typesafe. A new Jev version goes here together with its price entry. Provider inference feeds the proxy's provider/* wildcard access checks, so this rule is what lets typesafe/* on a key, team or project allowlist cover a jev-latest request.", + "model_info": { + "litellm_provider": "typesafe" + } + }, { "name": "claude-family-baseline", "pattern": "claude-[a-z]+-\\d+(?:[-.]\\d+)?(?:-\\d{8})?", - "description": "Any Claude family-major id with an optional minor and an optional 8-digit date suffix, under any provider namespace (bare, bedrock-dotted, vertex, databricks, ...), so bare majors like claude-newfamily-5 get the same baseline as claude-newfamily-5-1. Carries the model-family facts every Claude shares; it carries no pricing, so cost stays on the standard unpriced behavior rather than a guessed number.", + "fill_missing_for_providers": ["anthropic", "azure_ai", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"], + "description": "Any Claude family-major id with an optional minor and an optional 8-digit date suffix, under any provider namespace (bare, bedrock-dotted, vertex, databricks, ...), so bare majors like claude-newfamily-5 get the same baseline as claude-newfamily-5-1. Carries the model-family facts every Claude shares; it carries no pricing, so cost stays on the standard unpriced behavior rather than a guessed number. On mapped Claude entries from Anthropic, Azure Foundry, Bedrock and Vertex it only fills the keys an entry leaves out, so the entry's own values always win.", "model_info": { "mode": "chat", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, @@ -60739,6 +65455,14 @@ "thinking_always_on": true } }, + { + "name": "claude-thinking-on-by-default", + "pattern": "claude-[a-z]+-[5-9](?!\\d)", + "description": "Claude at major 5 or higher, in any id shape that contains claude--. Anthropic's thinking docs list every Claude 5+ model as thinking by default (on or always on) when the request sends no thinking param, and every 4.x as off. Two-digit majors are deliberately not matched so ids like claude-opus-41 (4.1) are not read as major 41. The response_format json tool is then left unforced, since a forced tool call skips the model's thinking.", + "model_info": { + "thinking_on_by_default": true + } + }, { "name": "claude-mid-conversation-system", "pattern": "claude-[a-z]+-(?:4[-._](?:[89]|[1-9]\\d)(?!\\d)|[5-9](?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)", @@ -60751,12 +65475,21 @@ { "name": "claude-tool-search", "pattern": "claude-[a-z]+-(?:4[-._](?:[5-9]|[1-9]\\d)(?!\\d)|[5-9](?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)", - "fill_missing_for_providers": ["anthropic", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"], - "description": "Claude at version 4.5 or higher, in any id shape that contains claude--: minors 4.5 through 4.99, any later major-minor, and bare 5+ majors so a new family like claude-fable-5 matches. Two-digit majors are deliberately not matched so ids like claude-opus-41 (4.1) are not read as major 41. Anthropic's tool search docs list every Claude 4.5 and newer model as supported and Opus 4.1 and earlier as unsupported, so the flag follows the version instead of a per-model list. azure_ai is left out on purpose: Anthropic documents tool search as unavailable on Azure-hosted Foundry deployments, and the azure_ai/ key cannot tell those from Anthropic-hosted ones.", + "fill_missing_for_providers": ["anthropic", "azure_ai", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"], + "description": "Claude at version 4.5 or higher, in any id shape that contains claude--: minors 4.5 through 4.99, any later major-minor, and bare 5+ majors so a new family like claude-fable-5 matches. Two-digit majors are deliberately not matched so ids like claude-opus-41 (4.1) are not read as major 41. Anthropic's tool search docs list every Claude 4.5 and newer model as supported and Opus 4.1 and earlier as unsupported, so the flag follows the version instead of a per-model list. azure_ai is included because Microsoft Foundry runs tool search for Claude on both Anthropic-hosted and Azure-hosted deployments.", "model_info": { "supports_tool_search": true } }, + { + "name": "claude-per-turn-control", + "pattern": "claude-[a-z]+-(?:4[-._](?:[5-9]|[1-9]\\d)(?!\\d)|[5-9](?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)", + "fill_missing_for_providers": ["bedrock", "bedrock_converse"], + "description": "Claude at version 4.5 or higher, with the same id shapes and version boundaries as claude-tool-search. On 2026-11-05 Bedrock InvokeModel answered 200 with the per-turn-control-2026-07-01 beta on every Claude 4.5 and newer model a QA account reached across 13 regions, and 400 invalid beta flag on Claude 3 Haiku in ca-central-1. The jp., au. and in. profiles answered 200 too, AWS lists no apac. profile for Claude 4.5 or newer, and GovCloud was not tested. Claude 3.5, 3.7, Sonnet 4, Opus 4 and Opus 4.1 were unreachable, so they keep the beta dropped as before. The flag means Bedrock accepts the beta name on the model, as supports_tool_search does for the tool search beta, and Bedrock Invoke forwards the beta only where it is set. It does not promise per-turn output_config works, since on 2026-11-05 Opus 4.8, Opus 5, Sonnet 5 and Fable 5 rejected it with or without the beta. A deployment turns the forward off with model_info supports_per_turn_control false.", + "model_info": { + "supports_per_turn_control": true + } + }, { "name": "wandb-reasoning-baseline", "pattern": "^wandb/", @@ -60765,6 +65498,14 @@ "supports_reasoning": true } }, + { + "name": "minimax-reasoning-baseline", + "pattern": "^minimax/", + "description": "Any MiniMax model id under the minimax/ namespace, anchored so only that provider's ids match. MiniMax ships reasoning models faster than this registry names them, so an id the map has not described yet is treated as reasoning-capable and keeps the caller's reasoning_effort and thinking instead of dropping them. Rules lose to exact entries, so mapped speech, video and image models are unaffected. Carries no mode and no pricing, so cost stays on the standard unpriced behavior.", + "model_info": { + "supports_reasoning": true + } + }, { "name": "openai-reasoning-family-baseline", "pattern": "^(?!.*search-api)(?:[a-z0-9_.-]+/)*(?:ft:)?(?:o[1-9]\\d*(?![a-z0-9])|gpt-[5-9](?:\\.\\d+)?(?![0-9.])|(?:gpt-\\d+(?:\\.\\d+)?(?:-[a-z0-9]+)*-)?(?:codex|deep-research|chat-latest)(?![a-z0-9]))", @@ -60799,7 +65540,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 2.1e-05, "output_cost_per_token": 2.1e-05, @@ -60826,6 +65566,8 @@ "input_cost_per_audio_token": 2e-06, "input_cost_per_token": 2e-06, "litellm_provider": "gemini", + "max_input_tokens": 98304, + "max_output_tokens": 32768, "mode": "audio_transcription", "output_cost_per_token": 1.2e-05, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -60848,6 +65590,8 @@ "input_cost_per_audio_token": 3.5e-06, "input_cost_per_token": 3.5e-06, "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, "mode": "audio_transcription", "output_cost_per_token": 2.1e-05, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -60904,7 +65648,7 @@ }, "vertex_ai/gemini-3.5-live-translate-preview": { "input_cost_per_audio_token": 3.5e-06, - "input_cost_per_second": 8.83333333333e-05, + "input_cost_per_second": 8.75e-05, "input_cost_per_token": 3.5e-06, "litellm_provider": "vertex_ai", "mode": "realtime", @@ -60928,7 +65672,6 @@ "input_cost_per_token": 8e-09, "litellm_provider": "perplexity", "max_input_tokens": 32768, - "max_tokens": 32768, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -60938,7 +65681,6 @@ "input_cost_per_token": 5e-08, "litellm_provider": "perplexity", "max_input_tokens": 32768, - "max_tokens": 32768, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 2560, @@ -60948,7 +65690,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -60958,7 +65699,6 @@ "input_cost_per_token": 6e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -60968,7 +65708,6 @@ "input_cost_per_token": 2e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -60978,7 +65717,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -60988,7 +65726,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 120000, - "max_tokens": 120000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -60998,7 +65735,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -61014,7 +65750,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-07, "output_cost_per_token_priority": 8.25e-07, @@ -61026,19 +65761,20 @@ "supports_vision": false }, "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash": { - "cache_read_input_token_cost": 7e-09, - "cache_read_input_token_cost_priority": 8.75e-09, - "input_cost_per_token": 2.2e-07, - "input_cost_per_token_priority": 2.75e-07, + "cache_read_input_token_cost": 6e-09, + "cache_read_input_token_cost_priority": 7.5e-09, + "input_cost_per_token": 3e-07, + "input_cost_per_token_priority": 3.75e-07, "litellm_provider": "fireworks_ai", + "token_count_framing": 23, "max_input_tokens": 1048576, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", - "output_cost_per_token": 6.6e-07, - "output_cost_per_token_priority": 8.25e-07, - "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_priority": 1.5e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -61053,12 +65789,12 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 1.8e-06, "output_cost_per_token_priority": 2.25e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -61073,7 +65809,7 @@ "input_cost_per_token_priority": 2.75e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-07, "output_cost_per_token_priority": 8.25e-07, @@ -61091,7 +65827,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_priority": 1.875e-05, @@ -61102,11 +65837,39 @@ ], "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/routers/kimi-latest": { + "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_priority": 3.75e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_priority": 3.75e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_priority": 1.875e-05, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, + "fireworks_ai/kimi-latest": { + "alias_of": "fireworks_ai/accounts/fireworks/models/kimi-k3" + }, "fireworks_ai/deepseek-v4-flash-0731": { "cache_read_input_token_cost": 7e-09, "cache_read_input_token_cost_priority": 8.75e-09, @@ -61116,7 +65879,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-07, "output_cost_per_token_priority": 8.25e-07, @@ -61128,19 +65890,20 @@ "supports_vision": false }, "fireworks_ai/deepseek-v4p1-flash": { - "cache_read_input_token_cost": 7e-09, - "cache_read_input_token_cost_priority": 8.75e-09, - "input_cost_per_token": 2.2e-07, - "input_cost_per_token_priority": 2.75e-07, + "cache_read_input_token_cost": 6e-09, + "cache_read_input_token_cost_priority": 7.5e-09, + "input_cost_per_token": 3e-07, + "input_cost_per_token_priority": 3.75e-07, "litellm_provider": "fireworks_ai", + "token_count_framing": 23, "max_input_tokens": 1048576, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", - "output_cost_per_token": 6.6e-07, - "output_cost_per_token_priority": 8.25e-07, - "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_priority": 1.5e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -61155,12 +65918,12 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 1.8e-06, "output_cost_per_token_priority": 2.25e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -61175,7 +65938,7 @@ "input_cost_per_token_priority": 2.75e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-07, "output_cost_per_token_priority": 8.25e-07, @@ -61188,14 +65951,15 @@ "fireworks_ai/glm-5p2-fast": { "cache_read_input_token_cost": 2.1e-07, "deprecation_date": "2026-09-25", + "deprecation_source": "https://docs.fireworks.ai/changelog.md", + "successor_model": "fireworks_ai/glm-5p3", "input_cost_per_token": 2.1e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://docs.fireworks.ai/changelog.md", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -61205,14 +65969,15 @@ "fireworks_ai/glm-5p2-fast-us": { "cache_read_input_token_cost": 2.1e-07, "deprecation_date": "2026-09-25", + "deprecation_source": "https://docs.fireworks.ai/changelog.md", "input_cost_per_token": 2.1e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://docs.fireworks.ai/changelog.md", + "successor_model": "fireworks_ai/glm-5p3", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -61227,7 +65992,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_priority": 1.875e-05, @@ -61238,6 +66002,7 @@ ], "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -61249,7 +66014,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.25e-05, "reasoning_effort_levels": [ @@ -61259,6 +66023,7 @@ ], "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -61272,7 +66037,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.25e-05, "output_cost_per_token_priority": 2.8125e-05, @@ -61283,6 +66047,7 @@ ], "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -61300,6 +66065,7 @@ "output_cost_per_token_priority": 9e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": false, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -61314,7 +66080,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-06, "output_cost_per_token_priority": 2.25e-06, @@ -61327,14 +66092,19 @@ }, "fireworks_ai/nemotron-lightning-3p5-30b-a3b": { "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_priority": 1.25e-08, + "deprecation_date": "2026-11-07", + "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md", "input_cost_per_token": 5e-08, + "input_cost_per_token_priority": 6.25e-08, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2e-07, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 2.5e-07, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "successor_model": "Nemotron Super VL", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -61343,15 +66113,21 @@ }, "fireworks_ai/nemotron-3-ultra-nvfp4": { "cache_read_input_token_cost": 1.2e-07, + "cache_read_input_token_cost_priority": 1.5e-07, + "deprecation_date": "2026-11-07", + "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md", "input_cost_per_token": 6e-07, + "input_cost_per_token_priority": 7.5e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.4e-06, - "source": "https://api.fireworks.ai/v1/serverless/models", + "output_cost_per_token_priority": 3e-06, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "successor_model": "Nemotron Super VL", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -61366,7 +66142,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-06, "output_cost_per_token_priority": 2.25e-06, @@ -61377,16 +66152,38 @@ "supports_tool_choice": true, "supports_vision": true }, + "fireworks_ai/accounts/fireworks/models/muse-spark-open": { + "cache_read_input_token_cost": 1.5e-07, + "cache_read_input_token_cost_priority": 2.25e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_priority": 1.875e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 4.25e-06, + "output_cost_per_token_priority": 6.375e-06, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, "fireworks_ai/accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b": { "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_priority": 1.25e-08, + "deprecation_date": "2026-11-07", + "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md", "input_cost_per_token": 5e-08, + "input_cost_per_token_priority": 6.25e-08, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2e-07, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 2.5e-07, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "successor_model": "Nemotron Super VL", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -61395,15 +66192,21 @@ }, "fireworks_ai/accounts/fireworks/models/nemotron-3-ultra-nvfp4": { "cache_read_input_token_cost": 1.2e-07, + "cache_read_input_token_cost_priority": 1.5e-07, + "deprecation_date": "2026-11-07", + "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md", "input_cost_per_token": 6e-07, + "input_cost_per_token_priority": 7.5e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.4e-06, - "source": "https://api.fireworks.ai/v1/serverless/models", + "output_cost_per_token_priority": 3e-06, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "successor_model": "Nemotron Super VL", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -61419,8 +66222,27 @@ "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_priority": 9e-06, - "source": "https://api.fireworks.ai/v1/serverless/models", + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, + "supports_mid_conversation_system": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/routers/qwen-max-latest": { + "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_priority": 3.75e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_priority": 3e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_priority": 9e-06, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "supports_function_calling": true, + "supports_mid_conversation_system": false, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -61429,14 +66251,15 @@ "fireworks_ai/accounts/fireworks/routers/glm-5p2-fast": { "cache_read_input_token_cost": 2.1e-07, "deprecation_date": "2026-09-25", + "deprecation_source": "https://docs.fireworks.ai/changelog.md", + "successor_model": "fireworks_ai/accounts/fireworks/models/glm-5p3", "input_cost_per_token": 2.1e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-06, - "source": "https://api.fireworks.ai/v1/serverless/models", + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -61446,14 +66269,15 @@ "fireworks_ai/accounts/fireworks/routers/glm-5p2-fast-us": { "cache_read_input_token_cost": 2.1e-07, "deprecation_date": "2026-09-25", + "deprecation_source": "https://docs.fireworks.ai/changelog.md", "input_cost_per_token": 2.1e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://docs.fireworks.ai/changelog.md", + "successor_model": "fireworks_ai/accounts/fireworks/models/glm-5p3", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -61466,7 +66290,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.25e-05, "reasoning_effort_levels": [ @@ -61476,6 +66299,28 @@ ], "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/routers/kimi-fast-latest": { + "cache_read_input_token_cost": 4.5e-07, + "input_cost_per_token": 4.5e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.25e-05, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -61489,7 +66334,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.25e-05, "output_cost_per_token_priority": 2.8125e-05, @@ -61500,6 +66344,7 @@ ], "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -61511,7 +66356,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -61523,12 +66367,11 @@ "supports_vision": false }, "novita/deepseek/deepseek-v4-pro-0813": { - "cache_read_input_token_cost": 1.3200000000000002e-07, + "cache_read_input_token_cost": 4.4e-08, "input_cost_per_token": 1.32e-06, "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 3.96e-06, "source": "https://novita.ai/pricing", @@ -61545,7 +66388,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://novita.ai/pricing", @@ -61562,7 +66404,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 5.8e-07, "source": "https://novita.ai/pricing", @@ -61579,7 +66420,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://novita.ai/pricing", @@ -61596,7 +66436,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://novita.ai/pricing", @@ -61613,7 +66452,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 1.32e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -61630,7 +66468,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 1.32e-06, "source": "https://novita.ai/pricing", @@ -61642,14 +66479,13 @@ "supports_vision": false }, "novita/mindai/macaron-v1-venti": { - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 1.5e-06, + "cache_read_input_token_cost": 1.65e-07, + "input_cost_per_token": 8.25e-07, "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 4.5e-06, + "output_cost_per_token": 2.475e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, @@ -61663,7 +66499,6 @@ "litellm_provider": "novita", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://novita.ai/pricing", @@ -61680,7 +66515,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://novita.ai/pricing", @@ -61697,7 +66531,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 3.2000000000000003e-06, "source": "https://novita.ai/pricing", @@ -61714,7 +66547,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.8e-07, "source": "https://novita.ai/pricing", @@ -61730,7 +66562,6 @@ "litellm_provider": "novita", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://novita.ai/pricing", @@ -61747,7 +66578,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.8e-07, "source": "https://novita.ai/pricing", @@ -61758,14 +66588,13 @@ "supports_vision": false }, "novita/mindai/macaron-v1-tall": { - "cache_read_input_token_cost": 8e-08, - "input_cost_per_token": 4.5000000000000003e-07, + "cache_read_input_token_cost": 4.4e-08, + "input_cost_per_token": 2.475e-07, "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 2.6e-06, + "output_cost_per_token": 1.43e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, @@ -61779,7 +66608,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 1.15e-06, "source": "https://novita.ai/pricing", @@ -61795,7 +66623,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.0000000000000002e-07, "source": "https://novita.ai/pricing", @@ -61811,7 +66638,6 @@ "litellm_provider": "novita", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.13e-06, "source": "https://novita.ai/pricing", @@ -61827,7 +66653,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.3600000000000004e-07, "source": "https://novita.ai/pricing", @@ -61844,7 +66669,6 @@ "litellm_provider": "novita", "max_input_tokens": 1000000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3.75e-06, "source": "https://novita.ai/pricing", @@ -61861,7 +66685,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.044e-06, "source": "https://novita.ai/pricing", @@ -61877,7 +66700,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3.6000000000000003e-06, "source": "https://novita.ai/pricing", @@ -61893,7 +66715,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.4e-06, "source": "https://novita.ai/pricing", @@ -61910,7 +66731,6 @@ "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://novita.ai/pricing", @@ -61927,7 +66747,6 @@ "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -61944,7 +66763,6 @@ "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -61960,7 +66778,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.0000000000000003e-07, "source": "https://novita.ai/pricing", @@ -61975,7 +66792,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.0000000000000003e-07, "source": "https://novita.ai/pricing", @@ -61991,7 +66807,6 @@ "litellm_provider": "novita", "max_input_tokens": 202800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -62008,7 +66823,6 @@ "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://novita.ai/pricing", @@ -62025,7 +66839,6 @@ "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131100, - "max_tokens": 131100, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://novita.ai/pricing", @@ -62041,7 +66854,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://novita.ai/pricing", @@ -62056,7 +66868,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3.2000000000000003e-06, "source": "https://novita.ai/pricing", @@ -62071,7 +66882,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://novita.ai/pricing", @@ -62086,7 +66896,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3.6000000000000003e-06, "source": "https://novita.ai/pricing", @@ -62102,7 +66911,6 @@ "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131100, - "max_tokens": 131100, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://novita.ai/pricing", @@ -62119,7 +66927,6 @@ "litellm_provider": "novita", "max_input_tokens": 202800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.2000000000000003e-06, "source": "https://novita.ai/pricing", @@ -62135,7 +66942,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://novita.ai/pricing", @@ -62149,7 +66955,6 @@ "litellm_provider": "novita", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3e-08, "source": "https://novita.ai/pricing", @@ -62161,7 +66966,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://novita.ai/pricing", @@ -62178,7 +66982,6 @@ "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.2e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -62195,7 +66998,6 @@ "litellm_provider": "novita", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.0000000000000003e-07, "source": "https://novita.ai/pricing", @@ -62211,7 +67013,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.4850000000000002e-06, "source": "https://novita.ai/pricing", @@ -62226,7 +67027,6 @@ "litellm_provider": "novita", "max_input_tokens": 64000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 8.900000000000001e-07, "source": "https://api.novita.ai/v3/openai/models", @@ -62239,7 +67039,6 @@ "litellm_provider": "novita", "max_input_tokens": 64000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -62253,7 +67052,6 @@ "litellm_provider": "novita", "max_input_tokens": 64000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 8.900000000000001e-07, "source": "https://api.novita.ai/v3/openai/models", @@ -62266,7 +67064,6 @@ "litellm_provider": "novita", "max_input_tokens": 64000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -62280,7 +67077,6 @@ "litellm_provider": "novita", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.66e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -62294,7 +67090,6 @@ "litellm_provider": "novita", "max_input_tokens": 131000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 2e-08, "source": "https://api.novita.ai/v3/openai/models", @@ -62303,7 +67098,7 @@ }, "wandb/deepseek-ai/DeepSeek-V4-Flash": { "supports_reasoning": true, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1049000, "input_cost_per_token": 1.4e-07, "output_cost_per_token": 2.8e-07, @@ -62317,20 +67112,20 @@ }, "wandb/deepseek-ai/DeepSeek-V4-Flash-0731": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 2.8e-07, - "cache_read_input_token_cost": 7e-08, + "output_cost_per_token": 2.7e-07, + "cache_read_input_token_cost": 5e-08, "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", "supports_vision": false, - "source": "https://wandb.ai/site/pricing/tokens/" + "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference" }, "wandb/deepseek-ai/DeepSeek-V4-Pro": { "supports_reasoning": true, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1049000, "input_cost_per_token": 1.15e-06, "output_cost_per_token": 2.55e-06, @@ -62344,7 +67139,7 @@ }, "wandb/google/gemma-4-31B-it": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 1e-07, "output_cost_per_token": 3.4e-07, @@ -62355,7 +67150,7 @@ }, "wandb/ibm-granite/granite-4.1-8b": { "deprecation_date": "2026-10-05", - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131000, "input_cost_per_token": 5e-08, "output_cost_per_token": 1e-07, @@ -62366,7 +67161,7 @@ }, "wandb/JetBrains/Mellum2-12B-A2.5B-Instruct": { "deprecation_date": "2026-10-05", - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131000, "input_cost_per_token": 5e-08, "output_cost_per_token": 1e-07, @@ -62377,7 +67172,7 @@ }, "wandb/meta-llama/Llama-3.1-70B-Instruct": { "deprecation_date": "2026-10-05", - "max_tokens": 128000, + "max_output_tokens": 128000, "max_input_tokens": 131000, "input_cost_per_token": 8e-07, "output_cost_per_token": 8e-07, @@ -62388,7 +67183,7 @@ }, "wandb/MiniMaxAI/MiniMax-M3": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 2.3e-07, "output_cost_per_token": 9.6e-07, @@ -62401,20 +67196,20 @@ }, "wandb/moonshotai/Kimi-K2.7-Code": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, - "input_cost_per_token": 7.1e-07, - "output_cost_per_token": 3.5e-06, - "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 6e-07, + "output_cost_per_token": 3e-06, + "cache_read_input_token_cost": 1.2e-07, "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", "supports_vision": true, - "source": "https://wandb.ai/site/pricing/tokens/" + "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference" }, "wandb/moonshotai/Kimi-K2.6": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 6.5e-07, "output_cost_per_token": 3.41e-06, @@ -62427,7 +67222,7 @@ }, "wandb/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 7e-08, "output_cost_per_token": 2e-07, @@ -62440,7 +67235,7 @@ }, "wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 5e-07, "output_cost_per_token": 2.15e-06, @@ -62453,7 +67248,7 @@ }, "wandb/OpenPipe/Qwen3-14B-Instruct": { "deprecation_date": "2026-10-05", - "max_tokens": 32768, + "max_output_tokens": 32768, "max_input_tokens": 32800, "input_cost_per_token": 5e-08, "output_cost_per_token": 2.2e-07, @@ -62464,7 +67259,7 @@ }, "wandb/Qwen/Qwen3.8-27B": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 4e-07, "output_cost_per_token": 3e-06, @@ -62476,19 +67271,21 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/Qwen/Qwen3.6-35B-A3B": { + "cache_read_input_token_cost": 3.5e-08, "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 1.25e-06, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 8.9e-07, "litellm_provider": "wandb", "mode": "chat", "supports_vision": true, - "source": "https://wandb.ai/site/pricing/tokens/" + "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference", + "supports_prompt_caching": true }, "wandb/Qwen/Qwen3.6-27B": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 6e-07, "output_cost_per_token": 3.6e-06, @@ -62503,7 +67300,7 @@ "wandb/Qwen/Qwen3.5-35B-A3B": { "deprecation_date": "2026-10-05", "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1.25e-06, @@ -62514,7 +67311,7 @@ }, "wandb/Qwen/Qwen3-30B-A3B-Instruct-2507": { "deprecation_date": "2026-10-05", - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 1e-07, "output_cost_per_token": 3e-07, @@ -62538,28 +67335,28 @@ "litellm_provider": "wandb", "mode": "chat", "supports_reasoning": true, - "input_cost_per_token": 1e-07, + "input_cost_per_token": 6e-08, "output_cost_per_token": 1.5e-07, - "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost": 1.5e-08, "max_input_tokens": 131000, "supports_prompt_caching": true, - "source": "https://wandb.ai/site/pricing/tokens/" + "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference" }, "wandb/zai-org/GLM-5.2": { "supports_reasoning": true, - "max_tokens": 262144, - "max_input_tokens": 1049000, - "input_cost_per_token": 7.6e-07, + "max_output_tokens": 262144, + "max_input_tokens": 262000, + "input_cost_per_token": 6.2e-07, "output_cost_per_token": 2.42e-06, "cache_read_input_token_cost": 1.4e-07, "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", "supports_vision": false, - "source": "https://wandb.ai/site/pricing/tokens/" + "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference" }, "deepinfra/openai/gpt-oss-120b-Turbo": { - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, @@ -62573,7 +67370,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/MiniMaxAI/MiniMax-M2.7": { - "max_tokens": 196608, + "max_output_tokens": 196608, "max_input_tokens": 196608, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1e-06, @@ -62589,7 +67386,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.8-27B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 4e-07, "output_cost_per_token": 3e-06, @@ -62605,7 +67402,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-4-31B-it-Ultra": { - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 2.7e-07, "output_cost_per_token": 7.6e-07, @@ -62619,7 +67416,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/moonshotai/Kimi-K2.5": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 4.5e-07, "output_cost_per_token": 2.25e-06, @@ -62635,7 +67432,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-4.7-Flash": { - "max_tokens": 202752, + "max_output_tokens": 202752, "max_input_tokens": 202752, "input_cost_per_token": 6e-08, "output_cost_per_token": 4e-07, @@ -62651,7 +67448,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-4.6": { - "max_tokens": 202752, + "max_output_tokens": 202752, "max_input_tokens": 202752, "input_cost_per_token": 5e-07, "output_cost_per_token": 2e-06, @@ -62670,7 +67467,7 @@ "input_cost_per_token": 5e-06, "litellm_provider": "deepinfra", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-05, "prompt_cache_min_tokens": 1024, @@ -62684,7 +67481,7 @@ "supports_vision": true }, "deepinfra/anthropic/claude-sonnet-4-6": { - "max_tokens": 1000000, + "max_output_tokens": 1000000, "max_input_tokens": 1000000, "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, @@ -62700,7 +67497,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemini-3.5-flash": { - "max_tokens": 1000000, + "max_output_tokens": 1000000, "max_input_tokens": 1000000, "input_cost_per_token": 1.5e-06, "output_cost_per_token": 9e-06, @@ -62715,7 +67512,7 @@ "supports_audio_input": true }, "deepinfra/XiaomiMiMo/MiMo-V2.5": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 4e-07, "output_cost_per_token": 2e-06, @@ -62731,7 +67528,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Max": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 1.2e-06, "output_cost_per_token": 6e-06, @@ -62746,7 +67543,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-4-31B-it-turbo": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 9e-08, "output_cost_per_token": 3.4e-07, @@ -62761,7 +67558,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/thinkingmachines/Inkling-Small": { - "max_tokens": 524288, + "max_output_tokens": 524288, "max_input_tokens": 524288, "input_cost_per_token": 4.5e-07, "output_cost_per_token": 1.2e-06, @@ -62777,7 +67574,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-models/Muse-Glimmer-30B": { - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, @@ -62793,7 +67590,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Max-Thinking": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 1.2e-06, "output_cost_per_token": 6e-06, @@ -62808,7 +67605,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 2e-07, "output_cost_per_token": 8.8e-07, @@ -62823,7 +67620,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, @@ -62836,7 +67633,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.5-27B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 2.6e-07, "output_cost_per_token": 2.6e-06, @@ -62850,7 +67647,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.6-35B-A3B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 1e-07, "output_cost_per_token": 9.5e-07, @@ -62864,7 +67661,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/nvidia/Nemotron-Content-Safety-3.5": { - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, @@ -62877,7 +67674,7 @@ "input_cost_per_token": 5e-06, "litellm_provider": "deepinfra", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-05, "prompt_cache_min_tokens": 512, @@ -62891,7 +67688,7 @@ "supports_vision": true }, "deepinfra/thinkingmachines/Inkling": { - "max_tokens": 524288, + "max_output_tokens": 524288, "max_input_tokens": 524288, "input_cost_per_token": 9.5e-07, "output_cost_per_token": 4.05e-06, @@ -62907,7 +67704,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/moonshotai/Kimi-K2.6": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 7.5e-07, "output_cost_per_token": 3.5e-06, @@ -62923,7 +67720,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813": { - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 1.3e-06, "output_cost_per_token": 2.6e-06, @@ -62938,7 +67735,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.7-Max": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 2.5e-06, "output_cost_per_token": 7.5e-06, @@ -62953,7 +67750,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/ByteDance/Seed-2.0-mini": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 1e-07, "output_cost_per_token": 4e-07, @@ -62969,7 +67766,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.8-2.4T-A95B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 2e-06, "output_cost_per_token": 6e-06, @@ -62985,7 +67782,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/MiniMaxAI/MiniMax-M3": { - "max_tokens": 524288, + "max_output_tokens": 524288, "max_input_tokens": 524288, "input_cost_per_token": 2.8e-07, "output_cost_per_token": 1.1e-06, @@ -63001,7 +67798,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemini-3.1-flash-lite": { - "max_tokens": 1000000, + "max_output_tokens": 1000000, "max_input_tokens": 1000000, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1.5e-06, @@ -63016,7 +67813,7 @@ "supports_audio_input": true }, "deepinfra/google/gemini-3.7-flash": { - "max_tokens": 1000000, + "max_output_tokens": 1000000, "max_input_tokens": 1000000, "input_cost_per_token": 7.5e-07, "output_cost_per_token": 3.75e-06, @@ -63026,12 +67823,13 @@ "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, + "supports_sampling_params": false, "supports_vision": true, "source": "https://deepinfra.com/pricing", "supports_audio_input": true }, "deepinfra/inclusionAI/Ling-3.0-flash": { - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 6e-08, "output_cost_per_token": 1.8e-07, @@ -63047,7 +67845,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/stepfun-ai/Step-3.7-Flash": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 2e-07, "output_cost_per_token": 1.15e-06, @@ -63061,7 +67859,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.5-35B-A3B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 1.4e-07, "output_cost_per_token": 1e-06, @@ -63077,7 +67875,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/ByteDance/Seed-1.8": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 2e-06, @@ -63093,7 +67891,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/tencent/Hy3": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 1.4e-07, "output_cost_per_token": 5.8e-07, @@ -63109,7 +67907,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/ByteDance/Seed-2.0-code": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 5e-07, "output_cost_per_token": 3e-06, @@ -63125,7 +67923,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/ByteDance/Seed-2.0-pro": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 5e-07, "output_cost_per_token": 3e-06, @@ -63141,7 +67939,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-5": { - "max_tokens": 202752, + "max_output_tokens": 202752, "max_input_tokens": 202752, "input_cost_per_token": 6e-07, "output_cost_per_token": 2.08e-06, @@ -63157,7 +67955,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/nvidia/Nemotron-3-Nano-30B-A3B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 5e-08, "output_cost_per_token": 2e-07, @@ -63172,7 +67970,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/moonshotai/Kimi-K2.7-Code": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 6.8e-07, "output_cost_per_token": 3.4e-06, @@ -63188,12 +67986,12 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/anthropic/claude-sonnet-5": { - "input_cost_per_token": 2e-06, + "input_cost_per_token": 3e-06, "litellm_provider": "deepinfra", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 1e-05, + "output_cost_per_token": 1.5e-05, "prompt_cache_min_tokens": 1024, "source": "https://deepinfra.com/pricing", "supports_adaptive_thinking": true, @@ -63205,7 +68003,7 @@ "supports_vision": true }, "deepinfra/Qwen/Qwen3.5-397B-A17B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 4.5e-07, "output_cost_per_token": 3e-06, @@ -63221,11 +68019,11 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731": { - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1048576, - "input_cost_per_token": 8e-08, + "input_cost_per_token": 6e-08, "output_cost_per_token": 1.8e-07, - "cache_read_input_token_cost": 1.6e-08, + "cache_read_input_token_cost": 1.5e-08, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", @@ -63237,7 +68035,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-4-E4B-it": { - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 2e-08, "output_cost_per_token": 1e-07, @@ -63250,7 +68048,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V3.2": { - "max_tokens": 163840, + "max_output_tokens": 163840, "max_input_tokens": 163840, "input_cost_per_token": 2.6e-07, "output_cost_per_token": 3.8e-07, @@ -63265,7 +68063,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.8-Max": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 1.65e-06, "output_cost_per_token": 4.951e-06, @@ -63283,7 +68081,7 @@ "input_cost_per_token": 1e-05, "litellm_provider": "deepinfra", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 5e-05, "prompt_cache_min_tokens": 512, @@ -63298,7 +68096,7 @@ "thinking_always_on": true }, "deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 5e-07, "output_cost_per_token": 2.2e-06, @@ -63314,7 +68112,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.5-122B-A10B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 2.9e-07, "output_cost_per_token": 2.4e-06, @@ -63328,7 +68126,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-5.1": { - "max_tokens": 202752, + "max_output_tokens": 202752, "max_input_tokens": 202752, "input_cost_per_token": 1.05e-06, "output_cost_per_token": 3.5e-06, @@ -63344,7 +68142,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V4-Pro": { - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 1.3e-06, "output_cost_per_token": 2.6e-06, @@ -63359,9 +68157,9 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, - "input_cost_per_token": 8.5e-08, + "input_cost_per_token": 7.5e-08, "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", @@ -63373,7 +68171,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-5.2": { - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 7.5e-07, "output_cost_per_token": 2.4e-06, @@ -63389,7 +68187,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/moonshotai/Kimi-K3": { - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 2.85e-06, "output_cost_per_token": 1.425e-05, @@ -63407,7 +68205,7 @@ "input_cost_per_token": 5e-06, "litellm_provider": "deepinfra", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-05, "prompt_cache_min_tokens": 2048, @@ -63421,7 +68219,7 @@ "supports_vision": true }, "deepinfra/Qwen/Qwen3.6-27B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 3.2e-07, "output_cost_per_token": 3.2e-06, @@ -63435,7 +68233,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-4-26B-A4B-it": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 7e-08, "output_cost_per_token": 3.4e-07, @@ -63449,7 +68247,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemini-3.1-pro": { - "max_tokens": 1000000, + "max_output_tokens": 1000000, "max_input_tokens": 1000000, "input_cost_per_token": 2e-06, "output_cost_per_token": 1.2e-05, @@ -63464,7 +68262,7 @@ "supports_audio_input": true }, "deepinfra/XiaomiMiMo/MiMo-V2.5-Pro": { - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 1e-06, "output_cost_per_token": 3e-06, @@ -63480,7 +68278,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/anthropic/claude-haiku-4-5": { - "max_tokens": 200000, + "max_output_tokens": 200000, "max_input_tokens": 200000, "input_cost_per_token": 1e-06, "output_cost_per_token": 5e-06, @@ -63495,7 +68293,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V4-Flash": { - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 9e-08, "output_cost_per_token": 1.8e-07, @@ -63510,8 +68308,40 @@ "supports_vision": false, "source": "https://deepinfra.com/pricing" }, + "deepinfra/deepseek-ai/DeepSeek-V4.1-Flash": { + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 4.2e-07, + "cache_read_input_token_cost": 4.2e-09, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/deepseek-ai/DeepSeek-V4.1-Flash" + }, + "deepinfra/deepseek-ai/DeepSeek-V4.1-Flash-1017": { + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 4.2e-07, + "cache_read_input_token_cost": 4.2e-09, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/deepseek-ai/DeepSeek-V4.1-Flash-1017" + }, "deepinfra/openai/gpt-oss-120b-Ultra": { - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 9.5e-07, @@ -63525,7 +68355,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.5-9B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 1e-07, "output_cost_per_token": 1.5e-07, @@ -63538,7 +68368,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/MiniMaxAI/MiniMax-M2.7-Turbo": { - "max_tokens": 196608, + "max_output_tokens": 196608, "max_input_tokens": 196608, "input_cost_per_token": 3.8e-07, "output_cost_per_token": 1.7e-06, @@ -63554,7 +68384,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-4.7": { - "max_tokens": 202752, + "max_output_tokens": 202752, "max_input_tokens": 202752, "input_cost_per_token": 4e-07, "output_cost_per_token": 1.75e-06, @@ -63570,10 +68400,10 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-4-31B-it": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 3.8e-07, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, @@ -63584,18 +68414,20 @@ "source": "https://deepinfra.com/pricing" }, "gemini/gemini-omni-1.1-flash": { + "deprecation_date": "2026-12-03", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", "input_cost_per_audio_token": 1.5e-06, "input_cost_per_token": 1.5e-06, "litellm_provider": "gemini", - "max_input_tokens": 1048576, + "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, "output_cost_per_video_token": 1.75e-05, "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://ai.google.dev/gemini-api/docs/models/gemini-omni-flash", + "successor_model": "gemini/gemini-omni-1.2-flash", "supported_endpoints": [ "/v1beta/interactions" ], @@ -63624,7 +68456,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, @@ -63652,7 +68483,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, @@ -63680,7 +68510,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, @@ -63734,10 +68563,12 @@ }, "xai/grok-imagine-image-quality": { "deprecation_date": "2026-11-02", + "deprecation_source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", "input_cost_per_image": 0.05, "litellm_provider": "xai", "mode": "image_generation", "source": "https://docs.x.ai/docs/models", + "successor_model": "xai/grok-imagine-image-2.0", "supported_endpoints": [ "/v1/images/generations" ], @@ -63751,10 +68582,12 @@ }, "xai/grok-imagine-image-quality-20260403": { "deprecation_date": "2026-11-02", + "deprecation_source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", "input_cost_per_image": 0.05, "litellm_provider": "xai", "mode": "image_generation", "source": "https://docs.x.ai/docs/models", + "successor_model": "xai/grok-imagine-image-2.0", "supported_endpoints": [ "/v1/images/generations" ], @@ -63768,10 +68601,12 @@ }, "xai/grok-imagine-image-quality-latest": { "deprecation_date": "2026-11-02", + "deprecation_source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", "input_cost_per_image": 0.05, "litellm_provider": "xai", "mode": "image_generation", "source": "https://docs.x.ai/docs/models", + "successor_model": "xai/grok-imagine-image-2.0", "supported_endpoints": [ "/v1/images/generations" ], @@ -63784,10 +68619,13 @@ ] }, "xai/grok-imagine-image-pro": { + "deprecation_date": "2026-05-15", + "deprecation_source": "https://docs.x.ai/developers/migration/may-15-retirement", "input_cost_per_image": 0.05, "litellm_provider": "xai", "mode": "image_generation", "source": "https://docs.x.ai/docs/models", + "successor_model": "xai/grok-imagine-image-2.0", "supported_endpoints": [ "/v1/images/generations" ], @@ -63803,7 +68641,9 @@ "input_cost_per_image": 0.06, "litellm_provider": "xai", "mode": "image_generation", - "source": "https://docs.x.ai/docs/models", + "output_cost_per_image_1K": 0.04, + "output_cost_per_image_2K": 0.06, + "source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", "supported_endpoints": [ "/v1/images/generations" ], @@ -63850,6 +68690,23 @@ "video" ] }, + "xai/grok-imagine-video-1.5-lite": { + "input_cost_per_image": 0.01, + "litellm_provider": "xai", + "mode": "video_generation", + "output_cost_per_second": 0.02, + "output_cost_per_second_1080p": 0.14, + "output_cost_per_second_480p": 0.02, + "output_cost_per_second_720p": 0.03, + "source": "https://docs.x.ai/developers/pricing", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, "xai/grok-imagine-video-1.5-2026-05-30": { "input_cost_per_image": 0.01, "litellm_provider": "xai", @@ -63887,6 +68744,9 @@ ] }, "xai/grok-voice-transcribe-1.0": { + "deprecation_date": "2026-10-02", + "deprecation_source": "https://docs.x.ai/docs/release-notes", + "successor_model": "xai/grok-voice-transcribe-2.0", "input_cost_per_second": 2.778e-05, "litellm_provider": "xai", "metadata": { @@ -63938,7 +68798,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, @@ -63965,7 +68824,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, @@ -63992,7 +68850,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, @@ -64023,7 +68880,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, @@ -64051,7 +68907,6 @@ "litellm_provider": "groq", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://console.groq.com/docs/model/qwen/qwen3.8-27b", @@ -64067,7 +68922,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ @@ -64088,7 +68942,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ @@ -64109,7 +68962,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ @@ -64130,7 +68982,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 6e-07, "reasoning_effort_levels": [ @@ -64151,7 +69002,6 @@ "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://docs.mistral.ai/models/model-cards/codestral-25-08", @@ -64166,7 +69016,6 @@ "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://docs.mistral.ai/models/model-cards/codestral-25-08", @@ -64181,12 +69030,16 @@ "litellm_provider": "mistral", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, + "reasoning_effort_levels": [ + "none", + "high" + ], "source": "https://mistral.ai/news/devstral-2-vibe-cli", "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, @@ -64282,13 +69135,14 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://docs.mistral.ai/models/model-cards/leanstral-1-5", "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true }, "fireworks_ai/accounts/fireworks/models/glm-5p3": { "cache_read_input_token_cost": 2.6e-07, @@ -64298,12 +69152,31 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_priority": 5.5e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/accounts/fireworks/routers/glm-latest": { + "cache_read_input_token_cost": 2.6e-07, + "cache_read_input_token_cost_priority": 3.25e-07, + "input_cost_per_token": 1.4e-06, + "input_cost_per_token_priority": 1.75e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "output_cost_per_token_priority": 5.5e-06, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -64311,15 +69184,18 @@ }, "fireworks_ai/accounts/fireworks/routers/glm-5p3-us": { "cache_read_input_token_cost": 3.9e-07, + "cache_read_input_token_cost_priority": 4.875e-07, "input_cost_per_token": 2.1e-06, + "input_cost_per_token_priority": 2.625e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6.6e-06, + "output_cost_per_token_priority": 8.25e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -64333,12 +69209,12 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_priority": 5.5e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -64346,15 +69222,18 @@ }, "fireworks_ai/glm-5p3-us": { "cache_read_input_token_cost": 3.9e-07, + "cache_read_input_token_cost_priority": 4.875e-07, "input_cost_per_token": 2.1e-06, + "input_cost_per_token_priority": 2.625e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6.6e-06, + "output_cost_per_token_priority": 8.25e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -64365,11 +69244,28 @@ "input_cost_per_token": 2.1e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/accounts/fireworks/routers/glm-fast-latest": { + "cache_read_input_token_cost": 3.9e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -64407,11 +69303,12 @@ "input_cost_per_token": 2.1e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -64424,26 +69321,52 @@ "input_cost_per_token_priority": 1.875e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_priority": 6.25e-07, - "source": "https://api.fireworks.ai/v1/serverless/models", + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/routers/glm-flash-latest": { + "cache_read_input_token_cost": 3e-08, + "cache_read_input_token_cost_priority": 3.75e-08, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_priority": 1.875e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_priority": 6.25e-07, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/accounts/fireworks/routers/glm-5p3-flash-us": { "cache_read_input_token_cost": 4.5e-08, + "cache_read_input_token_cost_priority": 5.625e-08, + "deprecation_date": "2026-11-07", + "deprecation_source": "https://docs.fireworks.ai/changelog.md", "input_cost_per_token": 2.25e-07, + "input_cost_per_token_priority": 2.8125e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 7.5e-07, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 9.375e-07, + "source": "https://docs.fireworks.ai/changelog.md", + "successor_model": "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017-us", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true @@ -64455,40 +69378,55 @@ "input_cost_per_token_priority": 1.875e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_priority": 6.25e-07, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/glm-5p3-flash-us": { "cache_read_input_token_cost": 4.5e-08, + "cache_read_input_token_cost_priority": 5.625e-08, + "deprecation_date": "2026-11-07", + "deprecation_source": "https://docs.fireworks.ai/changelog.md", "input_cost_per_token": 2.25e-07, + "input_cost_per_token_priority": 2.8125e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 7.5e-07, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 9.375e-07, + "source": "https://docs.fireworks.ai/changelog.md", + "successor_model": "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017-us", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/accounts/fireworks/models/inkling": { "cache_read_input_token_cost": 1.7e-07, + "cache_read_input_token_cost_priority": 1.7e-07, + "deprecation_date": "2026-11-07", + "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md", "input_cost_per_token": 1e-06, + "input_cost_per_token_priority": 1e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.05e-06, - "source": "https://fireworks.ai/models/fireworks/inkling", + "output_cost_per_token_priority": 4.05e-06, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "successor_model": "fireworks_ai/accounts/fireworks/models/muse-spark-open", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true @@ -64499,9 +69437,8 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 40960, "max_output_tokens": 40960, - "max_tokens": 40960, "mode": "embedding", - "source": "https://api.fireworks.ai/v1/serverless/models" + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested" }, "zai/glm-5.2": { "cache_creation_input_token_cost": 0, @@ -64518,15 +69455,192 @@ "supports_reasoning": true, "supports_tool_choice": true }, + "zerogpu/deepseek-v4.1-flash": { + "cache_read_input_token_cost": 3e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "zerogpu", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://docs.zerogpu.ai/docs/model-catalog", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "zerogpu/glm-5.3-flash": { + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "zerogpu", + "max_input_tokens": 1048576, + "max_output_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3.5e-07, + "source": "https://docs.zerogpu.ai/docs/model-catalog", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "zerogpu/gpt-4.1-mini": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 4e-07, + "litellm_provider": "zerogpu", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "source": "https://docs.zerogpu.ai/docs/model-catalog", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "zerogpu/gpt-5.4-nano": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "zerogpu", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "source": "https://docs.zerogpu.ai/docs/model-catalog", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "zerogpu/gpt-5.6-luna": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-07, + "litellm_provider": "zerogpu", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://docs.zerogpu.ai/docs/model-catalog", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "zerogpu/gpt-6-luna": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "zerogpu", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://docs.zerogpu.ai/docs/model-catalog", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "zerogpu/gpt-oss-120b": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "zerogpu", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://docs.zerogpu.ai/docs/model-catalog", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "zerogpu/LFM2.5-1.2B-Instruct": { + "input_cost_per_token": 2e-08, + "litellm_provider": "zerogpu", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5e-08, + "source": "https://docs.zerogpu.ai/docs/model-catalog" + }, + "zerogpu/LFM2.5-1.2B-Thinking": { + "input_cost_per_token": 2e-08, + "litellm_provider": "zerogpu", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5e-08, + "source": "https://docs.zerogpu.ai/docs/model-catalog" + }, + "zerogpu/llama-3.1-8b-instruct-fast": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "zerogpu", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "source": "https://docs.zerogpu.ai/docs/model-catalog", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "zerogpu/llama-3.2-3b-instruct-fast": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 5e-08, + "litellm_provider": "zerogpu", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://docs.zerogpu.ai/docs/model-catalog" + }, + "zerogpu/qwen3-30b-a3b-fp8": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "zerogpu", + "max_input_tokens": 32768, + "max_output_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 4.5e-07, + "source": "https://docs.zerogpu.ai/docs/model-catalog", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "zerogpu/qwen3.6-35b-a3b": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-07, + "litellm_provider": "zerogpu", + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://docs.zerogpu.ai/docs/model-catalog", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "together_ai/Qwen/Qwen3.8-Flash": { - "input_cost_per_token": 9e-08, + "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 2.82e-07, + "output_cost_per_token": 4.7e-07, "source": "https://api.together.ai/v1/models" }, + "together_ai/qwen-flash-latest": { + "alias_of": "together_ai/Qwen/Qwen3.8-Flash" + }, "together_ai/moonshotai/Kimi-K2.5-fp4": { "input_cost_per_token": 5e-07, "output_cost_per_token": 2.8e-06, @@ -64561,6 +69675,8 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/nvidia/NVIDIA-Nemotron-Nano-9B-v2": { + "deprecation_date": "2026-02-25", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 6e-08, "output_cost_per_token": 2.5e-07, "litellm_provider": "together_ai", @@ -64581,7 +69697,6 @@ "litellm_provider": "cerebras", "max_input_tokens": 131072, "max_output_tokens": 40960, - "max_tokens": 40960, "mode": "chat", "output_cost_per_token": 1.49e-06, "source": "https://api.cerebras.ai/public/v1/models/gemma-4-31b", @@ -64603,11 +69718,11 @@ ] }, "scaleway/glm-5.2": { + "deprecation_date": "2026-11-16", "input_cost_per_token": 1.8e-06, "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://www.scaleway.com/en/pricing/model-as-a-service/", @@ -64621,7 +69736,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-07, "source": "https://www.scaleway.com/en/pricing/model-as-a-service/", @@ -64632,12 +69746,12 @@ }, "azure_ai/kimi-k2.7-code": { "cache_read_input_token_cost": 1.9e-07, - "deprecation_date": "2026-10-03", + "deprecation_date": "2027-04-16", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 9.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -64649,6 +69763,7 @@ "text" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -64660,20 +69775,22 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 1.2e-06, "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "deprecation_date": "2026-12-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/deepseek-v4-1-flash-is-coming-to-microsoft-foundry/4556431" }, "azure_ai/MAI-Image-2.6": { "input_cost_per_image_token": 8e-06, "input_cost_per_token": 5e-06, "litellm_provider": "azure_ai", + "max_input_tokens": 32000, "mode": "image_generation", "output_cost_per_image_token": 3.8e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -64686,6 +69803,7 @@ "input_cost_per_image_token": 2.5e-06, "input_cost_per_token": 1.75e-06, "litellm_provider": "azure_ai", + "max_input_tokens": 32000, "mode": "image_generation", "output_cost_per_image_token": 1.9e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -64700,11 +69818,11 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true @@ -64715,11 +69833,11 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.1e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true @@ -64730,30 +69848,36 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, + "azure_ai/glm-latest": { + "alias_of": "azure_ai/FW-GLM-5.3" + }, "azure_ai/FW-GLM-5.3-Flash": { "cache_read_input_token_cost": 3.8e-08, "input_cost_per_token": 1.88e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.25e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, + "azure_ai/glm-flash-latest": { + "alias_of": "azure_ai/FW-GLM-5.3-Flash" + }, "azure_ai/FW-GPT-OSS-120B": { "deprecation_date": "2027-07-01", "cache_read_input_token_cost": 8.2e-08, @@ -64761,12 +69885,12 @@ "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -64774,15 +69898,17 @@ }, "azure_ai/Cohere-command-a-plus-05-2026": { "deprecation_date": "2026-10-16", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "coherelabs-command-a-plus-05-2026-fp81", "input_cost_per_token": 8e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 3.2e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_reasoning": true, "supports_tool_choice": true }, @@ -64791,7 +69917,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 7.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -64802,74 +69927,101 @@ "supported_output_modalities": [ "text" ], + "supports_pdf_input": false, "supports_response_schema": true, "supports_vision": true }, "azure_ai/deepseek-r1": { "deprecation_date": "2026-08-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/deepseek-v4-pro", "input_cost_per_token": 1.35e-06, "output_cost_per_token": 5.4e-06, "litellm_provider": "azure_ai", "mode": "chat", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_pdf_input": false }, "azure_ai/deepseek-v3-0324": { "deprecation_date": "2026-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/deepseek-v4-flash", "input_cost_per_token": 1.14e-06, "output_cost_per_token": 4.56e-06, "litellm_provider": "azure_ai", "mode": "chat", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_pdf_input": false }, "azure_ai/deepseek-v3.1": { "deprecation_date": "2026-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/deepseek-v4-flash", "input_cost_per_token": 1.23e-06, "output_cost_per_token": 4.94e-06, "litellm_provider": "azure_ai", "mode": "chat", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_pdf_input": false }, "azure_ai/grok-3": { "deprecation_date": "2026-05-01", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/grok-4", "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "litellm_provider": "azure_ai", "mode": "chat", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_pdf_input": false }, "azure_ai/grok-3-mini": { "deprecation_date": "2026-05-01", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/grok-4-1-fast-reasoning", "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1.27e-06, "litellm_provider": "azure_ai", "mode": "chat", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_pdf_input": false }, "azure_ai/grok-4-fast-non-reasoning": { "deprecation_date": "2026-05-01", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/grok-4-1-fast-non-reasoning", "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, "litellm_provider": "azure_ai", "mode": "chat", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_pdf_input": false }, "azure_ai/grok-4-fast-reasoning": { "deprecation_date": "2026-05-01", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/grok-4-1-fast-reasoning", "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, "litellm_provider": "azure_ai", "mode": "chat", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_pdf_input": false }, "bedrock/us-gov-west-1/nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 7.2e-08, + "input_cost_per_token_batches": 3.6e-08, + "input_cost_per_token_flex": 3.6e-08, + "input_cost_per_token_priority": 1.32e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.88e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 1.44e-07, + "output_cost_per_token_flex": 1.44e-07, + "output_cost_per_token_priority": 5.04e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, @@ -64879,13 +70031,21 @@ "supports_vision": false }, "bedrock/us-gov-west-1/nvidia.nemotron-nano-12b-v2": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-12b-v2-vl-bf16.html", "input_cost_per_token": 2.4e-07, + "input_cost_per_token_batches": 1.2e-07, + "input_cost_per_token_flex": 1.2e-07, + "input_cost_per_token_priority": 4.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, + "output_cost_per_token_batches": 3.6e-07, + "output_cost_per_token_flex": 3.6e-07, + "output_cost_per_token_priority": 1.26e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supports_system_messages": true, "supports_vision": true, "supports_audio_input": false, @@ -64893,13 +70053,21 @@ "supports_response_schema": true }, "bedrock/us-gov-west-1/nvidia.nemotron-nano-9b-v2": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-9b-v2.html", "input_cost_per_token": 7.2e-08, + "input_cost_per_token_batches": 3.6e-08, + "input_cost_per_token_flex": 3.6e-08, + "input_cost_per_token_priority": 1.32e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.76e-07, + "output_cost_per_token_batches": 1.44e-07, + "output_cost_per_token_flex": 1.44e-07, + "output_cost_per_token_priority": 4.8e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supports_system_messages": true, "supports_audio_input": false, "supports_function_calling": true, @@ -64908,13 +70076,18 @@ }, "bedrock/us-gov-west-1/nvidia.nemotron-super-3-120b": { "input_cost_per_token": 1.8e-07, + "input_cost_per_token_batches": 9e-08, + "input_cost_per_token_flex": 9e-08, + "input_cost_per_token_priority": 3.15e-07, "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.8e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 3.9e-07, + "output_cost_per_token_flex": 3.9e-07, + "output_cost_per_token_priority": 1.365e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -64924,26 +70097,50 @@ "supports_vision": false }, "bedrock/us-gov-west-1/openai.gpt-oss-20b-1:0": { + "supports_vision": false, "input_cost_per_token": 8.4e-08, + "input_cost_per_token_batches": 4.2e-08, + "input_cost_per_token_flex": 4.2e-08, + "input_cost_per_token_priority": 1.47e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 3.6e-07, + "output_cost_per_token_batches": 1.8e-07, + "output_cost_per_token_flex": 1.8e-07, + "output_cost_per_token_priority": 6.3e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "bedrock/us-gov-west-1/openai.gpt-oss-120b-1:0": { + "supports_vision": false, "input_cost_per_token": 1.8e-07, + "input_cost_per_token_batches": 9e-08, + "input_cost_per_token_flex": 9e-08, + "input_cost_per_token_priority": 3.15e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 7.2e-07, + "output_cost_per_token_batches": 3.6e-07, + "output_cost_per_token_flex": 3.6e-07, + "output_cost_per_token_priority": 1.26e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -64960,17 +70157,18 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "prompt_cache_min_tokens": 1024, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -64980,7 +70178,12 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "bedrock/us-gov-west-1/anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -64993,7 +70196,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 1024, @@ -65004,6 +70206,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -65013,7 +70216,12 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "bedrock/us-gov-west-1/anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, @@ -65025,11 +70233,11 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 512, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -65045,7 +70253,15 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + }, + "input_cost_per_token_batches": 3e-06, + "output_cost_per_token_batches": 1.5e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-gov-west-1/index.json" }, "bedrock/us-gov-west-1/anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -65057,7 +70273,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.4e-05, "prompt_cache_min_tokens": 512, @@ -65068,6 +70283,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -65080,7 +70296,12 @@ "supports_xhigh_reasoning_effort": true, "thinking_always_on": true, "supports_forced_tool_use": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "bedrock/us-gov-west-1/anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.5e-05, @@ -65090,7 +70311,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-05, "supports_adaptive_thinking": true, @@ -65109,21 +70329,66 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "token_count_model": { + "model": "anthropic.claude-fable-5-1", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } + }, + "bedrock/us-gov-west-1/anthropic.claude-fable-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.2e-05, + "cache_creation_input_token_cost_above_1hr": 1.92e-05, + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 9.6e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.8e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true }, "bedrock/us-gov-east-1/nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 7.2e-08, + "input_cost_per_token_batches": 3.6e-08, + "input_cost_per_token_flex": 3.6e-08, + "input_cost_per_token_priority": 1.32e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.88e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 1.44e-07, + "output_cost_per_token_flex": 1.44e-07, + "output_cost_per_token_priority": 5.04e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, @@ -65133,13 +70398,21 @@ "supports_vision": false }, "bedrock/us-gov-east-1/nvidia.nemotron-nano-12b-v2": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-12b-v2-vl-bf16.html", "input_cost_per_token": 2.4e-07, + "input_cost_per_token_batches": 1.2e-07, + "input_cost_per_token_flex": 1.2e-07, + "input_cost_per_token_priority": 4.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, + "output_cost_per_token_batches": 3.6e-07, + "output_cost_per_token_flex": 3.6e-07, + "output_cost_per_token_priority": 1.26e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supports_system_messages": true, "supports_vision": true, "supports_audio_input": false, @@ -65147,13 +70420,21 @@ "supports_response_schema": true }, "bedrock/us-gov-east-1/nvidia.nemotron-nano-9b-v2": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-9b-v2.html", "input_cost_per_token": 7.2e-08, + "input_cost_per_token_batches": 3.6e-08, + "input_cost_per_token_flex": 3.6e-08, + "input_cost_per_token_priority": 1.32e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.76e-07, + "output_cost_per_token_batches": 1.44e-07, + "output_cost_per_token_flex": 1.44e-07, + "output_cost_per_token_priority": 4.8e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supports_system_messages": true, "supports_audio_input": false, "supports_function_calling": true, @@ -65162,13 +70443,18 @@ }, "bedrock/us-gov-east-1/nvidia.nemotron-super-3-120b": { "input_cost_per_token": 1.8e-07, + "input_cost_per_token_batches": 9e-08, + "input_cost_per_token_flex": 9e-08, + "input_cost_per_token_priority": 3.15e-07, "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.8e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 3.9e-07, + "output_cost_per_token_flex": 3.9e-07, + "output_cost_per_token_priority": 1.365e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -65178,26 +70464,50 @@ "supports_vision": false }, "bedrock/us-gov-east-1/openai.gpt-oss-20b-1:0": { + "supports_vision": false, "input_cost_per_token": 8.4e-08, + "input_cost_per_token_batches": 4.2e-08, + "input_cost_per_token_flex": 4.2e-08, + "input_cost_per_token_priority": 1.47e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 3.6e-07, + "output_cost_per_token_batches": 1.8e-07, + "output_cost_per_token_flex": 1.8e-07, + "output_cost_per_token_priority": 6.3e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "bedrock/us-gov-east-1/openai.gpt-oss-120b-1:0": { + "supports_vision": false, "input_cost_per_token": 1.8e-07, + "input_cost_per_token_batches": 9e-08, + "input_cost_per_token_flex": 9e-08, + "input_cost_per_token_priority": 3.15e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 7.2e-07, + "output_cost_per_token_batches": 3.6e-07, + "output_cost_per_token_flex": 3.6e-07, + "output_cost_per_token_priority": 1.26e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -65214,17 +70524,18 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "prompt_cache_min_tokens": 1024, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -65247,7 +70558,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 1024, @@ -65258,6 +70568,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -65279,11 +70590,11 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 512, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -65299,7 +70610,10 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "input_cost_per_token_batches": 3e-06, + "output_cost_per_token_batches": 1.5e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-gov-east-1/index.json" }, "bedrock/us-gov-east-1/anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -65311,7 +70625,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.4e-05, "prompt_cache_min_tokens": 512, @@ -65322,6 +70635,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -65344,7 +70658,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-05, "supports_adaptive_thinking": true, @@ -65363,17 +70676,51 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512 }, + "bedrock/us-gov-east-1/anthropic.claude-fable-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.2e-05, + "cache_creation_input_token_cost_above_1hr": 1.92e-05, + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 9.6e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.8e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, "bedrock_mantle/us-gov-west-1/openai.gpt-5.6-terra": { "litellm_provider": "bedrock_mantle", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -65399,16 +70746,34 @@ "input_cost_per_token_above_272k_tokens": 5.28e-06, "cache_creation_input_token_cost": 3.3e-06, "cache_creation_input_token_cost_above_272k_tokens": 6.6e-06, + "cache_creation_input_token_cost_above_272k_tokens_flex": 3.3e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1.32e-05, + "cache_creation_input_token_cost_flex": 1.65e-06, + "cache_creation_input_token_cost_priority": 6.6e-06, "cache_read_input_token_cost": 2.64e-07, "cache_read_input_token_cost_above_272k_tokens": 5.28e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 2.64e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.056e-06, + "cache_read_input_token_cost_flex": 1.32e-07, + "cache_read_input_token_cost_priority": 5.28e-07, + "input_cost_per_token_above_272k_tokens_flex": 2.64e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.056e-05, + "input_cost_per_token_flex": 1.32e-06, + "input_cost_per_token_priority": 5.28e-06, "output_cost_per_token": 1.584e-05, - "output_cost_per_token_above_272k_tokens": 2.376e-05 + "output_cost_per_token_above_272k_tokens": 2.376e-05, + "output_cost_per_token_above_272k_tokens_flex": 1.188e-05, + "output_cost_per_token_above_272k_tokens_priority": 4.752e-05, + "output_cost_per_token_flex": 7.92e-06, + "output_cost_per_token_priority": 3.168e-05, + "search_context_cost_per_query": {"search_context_size_high":0.0144,"search_context_size_low":0.0144,"search_context_size_medium":0.0144}, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", + "supports_web_search": true }, "bedrock_mantle/us-gov-west-1/openai.gpt-5.6-luna": { "litellm_provider": "bedrock_mantle", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -65434,16 +70799,34 @@ "input_cost_per_token_above_272k_tokens": 5.28e-07, "cache_creation_input_token_cost": 3.3e-07, "cache_creation_input_token_cost_above_272k_tokens": 6.6e-07, + "cache_creation_input_token_cost_above_272k_tokens_flex": 3.3e-07, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1.32e-06, + "cache_creation_input_token_cost_flex": 1.65e-07, + "cache_creation_input_token_cost_priority": 6.6e-07, "cache_read_input_token_cost": 2.64e-08, "cache_read_input_token_cost_above_272k_tokens": 5.28e-08, + "cache_read_input_token_cost_above_272k_tokens_flex": 2.64e-08, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.056e-07, + "cache_read_input_token_cost_flex": 1.32e-08, + "cache_read_input_token_cost_priority": 5.28e-08, + "input_cost_per_token_above_272k_tokens_flex": 2.64e-07, + "input_cost_per_token_above_272k_tokens_priority": 1.056e-06, + "input_cost_per_token_flex": 1.32e-07, + "input_cost_per_token_priority": 5.28e-07, "output_cost_per_token": 1.584e-06, - "output_cost_per_token_above_272k_tokens": 2.376e-06 + "output_cost_per_token_above_272k_tokens": 2.376e-06, + "output_cost_per_token_above_272k_tokens_flex": 1.188e-06, + "output_cost_per_token_above_272k_tokens_priority": 4.752e-06, + "output_cost_per_token_flex": 7.92e-07, + "output_cost_per_token_priority": 3.168e-06, + "search_context_cost_per_query": {"search_context_size_high":0.0144,"search_context_size_low":0.0144,"search_context_size_medium":0.0144}, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", + "supports_web_search": true }, "bedrock_mantle/us-gov-west-1/openai.gpt-5.4": { "litellm_provider": "bedrock_mantle", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -65466,14 +70849,16 @@ "supports_vision": true, "input_cost_per_token": 3.3e-06, "cache_read_input_token_cost": 3.3e-07, - "output_cost_per_token": 1.98e-05 + "output_cost_per_token": 1.98e-05, + "search_context_cost_per_query": {"search_context_size_high":0.0144,"search_context_size_low":0.0144,"search_context_size_medium":0.0144}, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-54.html", + "supports_web_search": true }, "bedrock_mantle/us-gov-west-1/xai.grok-4.3": { "use_openai_responses_path": true, "litellm_provider": "bedrock_mantle", "max_input_tokens": 1048576, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", @@ -65484,21 +70869,36 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "input_cost_per_token": 1.5e-06, "output_cost_per_token": 3e-06, - "cache_read_input_token_cost": 2.4e-07 + "cache_read_input_token_cost": 2.4e-07, + "cache_read_input_token_cost_batches": 1.2e-07, + "cache_read_input_token_cost_flex": 1.2e-07, + "cache_read_input_token_cost_priority": 4.2e-07, + "input_cost_per_token_batches": 7.5e-07, + "input_cost_per_token_flex": 7.5e-07, + "input_cost_per_token_priority": 2.625e-06, + "output_cost_per_token_batches": 1.5e-06, + "output_cost_per_token_flex": 1.5e-06, + "output_cost_per_token_priority": 5.25e-06 }, "bedrock_mantle/us-gov-west-1/xai.grok-4.6": { "use_openai_responses_path": true, "input_cost_per_token": 2.64e-06, "output_cost_per_token": 7.92e-06, "cache_read_input_token_cost": 6.6e-07, + "cache_read_input_token_cost_flex": 3.3e-07, + "cache_read_input_token_cost_priority": 1.155e-06, + "input_cost_per_token_flex": 1.32e-06, + "input_cost_per_token_priority": 4.62e-06, "litellm_provider": "bedrock_mantle", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", + "output_cost_per_token_flex": 3.96e-06, + "output_cost_per_token_priority": 1.386e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -65512,12 +70912,17 @@ }, "bedrock_mantle/us-gov-west-1/google.gemma-4-e2b": { "input_cost_per_token": 4.8e-08, + "input_cost_per_token_flex": 2.4e-08, + "input_cost_per_token_priority": 8.4e-08, "output_cost_per_token": 9.6e-08, "litellm_provider": "bedrock_mantle", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", + "output_cost_per_token_batches": 4.8e-08, + "output_cost_per_token_flex": 4.8e-08, + "output_cost_per_token_priority": 1.68e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", @@ -65531,12 +70936,18 @@ }, "bedrock_mantle/us-gov-west-1/google.gemma-4-26b-a4b": { "input_cost_per_token": 1.56e-07, + "input_cost_per_token_batches": 7.8e-08, + "input_cost_per_token_flex": 7.8e-08, + "input_cost_per_token_priority": 2.73e-07, "output_cost_per_token": 4.8e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", + "output_cost_per_token_batches": 2.4e-07, + "output_cost_per_token_flex": 2.4e-07, + "output_cost_per_token_priority": 8.4e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", @@ -65550,12 +70961,18 @@ }, "bedrock_mantle/us-gov-west-1/google.gemma-4-31b": { "input_cost_per_token": 1.68e-07, + "input_cost_per_token_batches": 8.4e-08, + "input_cost_per_token_flex": 8.4e-08, + "input_cost_per_token_priority": 2.94e-07, "output_cost_per_token": 4.8e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", + "output_cost_per_token_batches": 2.4e-07, + "output_cost_per_token_flex": 2.4e-07, + "output_cost_per_token_priority": 8.4e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", @@ -65568,13 +70985,20 @@ "supports_vision": true }, "bedrock_mantle/us-gov-west-1/openai.gpt-oss-20b": { + "supports_vision": false, "input_cost_per_token": 8.4e-08, + "input_cost_per_token_batches": 4.2e-08, + "input_cost_per_token_flex": 4.2e-08, + "input_cost_per_token_priority": 1.47e-07, "output_cost_per_token": 3.6e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 16384, "mode": "chat", + "output_cost_per_token_batches": 1.8e-07, + "output_cost_per_token_flex": 1.8e-07, + "output_cost_per_token_priority": 6.3e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -65586,13 +71010,20 @@ "supports_tool_choice": true }, "bedrock_mantle/us-gov-west-1/openai.gpt-oss-120b": { + "supports_vision": false, "input_cost_per_token": 1.8e-07, + "input_cost_per_token_batches": 9e-08, + "input_cost_per_token_flex": 9e-08, + "input_cost_per_token_priority": 3.15e-07, "output_cost_per_token": 7.2e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 16384, "mode": "chat", + "output_cost_per_token_batches": 3.6e-07, + "output_cost_per_token_flex": 3.6e-07, + "output_cost_per_token_priority": 1.26e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -65613,7 +71044,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.4e-05, "prompt_cache_min_tokens": 512, @@ -65636,20 +71066,20 @@ "supports_xhigh_reasoning_effort": true, "thinking_always_on": true, "supports_forced_tool_use": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-5-5.html" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-5-5.html", + "token_count_model": {"model":"anthropic.claude-opus-5-5","litellm_provider":"bedrock_mantle","region":"us-gov-west-1"} }, "bedrock_mantle/us-gov-west-1/anthropic.claude-sonnet-5-5": { "bedrock_converse_supports_strict_tools": false, "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 3e-06, "cache_creation_input_token_cost_above_1hr": 4.8e-06, - "cache_read_input_token_cost": 2.4e-07, + "cache_read_input_token_cost": 1.2e-07, "input_cost_per_token": 2.4e-06, "litellm_provider": "bedrock_mantle", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "supports_forced_tool_use": false, @@ -65672,13 +71102,13 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-5-5.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": {"model":"anthropic.claude-sonnet-5-5","litellm_provider":"bedrock_mantle","region":"us-gov-west-1"} }, "bedrock_mantle/us-gov-east-1/openai.gpt-5.4": { "litellm_provider": "bedrock_mantle", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -65701,18 +71131,25 @@ "supports_vision": true, "input_cost_per_token": 3.3e-06, "cache_read_input_token_cost": 3.3e-07, - "output_cost_per_token": 1.98e-05 + "output_cost_per_token": 1.98e-05, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-54.md" }, "bedrock_mantle/us-gov-east-1/xai.grok-4.6": { "use_openai_responses_path": true, "input_cost_per_token": 2.64e-06, "output_cost_per_token": 7.92e-06, "cache_read_input_token_cost": 6.6e-07, + "cache_read_input_token_cost_flex": 3.3e-07, + "cache_read_input_token_cost_priority": 1.155e-06, + "input_cost_per_token_flex": 1.32e-06, + "input_cost_per_token_priority": 4.62e-06, "litellm_provider": "bedrock_mantle", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", + "output_cost_per_token_flex": 3.96e-06, + "output_cost_per_token_priority": 1.386e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -65725,13 +71162,20 @@ "supports_vision": true }, "bedrock_mantle/us-gov-east-1/openai.gpt-oss-20b": { + "supports_vision": false, "input_cost_per_token": 8.4e-08, + "input_cost_per_token_batches": 4.2e-08, + "input_cost_per_token_flex": 4.2e-08, + "input_cost_per_token_priority": 1.47e-07, "output_cost_per_token": 3.6e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 16384, "mode": "chat", + "output_cost_per_token_batches": 1.8e-07, + "output_cost_per_token_flex": 1.8e-07, + "output_cost_per_token_priority": 6.3e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -65743,13 +71187,20 @@ "supports_tool_choice": true }, "bedrock_mantle/us-gov-east-1/openai.gpt-oss-120b": { + "supports_vision": false, "input_cost_per_token": 1.8e-07, + "input_cost_per_token_batches": 9e-08, + "input_cost_per_token_flex": 9e-08, + "input_cost_per_token_priority": 3.15e-07, "output_cost_per_token": 7.2e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 16384, "mode": "chat", + "output_cost_per_token_batches": 3.6e-07, + "output_cost_per_token_flex": 3.6e-07, + "output_cost_per_token_priority": 1.26e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -65761,91 +71212,129 @@ "supports_tool_choice": true }, "bedrock_mantle/deepseek.v3.1": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 5.8e-07, + "input_cost_per_token_batches": 2.9e-07, + "input_cost_per_token_flex": 2.9e-07, + "input_cost_per_token_priority": 1.015e-06, "output_cost_per_token": 1.68e-06, + "output_cost_per_token_flex": 8.4e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", + "output_cost_per_token_batches": 8.4e-07, + "output_cost_per_token_priority": 2.94e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-1.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/moonshotai.kimi-k2-thinking": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 6e-07, + "input_cost_per_token_batches": 3e-07, + "input_cost_per_token_flex": 3e-07, + "input_cost_per_token_priority": 1.05e-06, "output_cost_per_token": 2.5e-06, + "output_cost_per_token_flex": 1.25e-06, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_priority": 4.38e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/qwen.qwen3-235b-a22b-2507": { "input_cost_per_token": 2.2e-07, + "input_cost_per_token_batches": 1.1e-07, + "input_cost_per_token_flex": 1.1e-07, + "input_cost_per_token_priority": 3.85e-07, "output_cost_per_token": 8.8e-07, + "output_cost_per_token_flex": 4.4e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", + "output_cost_per_token_batches": 4.4e-07, + "output_cost_per_token_priority": 1.54e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-235b-a22b-2507.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/qwen.qwen3-32b": { "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "input_cost_per_token_flex": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, "output_cost_per_token": 6e-07, + "output_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 32000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_priority": 1.05e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-32b.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/qwen.qwen3-coder-30b-a3b-instruct": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "input_cost_per_token_flex": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, "output_cost_per_token": 6e-07, + "output_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_priority": 1.05e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-30b-a3b-instruct.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/qwen.qwen3-coder-480b-a35b-instruct": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-480b-a35b-instruct.html", "input_cost_per_token": 4.5e-07, + "input_cost_per_token_batches": 2.25e-07, + "input_cost_per_token_flex": 2.25e-07, + "input_cost_per_token_priority": 7.875e-07, "output_cost_per_token": 1.8e-06, + "output_cost_per_token_flex": 9e-07, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 128000, + "max_input_tokens": 262144, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", + "output_cost_per_token_batches": 9e-07, + "output_cost_per_token_priority": 3.15e-06, "supported_endpoints": [ "/v1/chat/completions" ], @@ -65855,35 +71344,45 @@ }, "bedrock_mantle/qwen.qwen3-next-80b-a3b-instruct": { "input_cost_per_token": 1.4e-07, + "input_cost_per_token_batches": 7e-08, + "input_cost_per_token_flex": 7e-08, + "input_cost_per_token_priority": 2.6e-07, "output_cost_per_token": 1.2e-06, + "output_cost_per_token_flex": 6e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", + "output_cost_per_token_batches": 6e-07, + "output_cost_per_token_priority": 2.1e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/qwen.qwen3-vl-235b-a22b-instruct": { "input_cost_per_token": 5.3e-07, + "input_cost_per_token_batches": 2.6e-07, + "input_cost_per_token_flex": 2.6e-07, + "input_cost_per_token_priority": 9.3e-07, "output_cost_per_token": 2.66e-06, + "output_cost_per_token_flex": 1.33e-06, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", + "output_cost_per_token_batches": 1.33e-06, + "output_cost_per_token_priority": 4.66e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-vl-235b-a22b.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "azure/us-gov/gpt-5.1": { "cache_read_input_token_cost": 1.71875e-07, @@ -65892,7 +71391,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.375e-05, "supported_endpoints": [ @@ -65926,7 +71424,6 @@ "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6.05e-06, "supports_prompt_caching": true, @@ -65939,7 +71436,6 @@ "input_cost_per_token": 1.63e-07, "litellm_provider": "azure", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -65947,7 +71443,6 @@ "input_cost_per_token": 2.5e-08, "litellm_provider": "azure", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -65978,7 +71473,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_image": 0.04, "output_cost_per_token": 0, @@ -66003,7 +71497,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -66026,9 +71519,8 @@ "gemini/lyria-3.5": { "input_cost_per_token": 0, "litellm_provider": "gemini", - "max_input_tokens": 1048576, + "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -66053,7 +71545,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0, "source": "https://ai.google.dev/gemini-api/docs/models/lyria-realtime-exp", @@ -66134,12 +71625,12 @@ "mode": "responses", "supports_web_search": true, "supports_function_calling": true, - "input_cost_per_token": 5e-06, - "output_cost_per_token": 3e-05, - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token_above_272k_tokens": 1e-05, - "output_cost_per_token_above_272k_tokens": 4.5e-05, - "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "input_cost_per_token": 4e-06, + "output_cost_per_token": 2e-05, + "cache_read_input_token_cost": 4e-07, + "input_cost_per_token_above_272k_tokens": 8e-06, + "output_cost_per_token_above_272k_tokens": 3e-05, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/openai/gpt-5.6-terra": { @@ -66178,6 +71669,7 @@ "cache_read_input_token_cost": 5e-07, "input_cost_per_token_above_272k_tokens": 1e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/openai/gpt-5.4": { @@ -66222,6 +71714,22 @@ "cache_read_input_token_cost": 1.25e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, + "perplexity/openai/gpt-5-nano": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 5e-08, + "output_cost_per_token": 4e-07, + "cache_read_input_token_cost": 5e-09, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-5.3-codex": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 3.5e-06, + "output_cost_per_token": 2.8e-05, + "cache_read_input_token_cost": 3.5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, "perplexity/google/gemini-3.1-pro-preview": { "litellm_provider": "perplexity", "mode": "responses", @@ -66258,6 +71766,7 @@ "perplexity/google/gemini-3.5-flash-lite": { "litellm_provider": "perplexity", "mode": "responses", + "supports_sampling_params": false, "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 3e-07, @@ -66265,9 +71774,18 @@ "cache_read_input_token_cost": 3e-08, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, + "perplexity/google/gemini-4-argon": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, "perplexity/google/gemini-3.6-flash": { "litellm_provider": "perplexity", "mode": "responses", + "supports_sampling_params": false, "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 1.5e-06, @@ -66278,6 +71796,7 @@ "perplexity/google/gemini-3.7-flash": { "litellm_provider": "perplexity", "mode": "responses", + "supports_sampling_params": false, "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 7.5e-07, @@ -66390,6 +71909,14 @@ "cache_read_input_token_cost": 1.15e-09, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, + "perplexity/perplexity/nemotron-3.5-super-120b-a12b": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 2e-07, + "output_cost_per_token": 5e-07, + "cache_read_input_token_cost": 4e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, "perplexity/perplexity/nemotron-3-ultra-550b-a55b": { "litellm_provider": "perplexity", "mode": "responses", @@ -66401,12930 +71928,28904 @@ "cache_read_input_token_cost": 2.5e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, - "openrouter/anthropic/claude-fable-5": { - "input_cost_per_token": 1e-05, - "output_cost_per_token": 5e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "baseten/zai-org/GLM-5.3": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, "mode": "chat", - "supports_sampling_params": false, - "supports_adaptive_thinking": true, - "thinking_always_on": true, - "source": "https://openrouter.ai/api/v1/models", + "output_cost_per_token": 4.4e-06, + "source": "https://inference.baseten.co/v1/models", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 1e-06, "supports_prompt_caching": true, - "cache_creation_input_token_cost": 1.25e-05, - "cache_creation_input_token_cost_above_1hr": 2e-05, - "prompt_cache_min_tokens": 512, - "supports_web_search": true - }, - "openrouter/anthropic/claude-fable-5.1": { - "input_cost_per_token": 1e-05, - "output_cost_per_token": 5e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "supports_sampling_params": false, - "supports_adaptive_thinking": true, - "thinking_always_on": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2.5e-07, - "supports_prompt_caching": true, - "cache_creation_input_token_cost": 1.25e-05, - "cache_creation_input_token_cost_above_1hr": 2e-05, - "prompt_cache_min_tokens": 512, - "supports_web_search": true - }, - "openrouter/anthropic/claude-opus-4.8": { - "input_cost_per_token": 5e-06, - "output_cost_per_token": 2.5e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "supports_sampling_params": false, - "supports_adaptive_thinking": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 5e-07, - "supports_prompt_caching": true, - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "supports_web_search": true + "supports_vision": true }, - "openrouter/anthropic/claude-sonnet-5": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "supports_sampling_params": false, - "supports_adaptive_thinking": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-07, - "supports_prompt_caching": true, - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_1hr": 4e-06, - "supports_web_search": true + "baseten/glm-latest": { + "alias_of": "baseten/zai-org/GLM-5.3" }, - "openrouter/google/gemini-2.5-flash-lite": { - "cache_creation_input_token_cost": 8.33333333333333e-08, - "cache_read_input_audio_token_cost": 3e-08, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "openrouter", + "baseten/zai-org/GLM-5.3-Fast": { + "cache_read_input_token_cost": 2.1e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "baseten", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 262144, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", + "output_cost_per_token": 6.6e-06, + "source": "https://inference.baseten.co/v1/models", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, - "supports_tool_choice": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "cache_read_input_token_cost": 1e-08, - "deprecation_date": "2026-10-20", - "input_cost_per_audio_token": 3e-07, - "supports_prompt_caching": true, - "supports_web_search": true, - "supports_video_input": true + "supports_tool_choice": true, + "supports_vision": true }, - "openrouter/google/gemini-3.5-flash": { - "cache_creation_input_token_cost": 8.33333333333333e-08, - "cache_read_input_audio_token_cost": 3e-07, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 9e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "together_ai/arcee-ai/trinity-mini": { + "input_cost_per_token": 4.5e-08, + "litellm_provider": "together_ai", "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "cache_read_input_token_cost": 1.5e-07, + "output_cost_per_token": 1.5e-07, + "source": "https://api.together.ai/v1/models", + "max_input_tokens": 128000, + "max_output_tokens": 128000 + }, + "vertex_ai/gemini-2.5-flash-native-audio": { + "deprecation_date": "2026-12-13", "input_cost_per_audio_token": 3e-06, - "supports_prompt_caching": true, - "supports_web_search": true, - "supports_video_input": true + "input_cost_per_image_token": 3e-06, + "input_cost_per_token": 5e-07, + "input_cost_per_video_token": 3e-06, + "litellm_provider": "vertex_ai", + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 2e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, - "openrouter/google/gemini-3.5-flash-lite": { - "cache_creation_input_token_cost": 8.33333333333333e-08, - "cache_read_input_audio_token_cost": 3e-08, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "cache_read_input_token_cost": 3e-08, - "input_cost_per_audio_token": 3e-07, - "supports_prompt_caching": true, - "supports_web_search": true, - "supports_video_input": true + "vertex_ai/gemini-2.5-flash-preview-tts": { + "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "litellm_provider": "vertex_ai", + "mode": "audio_speech", + "output_cost_per_audio_token": 1e-05, + "output_cost_per_token": 1e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, - "openrouter/google/gemini-3.6-flash": { - "cache_creation_input_token_cost": 4.16666666666667e-08, - "cache_read_input_audio_token_cost": 7.5e-08, - "input_cost_per_token": 7.5e-07, - "output_cost_per_token": 3.75e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_audio_token": 7.5e-07, - "supports_prompt_caching": true, - "supports_web_search": true, - "supports_video_input": true + "vertex_ai/gemini-3.1-flash-tts-preview": { + "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, + "litellm_provider": "vertex_ai", + "mode": "audio_speech", + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 2e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, - "openrouter/google/gemini-3.7-flash": { - "cache_creation_input_token_cost": 4.16666666666667e-08, - "cache_read_input_audio_token_cost": 7.5e-08, - "input_cost_per_token": 7.5e-07, - "output_cost_per_token": 3.75e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "vertex_ai/gemini-3.5-transcribe": { + "input_cost_per_audio_token": 2e-06, + "input_cost_per_second": 5e-05, + "litellm_provider": "vertex_ai", + "mode": "audio_transcription", + "output_cost_per_token": 1.2e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/gemini-3.5-transcribe-live": { + "input_cost_per_audio_token": 3.5e-06, + "input_cost_per_second": 8.75e-05, + "litellm_provider": "vertex_ai", + "mode": "audio_transcription", + "output_cost_per_token": 2.1e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/gemini-omni-1.1-flash": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "vertex_ai", "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_audio_token": 7.5e-07, - "supports_prompt_caching": true, - "supports_web_search": true, - "supports_video_input": true + "output_cost_per_reasoning_token": 9e-06, + "output_cost_per_token": 9e-06, + "output_cost_per_video_token": 1.75e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "successor_model": "vertex_ai/gemini-omni-1.2-flash" }, - "openrouter/google/gemini-3.8-flash": { - "cache_creation_input_token_cost": 4.16666666666667e-08, - "cache_read_input_audio_token_cost": 7.5e-08, - "input_cost_per_token": 7.5e-07, - "output_cost_per_token": 3.75e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "vertex_ai/gemini-omni-1.1-flash-preview": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "vertex_ai", + "max_input_tokens": 131072, + "max_output_tokens": 57920, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, + "output_cost_per_reasoning_token": 9e-06, + "output_cost_per_token": 9e-06, + "output_cost_per_video_token": 1.75e-05, + "source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/omni-1-1-flash", + "successor_model": "vertex_ai/gemini-omni-1.2-flash", + "supported_endpoints": [ + "/v1beta/interactions" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text", + "video" + ], "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_audio_token": 7.5e-07, - "supports_prompt_caching": true, - "supports_web_search": true, - "supports_video_input": true + "supports_video_input": true, + "supports_vision": true }, - "openrouter/openai/gpt-4o-mini": { + "vertex_ai/gemma-4-26b-a4b-it": { + "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "litellm_provider": "vertex_ai", "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 7.5e-08, - "supports_prompt_caching": true, - "supports_web_search": true + "output_cost_per_token": 6e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, - "openrouter/openai/gpt-5.1": { - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "gpt-5.5-cyber": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 1.25e-05, + "litellm_provider": "openai", "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 1.25e-07, - "supports_prompt_caching": true, - "supports_web_search": true + "output_cost_per_token": 7.5e-05, + "fedramp_uplift_multiplier": 1.1, + "source": "https://developers.openai.com/api/docs/pricing", + "supports_reasoning": true }, - "openrouter/openai/gpt-5.3-codex": { - "input_cost_per_token": 1.75e-06, - "output_cost_per_token": 1.4e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "gpt-5.5-cyber-preview": { + "cache_read_input_token_cost": 1.25e-06, + "deprecation_date": "2027-02-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "input_cost_per_token": 1.25e-05, + "litellm_provider": "openai", "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 1.75e-07, - "supports_prompt_caching": true, - "supports_web_search": true + "output_cost_per_token": 7.5e-05, + "fedramp_uplift_multiplier": 1.1, + "source": "https://developers.openai.com/api/docs/pricing", + "supports_reasoning": true }, - "openrouter/openai/gpt-5.4": { - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "gpt-rosalind-research": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 5e-07, - "input_cost_per_token_above_272k_tokens": 5e-06, - "output_cost_per_token_above_272k_tokens": 2.25e-05, - "supports_prompt_caching": true, - "supports_web_search": true + "output_cost_per_token": 2.5e-05, + "source": "https://developers.openai.com/api/docs/pricing" }, - "openrouter/openai/gpt-5.4-mini": { - "input_cost_per_token": 7.5e-07, - "output_cost_per_token": 4.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "together_ai/meta-llama/Llama-3.1-405B-Instruct": { + "input_cost_per_token": 3.5e-06, + "litellm_provider": "together_ai", "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 7.5e-08, - "supports_prompt_caching": true, - "supports_web_search": true + "output_cost_per_token": 3.5e-06, + "source": "https://api.together.ai/v1/models", + "max_input_tokens": 4096, + "max_output_tokens": 4096 }, - "openrouter/openai/gpt-5.4-nano": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "together_ai/meta-llama/Llama-3.2-1B-Instruct": { + "input_cost_per_token": 6e-08, + "litellm_provider": "together_ai", "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-08, - "supports_prompt_caching": true, - "supports_web_search": true + "output_cost_per_token": 6e-08, + "source": "https://api.together.ai/v1/models", + "max_input_tokens": 131072, + "max_output_tokens": 131072 }, - "openrouter/openai/gpt-5.5": { - "input_cost_per_token": 5e-06, - "output_cost_per_token": 3e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "together_ai/meta-llama/Llama-3.2-3B-Instruct": { + "input_cost_per_token": 6e-08, + "litellm_provider": "together_ai", "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "input_cost_per_token_above_272k_tokens": 1e-05, - "output_cost_per_token_above_272k_tokens": 4.5e-05, - "supports_prompt_caching": true, - "supports_web_search": true + "output_cost_per_token": 6e-08, + "source": "https://api.together.ai/v1/models", + "max_input_tokens": 131072, + "max_output_tokens": 131072 }, - "openrouter/openai/gpt-5.6-luna": { - "cache_creation_input_token_cost": 2.5e-07, - "cache_creation_input_token_cost_above_272k_tokens": 5e-07, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "together_ai/Qwen/Qwen2-1.5B-Instruct": { + "input_cost_per_token": 2e-08, + "litellm_provider": "together_ai", "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-08, - "cache_read_input_token_cost_above_272k_tokens": 4e-08, - "input_cost_per_token_above_272k_tokens": 4e-07, - "output_cost_per_token_above_272k_tokens": 1.8e-06, - "supports_prompt_caching": true, - "supports_web_search": true + "output_cost_per_token": 2e-08, + "source": "https://api.together.ai/v1/models", + "max_input_tokens": 32768, + "max_output_tokens": 32768 }, - "openrouter/openai/gpt-5.6-luna-pro": { - "input_cost_per_token": 2e-07, + "together_ai/Qwen/Qwen2.5-14B-Instruct": { + "input_cost_per_token": 8e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 8e-07, + "source": "https://api.together.ai/v1/models", + "max_input_tokens": 32768, + "max_output_tokens": 32768 + }, + "together_ai/Qwen/Qwen2.5-72B-Instruct": { + "input_cost_per_token": 1.2e-06, + "litellm_provider": "together_ai", + "mode": "chat", "output_cost_per_token": 1.2e-06, - "cache_read_input_token_cost": 2e-08, - "cache_creation_input_token_cost": 2.5e-07, - "cache_creation_input_token_cost_above_272k_tokens": 5e-07, - "input_cost_per_token_above_272k_tokens": 4e-07, - "output_cost_per_token_above_272k_tokens": 1.8e-06, - "cache_read_input_token_cost_above_272k_tokens": 4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "source": "https://api.together.ai/v1/models", + "max_input_tokens": 32768, + "max_output_tokens": 32768 + }, + "together_ai/Salesforce/Llama-Rank-V1": { + "deprecation_date": "2026-02-06", + "deprecation_source": "https://docs.together.ai/docs/deprecations", + "input_cost_per_token": 1e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 8192, + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/meta-llama/Meta-Llama-3.1-8B": { + "input_cost_per_token": 2e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "mode": "completion", + "output_cost_per_token": 2e-07, + "source": "https://api.together.xyz/v1/models" + }, + "together_ai/together/Tev1-4B-experimental": { + "input_cost_per_token": 4.2e-08, + "litellm_provider": "together_ai", + "max_input_tokens": 32768, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_web_search": true + "output_cost_per_token": 0.0, + "source": "https://api.together.ai/v1/models" }, - "openrouter/openai/gpt-5.6-terra": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1.2e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo": { + "deprecation_date": "2026-02-06", + "deprecation_source": "https://docs.together.ai/docs/deprecations", + "input_cost_per_token": 1.2e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_272k_tokens": 4e-07, - "input_cost_per_token_above_272k_tokens": 4e-06, - "output_cost_per_token_above_272k_tokens": 1.8e-05, - "supports_prompt_caching": true, - "supports_web_search": true + "output_cost_per_token": 1.2e-06, + "source": "https://api.together.ai/v1/models" }, - "openrouter/openai/gpt-5.6-terra-pro": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1.2e-05, - "cache_read_input_token_cost": 2e-07, - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "output_cost_per_token_above_272k_tokens": 1.8e-05, - "cache_read_input_token_cost_above_272k_tokens": 4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "together_ai/Qwen/Qwen2.5-VL-72B-Instruct": { + "deprecation_date": "2026-01-05", + "deprecation_source": "https://docs.together.ai/docs/deprecations", + "input_cost_per_token": 1.95e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_web_search": true + "output_cost_per_token": 8e-06, + "source": "https://api.together.ai/v1/models" }, - "openrouter/openai/o3": { + "together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { + "deprecation_date": "2026-06-04", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 5e-07, - "supports_prompt_caching": true, - "supports_web_search": true + "output_cost_per_token": 2e-06, + "source": "https://api.together.ai/v1/models" }, - "openrouter/openai/o4-mini": { - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "together_ai/Qwen/Qwen3-Coder-Next-FP8": { + "deprecation_date": "2026-05-14", + "deprecation_source": "https://docs.together.ai/docs/deprecations", + "input_cost_per_token": 5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2.75e-07, - "supports_prompt_caching": true, - "supports_web_search": true + "output_cost_per_token": 1.2e-06, + "source": "https://api.together.ai/v1/models" }, - "openrouter/x-ai/grok-4.20": { - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 2000000, - "max_output_tokens": 1800000, - "max_tokens": 1800000, + "together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct": { + "deprecation_date": "2026-04-02", + "deprecation_source": "https://docs.together.ai/docs/deprecations", + "input_cost_per_token": 1.5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "supports_prompt_caching": true, - "supports_web_search": true + "output_cost_per_token": 1.5e-06, + "source": "https://api.together.ai/v1/models" }, - "openrouter/x-ai/grok-4.20-multi-agent": { - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 2000000, - "max_output_tokens": 1800000, - "max_tokens": 1800000, + "together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking": { + "deprecation_date": "2026-02-25", + "deprecation_source": "https://docs.together.ai/docs/deprecations", + "input_cost_per_token": 1.5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": false, - "supports_tool_choice": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "supports_prompt_caching": true, - "supports_web_search": true + "output_cost_per_token": 1.5e-06, + "source": "https://api.together.ai/v1/models" }, - "openrouter/x-ai/grok-4.3": { - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 900000, - "max_tokens": 900000, + "together_ai/Qwen/Qwen3-VL-32B-Instruct": { + "deprecation_date": "2026-02-25", + "deprecation_source": "https://docs.together.ai/docs/deprecations", + "input_cost_per_token": 5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "supports_prompt_caching": true, - "supports_web_search": true + "output_cost_per_token": 1.5e-06, + "source": "https://api.together.ai/v1/models" }, - "openrouter/x-ai/grok-4.5": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 500000, - "max_output_tokens": 450000, - "max_tokens": 450000, + "together_ai/Qwen/Qwen3-VL-8B-Instruct": { + "deprecation_date": "2026-04-16", + "deprecation_source": "https://docs.together.ai/docs/deprecations", + "input_cost_per_token": 1.8e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 3e-07, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "input_cost_per_token_above_200k_tokens": 4e-06, - "output_cost_per_token_above_200k_tokens": 1.2e-05, - "supports_prompt_caching": true, - "supports_web_search": true + "output_cost_per_token": 6.8e-07, + "source": "https://api.together.ai/v1/models" }, - "openrouter/x-ai/grok-4.6": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 500000, - "max_output_tokens": 450000, - "max_tokens": 450000, + "together_ai/Qwen/Qwen3.5-397B-A17B": { + "cache_read_input_token_cost": 3.5e-07, + "deprecation_date": "2026-06-29", + "deprecation_source": "https://docs.together.ai/docs/deprecations", + "input_cost_per_token": 6e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_200k_tokens": 1e-06, - "input_cost_per_token_above_200k_tokens": 4e-06, - "output_cost_per_token_above_200k_tokens": 1.2e-05, - "supports_prompt_caching": true, - "supports_web_search": true + "output_cost_per_token": 3.6e-06, + "source": "https://api.together.ai/v1/models" }, - "openrouter/x-ai/grok-build-0.1": { - "input_cost_per_token": 1e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 256000, - "max_output_tokens": 230400, - "max_tokens": 230400, + "together_ai/deepseek-ai/DeepSeek-V3.1": { + "deprecation_date": "2026-05-14", + "deprecation_source": "https://docs.together.ai/docs/deprecations", + "input_cost_per_token": 6e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_token_above_200k_tokens": 2e-06, - "output_cost_per_token_above_200k_tokens": 4e-06, - "supports_prompt_caching": true, - "supports_web_search": true + "output_cost_per_token": 1.7e-06, + "source": "https://api.together.ai/v1/models" }, - "baseten/zai-org/GLM-5.3": { - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 1.4e-06, - "litellm_provider": "baseten", - "max_input_tokens": 1048576, - "max_output_tokens": 262144, - "max_tokens": 262144, + "together_ai/essentialai/rnj-1-instruct": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "together_ai", "mode": "chat", - "output_cost_per_token": 4.4e-06, - "source": "https://inference.baseten.co/v1/models", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 1.5e-07, + "source": "https://www.together.ai/models/rnj-1-instruct" }, - "baseten/zai-org/GLM-5.3-Fast": { - "cache_read_input_token_cost": 2.1e-07, - "input_cost_per_token": 2.1e-06, - "litellm_provider": "baseten", - "max_input_tokens": 1048576, + "together_ai/google/gemma-4-31B-it": { + "deprecation_date": "2026-09-15", + "deprecation_source": "https://docs.together.ai/docs/deprecations", + "input_cost_per_token": 3.9e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 6.6e-06, - "source": "https://inference.baseten.co/v1/models", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 9.7e-07, + "source": "https://api.together.ai/v1/models", + "successor_model": "together_ai/zai-org/GLM-5.3-Flash" }, - "openrouter/minimax/minimax-m3": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "openrouter", + "together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct": { + "deprecation_date": "2026-02-06", + "deprecation_source": "https://docs.together.ai/docs/deprecations", + "input_cost_per_token": 1.8e-07, + "litellm_provider": "together_ai", "max_input_tokens": 1048576, - "max_output_tokens": 512000, - "max_tokens": 512000, + "max_output_tokens": 1048576, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "cache_read_input_token_cost": 6e-08, - "supports_audio_input": false, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_web_search": false + "output_cost_per_token": 5.9e-07, + "source": "https://api.together.ai/v1/models" }, - "openrouter/qwen/qwen3.7-plus": { - "input_cost_per_token": 3.2e-07, - "input_cost_per_token_above_256k_tokens": 9.6e-07, - "cache_creation_input_token_cost_above_256k_tokens": 1.2e-06, - "cache_read_input_token_cost_above_256k_tokens": 1.92e-07, - "output_cost_per_token_above_256k_tokens": 3.84e-06, - "output_cost_per_token": 1.28e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, + "together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { + "deprecation_date": "2026-02-25", + "deprecation_source": "https://docs.together.ai/docs/deprecations", + "input_cost_per_token": 8.8e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "cache_read_input_token_cost": 6.4e-08, - "supports_prompt_caching": true, - "cache_creation_input_token_cost": 4e-07, - "supports_audio_input": false, - "supports_pdf_input": false, - "supports_web_search": false + "output_cost_per_token": 8.8e-07, + "source": "https://api.together.ai/v1/models" }, - "openrouter/openai/gpt-6-astra": { - "input_cost_per_token": 1e-05, - "output_cost_per_token": 5e-05, - "cache_read_input_token_cost": 1e-06, - "cache_creation_input_token_cost": 1.25e-05, - "input_cost_per_token_above_272k_tokens": 2e-05, - "output_cost_per_token_above_272k_tokens": 7.5e-05, - "cache_read_input_token_cost_above_272k_tokens": 2e-06, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { + "deprecation_date": "2026-03-06", + "deprecation_source": "https://docs.together.ai/docs/deprecations", + "input_cost_per_token": 1.8e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_web_search": true + "output_cost_per_token": 1.8e-07, + "source": "https://api.together.ai/v1/models" }, - "openrouter/openai/gpt-6-astra-pro": { - "input_cost_per_token": 1e-05, - "output_cost_per_token": 5e-05, - "cache_read_input_token_cost": 1e-06, - "cache_creation_input_token_cost": 1.25e-05, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, - "input_cost_per_token_above_272k_tokens": 2e-05, - "output_cost_per_token_above_272k_tokens": 7.5e-05, - "cache_read_input_token_cost_above_272k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "together_ai/mistralai/Mistral-Small-24B-Instruct-2501": { + "deprecation_date": "2026-04-02", + "deprecation_source": "https://docs.together.ai/docs/deprecations", + "input_cost_per_token": 1e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_web_search": true + "output_cost_per_token": 3e-07, + "source": "https://api.together.ai/v1/models" }, - "openrouter/qwen/qwen3.8-flash": { - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 4.7e-07, - "cache_read_input_token_cost": 1.6e-08, - "cache_creation_input_token_cost": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, + "together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1": { + "deprecation_date": "2026-04-16", + "deprecation_source": "https://docs.together.ai/docs/deprecations", + "input_cost_per_token": 6e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false + "output_cost_per_token": 6e-07, + "source": "https://api.together.ai/v1/models" }, - "openrouter/z-ai/glm-5.3-flash": { - "cache_read_input_token_cost": 3e-08, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1310720, - "max_output_tokens": 131072, - "max_tokens": 131072, + "together_ai/moonshotai/Kimi-K2.6": { + "cache_read_input_token_cost": 2e-07, + "deprecation_date": "2026-08-19", + "deprecation_source": "https://docs.together.ai/docs/deprecations", + "input_cost_per_token": 1.2e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", - "output_cost_per_token": 5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "output_cost_per_token": 4.5e-06, + "source": "https://api.together.ai/v1/models" }, - "openrouter/deepseek/deepseek-v4-flash-vision-exp": { - "input_cost_per_token": 2.156e-07, - "output_cost_per_token": 6.468e-07, - "cache_read_input_token_cost": 6.86e-09, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, + "together_ai/moonshotai/Kimi-K2.7-Code": { + "cache_read_input_token_cost": 1.9e-07, + "deprecation_date": "2026-08-27", + "deprecation_source": "https://docs.together.ai/docs/deprecations", + "input_cost_per_token": 9.5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false + "output_cost_per_token": 4e-06, + "source": "https://api.together.ai/v1/models" }, - "openrouter/z-ai/glm-5.3": { - "input_cost_per_token": 1.4e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 2.6e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1310720, - "max_output_tokens": 943717, - "max_tokens": 943717, + "together_ai/nvidia/nemotron-3-ultra-550b-a55b": { + "cache_read_input_token_cost": 2e-07, + "deprecation_date": "2026-08-27", + "deprecation_source": "https://docs.together.ai/docs/deprecations", + "input_cost_per_token": 6e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 512288, + "max_output_tokens": 512288, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": false, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false + "output_cost_per_token": 3.6e-06, + "source": "https://api.together.ai/v1/models" }, - "openrouter/qwen/qwen3.8-27b": { - "input_cost_per_token": 4.2e-07, - "output_cost_per_token": 3e-06, - "cache_read_input_token_cost": 8.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, + "together_ai/openai/gpt-oss-20b": { + "deprecation_date": "2026-09-15", + "deprecation_source": "https://docs.together.ai/docs/deprecations", + "input_cost_per_token": 5e-08, + "litellm_provider": "together_ai", + "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false + "output_cost_per_token": 2e-07, + "source": "https://api.together.ai/v1/models", + "successor_model": "together_ai/Qwen/Qwen3.5-9B" }, - "openrouter/qwen/qwen3.8-2.4t-a95b": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "cache_read_input_token_cost": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, + "together_ai/zai-org/GLM-4.5-Air-FP8": { + "deprecation_date": "2026-04-02", + "deprecation_source": "https://docs.together.ai/docs/deprecations", + "input_cost_per_token": 2e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false + "output_cost_per_token": 1.1e-06, + "source": "https://api.together.ai/v1/models" }, - "openrouter/nvidia/nemotron-3.5-lightning:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "together_ai/zai-org/GLM-4.7": { + "deprecation_date": "2026-04-02", + "deprecation_source": "https://docs.together.ai/docs/deprecations", + "input_cost_per_token": 4.5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 202752, + "max_output_tokens": 202752, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_vision": false, - "supports_web_search": false + "output_cost_per_token": 2e-06, + "source": "https://api.together.ai/v1/models" }, - "openrouter/qwen/qwen3.8-max": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "cache_read_input_token_cost": 2.5e-07, - "cache_creation_input_token_cost": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, + "together_ai/zai-org/GLM-5": { + "deprecation_date": "2026-06-22", + "deprecation_source": "https://docs.together.ai/docs/deprecations", + "input_cost_per_token": 1e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 202752, + "max_output_tokens": 202752, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3.8-max", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true + "output_cost_per_token": 3.2e-06, + "source": "https://api.together.ai/v1/models" }, - "openrouter/qwen/qwen3.8-max-0902": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "cache_read_input_token_cost": 2.5e-07, - "cache_creation_input_token_cost": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, + "together_ai/zai-org/GLM-5.1": { + "cache_read_input_token_cost": 2.6e-07, + "deprecation_date": "2026-07-10", + "deprecation_source": "https://docs.together.ai/docs/deprecations", + "input_cost_per_token": 1.4e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 202752, + "max_output_tokens": 202752, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_web_search": false + "output_cost_per_token": 4.4e-06, + "source": "https://api.together.ai/v1/models" }, - "openrouter/qwen/qwen3.8-max-prime": { - "input_cost_per_token": 4e-06, - "output_cost_per_token": 1.2e-05, - "cache_read_input_token_cost": 5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_video_input": true, - "supports_prompt_caching": true + "azure/eu/codex-mini": { + "deprecation_date": "2026-11-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "cache_read_input_token_cost": 4.13e-07, + "input_cost_per_token": 1.65e-06, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 6.6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/deepseek/deepseek-v4-flash-0731": { - "cache_read_input_token_cost": 1.6e-08, - "input_cost_per_token": 1.8e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 1310720, - "max_output_tokens": 943718, - "max_tokens": 943718, + "azure/eu/computer-use-preview": { + "input_cost_per_token": 3.3e-06, + "litellm_provider": "azure", "mode": "chat", - "output_cost_per_token": 3.2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "output_cost_per_token": 1.32e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/qwen/qwen3.7-flash": { - "input_cost_per_token": 3e-08, - "input_cost_per_token_above_32k_tokens": 1e-07, - "cache_creation_input_token_cost_above_32k_tokens": 1.25e-07, - "cache_read_input_token_cost_above_32k_tokens": 2e-08, - "output_cost_per_token_above_32k_tokens": 4e-07, - "output_cost_per_token": 1.3e-07, - "cache_read_input_token_cost": 6e-09, - "cache_creation_input_token_cost": 3.8e-08, - "input_cost_per_token_above_256k_tokens": 2e-07, - "output_cost_per_token_above_256k_tokens": 8e-07, - "cache_read_input_token_cost_above_256k_tokens": 4e-08, - "cache_creation_input_token_cost_above_256k_tokens": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "azure/eu/gpt-4.1": { + "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.1", + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_priority": 9.63e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false + "output_cost_per_token": 8.8e-06, + "output_cost_per_token_batches": 4.4e-06, + "output_cost_per_token_priority": 1.54e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/poolside/laguna-s-2.1": { - "input_cost_per_token": 9e-08, - "output_cost_per_token": 1.8e-07, - "cache_read_input_token_cost": 9e-09, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, + "azure/eu/gpt-4.1-mini": { + "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.4-mini", + "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_priority": 1.93e-07, + "input_cost_per_token": 4.4e-07, + "input_cost_per_token_batches": 2.2e-07, + "input_cost_per_token_priority": 7.7e-07, + "litellm_provider": "azure", "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_response_schema": false, - "supports_web_search": false + "output_cost_per_token": 1.76e-06, + "output_cost_per_token_batches": 8.8e-07, + "output_cost_per_token_priority": 3.08e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/poolside/laguna-s-2.1:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, + "azure/eu/gpt-4.1-nano": { + "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.4-nano", + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 1.1e-07, + "input_cost_per_token_batches": 5.5e-08, + "litellm_provider": "azure", "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_vision": false, - "supports_web_search": false + "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/moonshotai/kimi-k3": { - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, + "azure/eu/gpt-4o-2024-05-13": { + "deprecation_date": "2027-01-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.1", + "input_cost_per_token": 5.5e-06, + "input_cost_per_token_batches": 2.75e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false + "output_cost_per_token": 1.65e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/poolside/laguna-xs-2.1": { - "input_cost_per_token": 6e-08, - "output_cost_per_token": 1.2e-07, - "cache_read_input_token_cost": 3e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, + "azure/eu/gpt-5": { + "deprecation_date": "2027-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.1", + "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_batches": 6.875e-08, + "cache_read_input_token_cost_priority": 2.75e-07, + "input_cost_per_token": 1.375e-06, + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.75e-06, + "litellm_provider": "azure", "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_response_schema": false, - "supports_web_search": false + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 2.2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/poolside/laguna-xs-2.1:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_vision": false, - "supports_web_search": false + "azure/eu/gpt-5-codex": { + "deprecation_date": "2027-03-17", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.1-codex", + "cache_read_input_token_cost": 1.38e-07, + "input_cost_per_token": 1.375e-06, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/google/gemini-3.1-flash-lite-image": { - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 1.5e-06, - "output_cost_per_image_token": 3e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 58982, - "max_tokens": 58982, + "azure/eu/gpt-5-mini": { + "deprecation_date": "2027-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.4-mini", + "cache_read_input_token_cost": 2.75e-08, + "cache_read_input_token_cost_batches": 1.375e-08, + "cache_read_input_token_cost_priority": 4.95e-08, + "input_cost_per_token": 2.75e-07, + "input_cost_per_token_batches": 1.375e-07, + "input_cost_per_token_priority": 4.95e-07, + "litellm_provider": "azure", "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": true + "output_cost_per_token": 2.2e-06, + "output_cost_per_token_batches": 1.1e-06, + "output_cost_per_token_priority": 3.96e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/google/gemini-3.1-flash-image": { - "input_cost_per_token": 5e-07, - "output_cost_per_token": 3e-06, - "output_cost_per_image_token": 6e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/google/gemini-3-pro-image": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1.2e-05, - "cache_read_input_token_cost": 2e-07, - "cache_creation_input_token_cost": 3.75e-07, - "cache_read_input_audio_token_cost": 2e-07, - "input_cost_per_audio_token": 2e-06, - "output_cost_per_image_token": 0.00012, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "azure/eu/gpt-5-nano": { + "deprecation_date": "2027-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.4-nano", + "cache_read_input_token_cost": 5.5e-09, + "cache_read_input_token_cost_batches": 2.75e-09, + "input_cost_per_token": 5.5e-08, + "input_cost_per_token_batches": 2.75e-08, + "litellm_provider": "azure", "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": true + "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/z-ai/glm-5.2": { - "input_cost_per_token": 6.496e-07, - "output_cost_per_token": 2.0416e-06, - "cache_read_input_token_cost": 1.2064e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": false, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false + "azure/eu/gpt-5-pro": { + "deprecation_date": "2027-04-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.2-pro", + "input_cost_per_token": 1.65e-05, + "input_cost_per_token_batches": 8.25e-06, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 0.000132, + "output_cost_per_token_batches": 6.6e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/z-ai/glm-5.2:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 29491, - "max_tokens": 29491, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_vision": false, - "supports_web_search": false + "azure/eu/gpt-5.1-codex-max": { + "deprecation_date": "2027-05-18", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "cache_read_input_token_cost": 1.375e-07, + "input_cost_per_token": 1.375e-06, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/moonshotai/kimi-k2.7-code": { - "input_cost_per_token": 6.562e-07, - "output_cost_per_token": 3.3e-06, - "cache_read_input_token_cost": 1.8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, + "azure/eu/gpt-5.2": { + "deprecation_date": "2027-06-08", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.4", + "cache_read_input_token_cost": 1.925e-07, + "cache_read_input_token_cost_batches": 9.625e-08, + "cache_read_input_token_cost_priority": 3.85e-07, + "input_cost_per_token": 1.925e-06, + "input_cost_per_token_batches": 9.625e-07, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": false, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false + "output_cost_per_token": 1.54e-05, + "output_cost_per_token_batches": 7.7e-06, + "output_cost_per_token_priority": 3.08e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/nvidia/nemotron-3.5-content-safety": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_vision": true, - "supports_web_search": false + "azure/eu/gpt-5.2-codex": { + "deprecation_date": "2027-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.3-codex", + "cache_read_input_token_cost": 1.925e-07, + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/nvidia/nemotron-3.5-content-safety:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_vision": true, - "supports_web_search": false + "azure/eu/gpt-5.2-pro": { + "input_cost_per_token": 2.31e-05, + "input_cost_per_token_batches": 1.155e-05, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 0.0001848, + "output_cost_per_token_batches": 9.24e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/nvidia/nemotron-3-ultra-550b-a55b": { - "input_cost_per_token": 6e-07, - "output_cost_per_token": 2.4e-06, - "cache_read_input_token_cost": 1.2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 182520, - "max_tokens": 182520, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false + "azure/eu/gpt-5.3-codex": { + "deprecation_date": "2027-08-24", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "cache_read_input_token_cost": 1.925e-07, + "cache_read_input_token_cost_priority": 3.85e-07, + "input_cost_per_token": 1.925e-06, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 1.54e-05, + "output_cost_per_token_priority": 3.08e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/nvidia/nemotron-3-ultra-550b-a55b:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "azure/eu/gpt-5.4-mini": { + "default_reasoning_effort": "none", + "deprecation_date": "2027-09-21", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "cache_read_input_token_cost": 8.25e-08, + "cache_read_input_token_cost_batches": 4.125e-08, + "cache_read_input_token_cost_priority": 1.65e-07, + "input_cost_per_token": 8.25e-07, + "input_cost_per_token_batches": 4.125e-07, + "input_cost_per_token_priority": 1.65e-06, + "litellm_provider": "azure", "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_vision": false, - "supports_web_search": false + "output_cost_per_token": 4.95e-06, + "output_cost_per_token_batches": 2.475e-06, + "output_cost_per_token_priority": 9.9e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/minimax/minimax-m3:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, + "azure/eu/gpt-5.4-nano": { + "default_reasoning_effort": "none", + "deprecation_date": "2027-09-21", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "cache_read_input_token_cost": 2.2e-08, + "cache_read_input_token_cost_batches": 1.1e-08, + "input_cost_per_token": 2.2e-07, + "input_cost_per_token_batches": 1.1e-07, + "litellm_provider": "azure", "mode": "chat", - "source": "https://openrouter.ai/minimax/minimax-m3:free", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true + "output_cost_per_token": 1.375e-06, + "output_cost_per_token_batches": 6.875e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/qwen/qwen3.7-max": { - "input_cost_per_token": 1.475e-06, - "output_cost_per_token": 4.425e-06, - "cache_read_input_token_cost": 2.95e-07, - "cache_creation_input_token_cost": 1.84375e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false + "azure/eu/gpt-5.4-pro": { + "deprecation_date": "2027-09-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_token": 3.3e-05, + "input_cost_per_token_above_272k_tokens": 6.6e-05, + "input_cost_per_token_above_272k_tokens_batches": 3.3e-05, + "input_cost_per_token_batches": 1.65e-05, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 0.000198, + "output_cost_per_token_above_272k_tokens": 0.000297, + "output_cost_per_token_above_272k_tokens_batches": 0.0001485, + "output_cost_per_token_batches": 9.9e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/mistralai/mistral-medium-3-5": { - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 7.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, + "azure/eu/gpt-6-astra": { + "deprecation_date": "2028-01-11", + "cache_creation_input_token_cost": 1.5e-05, + "cache_creation_input_token_cost_above_272k_tokens": 3e-05, + "cache_read_input_token_cost": 1.2e-06, + "cache_read_input_token_cost_above_272k_tokens": 2.4e-06, + "input_cost_per_token": 1.2e-05, + "input_cost_per_token_above_272k_tokens": 2.4e-05, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 6e-05, + "output_cost_per_token_above_272k_tokens": 9e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, + "supports_max_reasoning_effort": false, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_web_search": false - }, - "openrouter/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 256000, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": true, - "supports_audio_input": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_response_schema": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.5-plus-20260420": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.8e-06, - "cache_creation_input_token_cost": 3.75e-07, - "input_cost_per_token_above_256k_tokens": 3.75e-07, - "output_cost_per_token_above_256k_tokens": 2.25e-06, - "cache_creation_input_token_cost_above_256k_tokens": 4.6875e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.6-flash": { - "input_cost_per_token": 1.875e-07, - "output_cost_per_token": 1.125e-06, - "cache_creation_input_token_cost": 2.34375e-07, - "input_cost_per_token_above_256k_tokens": 7.5e-07, - "output_cost_per_token_above_256k_tokens": 3e-06, - "cache_creation_input_token_cost_above_256k_tokens": 9.375e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, + "supports_system_messages": true, "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, "supports_vision": true, - "supports_web_search": false + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true }, - "openrouter/qwen/qwen3.6-35b-a3b": { - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1e-06, - "cache_read_input_token_cost": 5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, + "azure/eu/gpt-6-luna": { + "deprecation_date": "2028-03-11", + "cache_creation_input_token_cost": 1.5e-07, + "cache_creation_input_token_cost_above_272k_tokens": 3e-07, + "cache_read_input_token_cost": 1.2e-08, + "cache_read_input_token_cost_above_272k_tokens": 2.4e-08, + "input_cost_per_token": 1.2e-07, + "input_cost_per_token_above_272k_tokens": 2.4e-07, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 6e-07, + "output_cost_per_token_above_272k_tokens": 9e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.6-max-preview": { - "cache_creation_input_token_cost": 1.28375e-06, - "cache_creation_input_token_cost_above_128k_tokens": 1.975e-06, - "deprecation_date": "2026-10-09", - "input_cost_per_token": 1.027e-06, - "input_cost_per_token_above_128k_tokens": 1.58e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 6.162e-06, - "output_cost_per_token_above_128k_tokens": 9.48e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true }, - "openrouter/qwen/qwen3.6-27b": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 3.2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 81920, - "max_tokens": 81920, + "azure/eu/gpt-6-sol": { + "deprecation_date": "2028-03-11", + "cache_creation_input_token_cost": 3e-06, + "cache_creation_input_token_cost_above_272k_tokens": 6e-06, + "cache_read_input_token_cost": 2.4e-07, + "cache_read_input_token_cost_above_272k_tokens": 4.8e-07, + "input_cost_per_token": 2.4e-06, + "input_cost_per_token_above_272k_tokens": 4.8e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3.2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_272k_tokens": 1.8e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, "supports_function_calling": true, - "supports_pdf_input": false, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": false + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true }, - "openrouter/openai/gpt-5.5-pro": { - "input_cost_per_token": 3e-05, - "output_cost_per_token": 0.00018, - "input_cost_per_token_above_272k_tokens": 6e-05, - "output_cost_per_token_above_272k_tokens": 0.00027, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "azure/eu/o1-mini": { + "cache_read_input_token_cost": 6.05e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_web_search": true + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/openai/gpt-chat-latest": { - "input_cost_per_token": 5e-06, - "output_cost_per_token": 3e-05, - "cache_read_input_token_cost": 5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "azure/eu/o3": { + "deprecation_date": "2026-11-19", + "successor_model": "azure/eu/gpt-5.6-sol", + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_web_search": true + "output_cost_per_token": 8.8e-06, + "output_cost_per_token_batches": 4.4e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/deepseek/deepseek-v4-flash": { - "cache_read_input_token_cost": 2.8e-08, - "input_cost_per_token": 1.4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, + "azure/eu/o3-2025-04-16": { + "deprecation_date": "2026-11-19", + "successor_model": "azure/eu/gpt-5.6-sol", + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, "mode": "chat", - "output_cost_per_token": 2.8e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "output_cost_per_token": 8.8e-06, + "output_cost_per_token_batches": 4.4e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/moonshotai/kimi-k2.6": { - "input_cost_per_token": 6.5e-07, - "output_cost_per_token": 3.41e-06, - "cache_read_input_token_cost": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, + "azure/eu/o3-deep-research": { + "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.6-sol", + "cache_read_input_token_cost": 2.75e-06, + "input_cost_per_token": 1.1e-05, + "litellm_provider": "azure", "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": false, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false + "output_cost_per_token": 4.4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/google/gemma-4-26b-a4b-it": { - "cache_read_input_token_cost": 3.75e-08, - "input_cost_per_token": 6.75e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, + "azure/eu/o4-mini": { + "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.6-terra", + "cache_read_input_token_cost": 3.03e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, "mode": "chat", - "output_cost_per_token": 2.25e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/google/gemma-4-26b-a4b-it:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, + "azure/eu/o4-mini-2025-04-16": { + "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.6-terra", + "cache_read_input_token_cost": 3.03e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/google/gemma-4-31b-it": { - "input_cost_per_token": 9e-08, - "output_cost_per_token": 3.4e-07, - "cache_read_input_token_cost": 5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false + "azure/eu/text-embedding-3-large": { + "deprecation_date": "2028-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_token": 1.43e-07, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/google/gemma-4-31b-it:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "azure/eu/text-embedding-3-small": { + "deprecation_date": "2028-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_token": 2.2e-08, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/text-embedding-ada-002": { + "deprecation_date": "2028-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_token": 1.1e-07, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "gemini/gemini-3.8-live": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 7.5e-07, + "input_cost_per_video_token": 1e-06, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 4.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supports_audio_input": true, + "supports_audio_output": true, + "tpm": 250000, + "rpm": 10, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, + "supports_response_schema": false, "supports_vision": true, - "supports_web_search": false + "supports_web_search": true, + "supports_reasoning": true }, - "openrouter/z-ai/glm-5v-turbo": { - "input_cost_per_token": 1.2e-06, - "output_cost_per_token": 4e-06, - "cache_read_input_token_cost": 2.4e-07, - "deprecation_date": "2098-12-31", - "litellm_provider": "openrouter", - "max_input_tokens": 202752, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "gemini/gemini-3.8-live-extended-thinking": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 7.5e-07, + "input_cost_per_video_token": 1e-06, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 4.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supports_audio_input": true, + "supports_audio_output": true, + "tpm": 250000, + "rpm": 10, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, + "supports_response_schema": false, "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false + "supports_web_search": true, + "supports_reasoning": true }, - "openrouter/minimax/minimax-m2.7": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "cache_read_input_token_cost": 6e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 204800, - "max_output_tokens": 176947, - "max_tokens": 176947, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false + "azure/us/codex-mini": { + "deprecation_date": "2026-11-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "cache_read_input_token_cost": 4.13e-07, + "input_cost_per_token": 1.65e-06, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 6.6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/minimax/minimax-m2.7:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 196608, - "max_output_tokens": 176947, - "max_tokens": 176947, + "azure/us/computer-use-preview": { + "input_cost_per_token": 3.3e-06, + "litellm_provider": "azure", "mode": "chat", - "source": "https://openrouter.ai/minimax/minimax-m2.7:free", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false + "output_cost_per_token": 1.32e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/mistralai/mistral-small-2603": { - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "cache_read_input_token_cost": 1.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, + "azure/us/gpt-4.1": { + "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.1", + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_priority": 9.63e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false + "output_cost_per_token": 8.8e-06, + "output_cost_per_token_batches": 4.4e-06, + "output_cost_per_token_priority": 1.54e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/z-ai/glm-5-turbo": { - "input_cost_per_token": 1.2e-06, - "output_cost_per_token": 4e-06, - "cache_read_input_token_cost": 2.4e-07, - "deprecation_date": "2098-12-31", - "litellm_provider": "openrouter", - "max_input_tokens": 202752, - "max_output_tokens": 131072, - "max_tokens": 131072, + "azure/us/gpt-4.1-mini": { + "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.4-mini", + "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_priority": 1.93e-07, + "input_cost_per_token": 4.4e-07, + "input_cost_per_token_batches": 2.2e-07, + "input_cost_per_token_priority": 7.7e-07, + "litellm_provider": "azure", "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false + "output_cost_per_token": 1.76e-06, + "output_cost_per_token_batches": 8.8e-07, + "output_cost_per_token_priority": 3.08e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/nvidia/nemotron-3-super-120b-a12b": { - "input_cost_per_token": 8e-08, - "output_cost_per_token": 4.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, + "azure/us/gpt-4.1-nano": { + "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.4-nano", + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 1.1e-07, + "input_cost_per_token_batches": 5.5e-08, + "litellm_provider": "azure", "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false + "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/nvidia/nemotron-3-super-120b-a12b:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, + "azure/us/gpt-4o-2024-05-13": { + "deprecation_date": "2027-01-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.1", + "input_cost_per_token": 5.5e-06, + "input_cost_per_token_batches": 2.75e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false + "output_cost_per_token": 1.65e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/qwen/qwen3.5-9b": { - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, + "azure/us/gpt-5": { + "deprecation_date": "2027-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.1", + "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_batches": 6.875e-08, + "cache_read_input_token_cost_priority": 2.75e-07, + "input_cost_per_token": 1.375e-06, + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.75e-06, + "litellm_provider": "azure", "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 2.2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/openai/gpt-5.4-pro": { - "input_cost_per_token": 3e-05, - "output_cost_per_token": 0.00018, - "input_cost_per_token_above_272k_tokens": 6e-05, - "output_cost_per_token_above_272k_tokens": 0.00027, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_web_search": true + "azure/us/gpt-5-codex": { + "deprecation_date": "2027-03-17", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.1-codex", + "cache_read_input_token_cost": 1.38e-07, + "input_cost_per_token": 1.375e-06, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/google/gemini-3.1-flash-image-preview": { - "input_cost_per_token": 5e-07, - "output_cost_per_token": 3e-06, - "output_cost_per_image_token": 6e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 58982, - "max_tokens": 58982, + "azure/us/gpt-5-mini": { + "deprecation_date": "2027-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.4-mini", + "cache_read_input_token_cost": 2.75e-08, + "cache_read_input_token_cost_batches": 1.375e-08, + "cache_read_input_token_cost_priority": 4.95e-08, + "input_cost_per_token": 2.75e-07, + "input_cost_per_token_batches": 1.375e-07, + "input_cost_per_token_priority": 4.95e-07, + "litellm_provider": "azure", "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": true + "output_cost_per_token": 2.2e-06, + "output_cost_per_token_batches": 1.1e-06, + "output_cost_per_token_priority": 3.96e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/google/gemini-3.1-pro-preview-customtools": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1.2e-05, - "cache_read_input_token_cost": 2e-07, - "cache_creation_input_token_cost": 3.75e-07, - "cache_read_input_audio_token_cost": 2e-07, - "input_cost_per_audio_token": 2e-06, - "input_cost_per_token_above_200k_tokens": 4e-06, - "output_cost_per_token_above_200k_tokens": 1.8e-05, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "azure/us/gpt-5-nano": { + "deprecation_date": "2027-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.4-nano", + "cache_read_input_token_cost": 5.5e-09, + "cache_read_input_token_cost_batches": 2.75e-09, + "input_cost_per_token": 5.5e-08, + "input_cost_per_token_batches": 2.75e-08, + "litellm_provider": "azure", "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "supports_prompt_caching": true, - "supports_web_search": true, - "supports_video_input": true + "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/qwen/qwen3-max-thinking": { - "deprecation_date": "2026-10-09", - "input_cost_per_token": 7.8e-07, - "input_cost_per_token_above_128k_tokens": 1.95e-06, - "input_cost_per_token_above_32k_tokens": 1.56e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 3.9e-06, - "output_cost_per_token_above_128k_tokens": 9.75e-06, - "output_cost_per_token_above_32k_tokens": 7.8e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "azure/us/gpt-5-pro": { + "deprecation_date": "2027-04-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.2-pro", + "input_cost_per_token": 1.65e-05, + "input_cost_per_token_batches": 8.25e-06, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 0.000132, + "output_cost_per_token_batches": 6.6e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/qwen/qwen3-coder-next": { - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 8e-07, - "cache_read_input_token_cost": 7e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, + "azure/us/gpt-5.1-codex-max": { + "deprecation_date": "2027-05-18", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "cache_read_input_token_cost": 1.375e-07, + "input_cost_per_token": 1.375e-06, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.2": { + "deprecation_date": "2027-06-08", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.4", + "cache_read_input_token_cost": 1.925e-07, + "cache_read_input_token_cost_batches": 9.625e-08, + "cache_read_input_token_cost_priority": 3.85e-07, + "input_cost_per_token": 1.925e-06, + "input_cost_per_token_batches": 9.625e-07, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false + "output_cost_per_token": 1.54e-05, + "output_cost_per_token_batches": 7.7e-06, + "output_cost_per_token_priority": 3.08e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/minimax/minimax-m2-her": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "cache_read_input_token_cost": 3e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 2048, - "max_tokens": 2048, + "azure/us/gpt-5.2-codex": { + "deprecation_date": "2027-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.3-codex", + "cache_read_input_token_cost": 1.925e-07, + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.2-pro": { + "input_cost_per_token": 2.31e-05, + "input_cost_per_token_batches": 1.155e-05, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 0.0001848, + "output_cost_per_token_batches": 9.24e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.3-codex": { + "deprecation_date": "2027-08-24", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "cache_read_input_token_cost": 1.925e-07, + "cache_read_input_token_cost_priority": 3.85e-07, + "input_cost_per_token": 1.925e-06, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 1.54e-05, + "output_cost_per_token_priority": 3.08e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.4-mini": { + "default_reasoning_effort": "none", + "deprecation_date": "2027-09-21", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "cache_read_input_token_cost": 8.25e-08, + "cache_read_input_token_cost_batches": 4.125e-08, + "cache_read_input_token_cost_priority": 1.65e-07, + "input_cost_per_token": 8.25e-07, + "input_cost_per_token_batches": 4.125e-07, + "input_cost_per_token_priority": 1.65e-06, + "litellm_provider": "azure", "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_tool_choice": false, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_web_search": false + "output_cost_per_token": 4.95e-06, + "output_cost_per_token_batches": 2.475e-06, + "output_cost_per_token_priority": 9.9e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "openrouter/openai/gpt-audio": { - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, + "azure/us/gpt-5.4-nano": { + "default_reasoning_effort": "none", + "deprecation_date": "2027-09-21", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "cache_read_input_token_cost": 2.2e-08, + "cache_read_input_token_cost_batches": 1.1e-08, + "input_cost_per_token": 2.2e-07, + "input_cost_per_token_batches": 1.1e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.375e-06, + "output_cost_per_token_batches": 6.875e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.4-pro": { + "deprecation_date": "2027-09-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_token": 3.3e-05, + "input_cost_per_token_above_272k_tokens": 6.6e-05, + "input_cost_per_token_above_272k_tokens_batches": 3.3e-05, + "input_cost_per_token_batches": 1.65e-05, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 0.000198, + "output_cost_per_token_above_272k_tokens": 0.000297, + "output_cost_per_token_above_272k_tokens_batches": 0.0001485, + "output_cost_per_token_batches": 9.9e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/o1-mini": { + "cache_read_input_token_cost": 6.05e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/o3-deep-research": { + "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.6-sol", + "cache_read_input_token_cost": 2.75e-06, + "input_cost_per_token": 1.1e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/text-embedding-3-large": { + "deprecation_date": "2028-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_token": 1.43e-07, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/text-embedding-3-small": { + "deprecation_date": "2028-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_token": 2.2e-08, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/text-embedding-ada-002": { + "deprecation_date": "2028-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_token": 1.1e-07, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/gpt-realtime-2": { + "cache_read_input_image_token_cost": 5e-07, + "cache_creation_input_audio_token_cost": 4e-07, + "cache_read_input_audio_token_cost": 4e-07, + "cache_read_input_token_cost": 4e-07, + "deprecation_date": "2027-01-20", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-realtime-2.1", "input_cost_per_audio_token": 3.2e-05, + "input_cost_per_image_token": 5e-06, + "input_cost_per_token": 4e-06, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", + "output_cost_per_token": 2.4e-05, + "provider_specific_entry": { + "realtime_ga_only": 1 + }, + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "azure/gpt-live-1": { + "deprecation_date": "2027-09-10", + "input_cost_per_second": 0.000833333333333, + "litellm_provider": "azure", + "mode": "realtime", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], "supports_audio_input": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_web_search": false + "supports_audio_output": true, + "supports_function_calling": true }, - "openrouter/openai/gpt-audio-mini": { - "input_cost_per_token": 6e-07, - "output_cost_per_token": 2.4e-06, - "input_cost_per_audio_token": 6e-07, - "output_cost_per_audio_token": 2.4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, + "azure/gpt-live-transcribe": { + "deprecation_date": "2028-02-01", + "input_cost_per_second": 0.000283333333333, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "mode": "audio_transcription", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/realtime", + "/v1/realtime/transcription_sessions" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text" + ], "supports_audio_input": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_web_search": false + "provider_specific_entry": { + "realtime_ga_only": 1 + }, + "supports_native_streaming": true }, - "openrouter/nvidia/nemotron-3-nano-30b-a3b": { - "input_cost_per_token": 5e-08, - "output_cost_per_token": 2e-07, - "cache_read_input_token_cost": 3e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, + "azure/gpt-transcribe": { + "deprecation_date": "2028-02-01", + "input_cost_per_second": 7.5e-05, + "litellm_provider": "azure", + "mode": "audio_transcription", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/audio/transcriptions", + "/v1/realtime/transcription_sessions", + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "provider_specific_entry": { + "realtime_ga_only": 1, + "transcription_json_or_text_only": 1, + "transcription_usage_duration": 1 + }, + "supports_native_streaming": true + }, + "azure/gpt-realtime-translate": { + "deprecation_date": "2027-11-09", + "input_cost_per_second": 0.000566666666667, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "mode": "realtime", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "provider_specific_entry": { + "realtime_ga_only": 1 + }, + "supports_native_streaming": true + }, + "aihubmix/agnes-2.5-flash": { + "input_cost_per_token": 3e-08, + "litellm_provider": "aihubmix", + "max_input_tokens": 512000, + "max_output_tokens": 65500, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, + "output_cost_per_token": 1.5e-07, + "source": "https://aihubmix.com/api/v1/models", "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false + "supports_vision": true }, - "openrouter/z-ai/glm-4.6v": { - "input_cost_per_token": 3e-07, + "aihubmix/agnes-2.5-pro": { + "cache_read_input_token_cost": 3.78e-09, + "input_cost_per_token": 4.5e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "mode": "chat", "output_cost_per_token": 9e-07, - "cache_read_input_token_cost": 5.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "source": "https://aihubmix.com/api/v1/models", + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true + }, + "aihubmix/cc-glm-5.1": { + "input_cost_per_token": 6e-08, + "litellm_provider": "aihubmix", + "max_input_tokens": 200000, + "max_output_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 2.2e-07, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false + "supports_response_schema": true }, - "openrouter/google/gemini-3-pro-image-preview": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1.2e-05, - "cache_read_input_token_cost": 2e-07, - "cache_creation_input_token_cost": 3.75e-07, - "cache_read_input_audio_token_cost": 2e-07, - "input_cost_per_audio_token": 2e-06, - "output_cost_per_image_token": 0.00012, - "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 32768, - "max_tokens": 32768, + "aihubmix/claude-fable-5": { + "cache_read_input_token_cost": 1.1e-06, + "cache_creation_input_token_cost": 1.375e-05, + "input_cost_per_token": 1.1e-05, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_tool_choice": false, + "output_cost_per_token": 5.5e-05, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": true + "prompt_cache_min_tokens": 512, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_sampling_params": false }, - "openrouter/openai/gpt-5.1-codex": { - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "aihubmix/claude-haiku-4-5": { + "cache_read_input_token_cost": 1.1e-07, + "cache_creation_input_token_cost": 1.375e-06, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 200000, + "max_output_tokens": 64000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 5.5e-06, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": true + "prompt_cache_min_tokens": 4096 }, - "openrouter/openai/gpt-5.1-codex-mini": { - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 2e-06, - "cache_read_input_token_cost": 3e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, + "aihubmix/claude-opus-4-8-think": { + "cache_read_input_token_cost": 5e-07, + "cache_creation_input_token_cost": 6.25e-06, + "input_cost_per_token": 5e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 2.5e-05, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": true + "prompt_cache_min_tokens": 1024, + "supports_adaptive_thinking": true, + "supports_sampling_params": false }, - "openrouter/moonshotai/kimi-k2-thinking": { - "input_cost_per_token": 6e-07, - "output_cost_per_token": 2.5e-06, - "cache_read_input_token_cost": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 98304, - "max_tokens": 98304, + "aihubmix/claude-opus-5": { + "cache_read_input_token_cost": 5e-07, + "cache_creation_input_token_cost": 6.25e-06, + "input_cost_per_token": 5e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 2.5e-05, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false + "supports_vision": true, + "supports_web_search": true, + "supports_adaptive_thinking": true, + "prompt_cache_min_tokens": 512, + "supports_sampling_params": false }, - "openrouter/mistralai/voxtral-small-24b-2507": { - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "cache_read_input_token_cost": 1e-08, - "input_cost_per_audio_token": 0.0001, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 26214, - "max_tokens": 26214, + "aihubmix/claude-sonnet-5": { + "cache_read_input_token_cost": 2e-07, + "cache_creation_input_token_cost": 2.5e-06, + "input_cost_per_token": 2e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", + "output_cost_per_token": 1e-05, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, - "supports_pdf_input": true, - "supports_audio_input": true, + "supports_vision": true, + "prompt_cache_min_tokens": 1024, + "supports_adaptive_thinking": true, + "supports_sampling_params": false + }, + "aihubmix/coding-glm-5.3": { + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 6e-08, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.2e-07, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false + "supports_reasoning": true, + "supports_response_schema": true }, - "openrouter/openai/gpt-oss-safeguard-20b": { - "input_cost_per_token": 7.5e-08, - "output_cost_per_token": 3e-07, - "cache_read_input_token_cost": 3.75e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 65536, - "max_tokens": 65536, + "aihubmix/coding-kimi-k3": { + "cache_read_input_token_cost": 6.6e-08, + "input_cost_per_token": 4.4e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1.61333e-06, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false + "supports_vision": true }, - "openrouter/qwen/qwen3-vl-32b-instruct": { - "deprecation_date": "2026-10-09", - "input_cost_per_token": 1.04e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "aihubmix/coding-xiaomi-mimo-v2-omni": { + "cache_read_input_token_cost": 1.6e-08, + "input_cost_per_token": 8e-08, + "litellm_provider": "aihubmix", "mode": "chat", - "output_cost_per_token": 4.16e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 4e-07, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "supports_vision": true }, - "openrouter/qwen/qwen3-vl-8b-thinking": { - "deprecation_date": "2026-10-09", - "input_cost_per_token": 1.8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "aihubmix/coding-xiaomi-mimo-v2.5": { + "cache_read_input_token_cost": 1.6e-09, + "input_cost_per_token": 8e-08, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2.1e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1.6e-07, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "supports_vision": true }, - "openrouter/qwen/qwen3-vl-8b-instruct": { - "deprecation_date": "2026-10-09", - "input_cost_per_token": 1.17e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, + "aihubmix/coding-xiaomi-mimo-v2.5-pro": { + "cache_read_input_token_cost": 1.6e-09, + "input_cost_per_token": 2e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 4.55e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 4e-07, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true }, - "openrouter/google/gemini-2.5-flash-image": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 2.5e-06, - "cache_read_input_token_cost": 3e-08, - "cache_creation_input_token_cost": 8.33333333333333e-08, - "cache_read_input_audio_token_cost": 1e-07, - "deprecation_date": "2027-03-15", - "input_cost_per_audio_token": 1e-06, - "output_cost_per_image_token": 3e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "max_tokens": 8192, + "aihubmix/command-a-plus-05-2026": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 128000, + "max_output_tokens": 64000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_tool_choice": false, + "output_cost_per_token": 1e-05, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true, + "supports_vision": true + }, + "aihubmix/deepseek-v4-flash": { + "cache_read_input_token_cost": 2.84e-08, + "input_cost_per_token": 1.42e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 2.84e-07, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": true + "supports_reasoning": true, + "supports_response_schema": true }, - "openrouter/qwen/qwen3-vl-30b-a3b-thinking": { - "deprecation_date": "2026-10-09", - "input_cost_per_token": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, + "aihubmix/deepseek-v4-pro": { + "cache_read_input_token_cost": 1.4027e-07, + "input_cost_per_token": 1.69e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, "mode": "chat", - "output_cost_per_token": 2.4e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 3.38e-06, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true + }, + "aihubmix/doubao-seed-2-0-code-preview": { + "cache_read_input_token_cost": 9.644e-08, + "input_cost_per_token": 4.822e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 256000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.411e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": false + "supports_web_search": true }, - "openrouter/qwen/qwen3-vl-30b-a3b-instruct": { - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 16384, - "max_tokens": 16384, + "aihubmix/doubao-seed-2-0-lite-260428": { + "cache_read_input_token_cost": 1.8082e-08, + "input_cost_per_token": 9.041e-08, + "litellm_provider": "aihubmix", + "max_input_tokens": 256000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 5.4246e-07, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": false + "supports_web_search": true }, - "openrouter/openai/gpt-5-pro": { - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 0.00012, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, + "aihubmix/doubao-seed-2-0-mini": { + "cache_read_input_token_cost": 6.027e-09, + "input_cost_per_token": 3.0136e-08, + "litellm_provider": "aihubmix", + "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 3.0136e-07, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_tool_choice": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, "supports_web_search": true }, - "openrouter/qwen/qwen3-vl-235b-a22b-thinking": { - "deprecation_date": "2026-10-09", - "input_cost_per_token": 4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "aihubmix/doubao-seed-2-0-pro": { + "cache_read_input_token_cost": 9.644e-08, + "input_cost_per_token": 4.822e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 256000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 4e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 2.411e-06, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": false + "supports_web_search": true }, - "openrouter/qwen/qwen3-vl-235b-a22b-instruct": { - "input_cost_per_token": 2.1e-07, - "output_cost_per_token": 1.9e-06, - "cache_read_input_token_cost": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, + "aihubmix/doubao-seed-2-1-turbo": { + "cache_read_input_token_cost": 9.295e-08, + "input_cost_per_token": 4.6475e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 256000, + "max_output_tokens": 256000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 2.32375e-06, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/ernie-5.1": { + "cache_read_input_token_cost": 5.634e-07, + "input_cost_per_token": 5.634e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 119000, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 2.5353e-06, + "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false + "supports_reasoning": true }, - "openrouter/qwen/qwen3-max": { - "cache_creation_input_token_cost": 9.75e-07, - "cache_creation_input_token_cost_above_128k_tokens": 2.4375e-06, - "cache_creation_input_token_cost_above_32k_tokens": 1.95e-06, - "cache_read_input_token_cost": 1.56e-07, - "cache_read_input_token_cost_above_128k_tokens": 3.9e-07, - "cache_read_input_token_cost_above_32k_tokens": 3.12e-07, - "deprecation_date": "2026-10-09", - "input_cost_per_token": 7.8e-07, - "input_cost_per_token_above_128k_tokens": 1.95e-06, - "input_cost_per_token_above_32k_tokens": 1.56e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, + "aihubmix/gemini-3-flash-preview": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 5e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 3.9e-06, - "output_cost_per_token_above_128k_tokens": 9.75e-06, - "output_cost_per_token_above_32k_tokens": 7.8e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 3e-06, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, "supports_prompt_caching": true, - "supports_reasoning": false, + "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_vision": true, + "supports_web_search": true }, - "openrouter/deepseek/deepseek-v3.1-terminus": { - "input_cost_per_token": 2.7e-07, - "output_cost_per_token": 1e-06, - "cache_read_input_token_cost": 1.35e-07, - "deprecation_date": "2026-09-28", - "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 32768, - "max_tokens": 32768, + "aihubmix/gemini-3-flash-preview-search": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 5e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 3e-06, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false + "supports_vision": true, + "supports_web_search": true }, - "openrouter/qwen/qwen3-coder-flash": { - "input_cost_per_token": 1.95e-07, - "input_cost_per_token_above_32k_tokens": 3.25e-07, - "cache_creation_input_token_cost_above_32k_tokens": 4.0625e-07, - "cache_read_input_token_cost_above_32k_tokens": 6.5e-08, - "output_cost_per_token_above_32k_tokens": 1.625e-06, - "output_cost_per_token": 9.75e-07, - "cache_read_input_token_cost": 3.9e-08, - "cache_creation_input_token_cost": 2.4375e-07, - "input_cost_per_token_above_128k_tokens": 5.2e-07, - "output_cost_per_token_above_128k_tokens": 2.6e-06, - "cache_read_input_token_cost_above_128k_tokens": 1.04e-07, - "cache_creation_input_token_cost_above_128k_tokens": 6.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, + "aihubmix/gemini-3.1-pro-preview": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1.2e-05, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/qwen/qwen3-next-80b-a3b-thinking": { - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, + "aihubmix/gemini-3.1-pro-preview-customtools": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1.2e-05, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false + "supports_vision": true, + "supports_web_search": true }, - "openrouter/qwen/qwen3-next-80b-a3b-instruct": { - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1.1e-06, - "cache_read_input_token_cost": 7e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, + "aihubmix/gemini-3.5-flash-lite": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 2.499999e-06, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_web_search": false + "supports_sampling_params": false, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/qwen/qwen-plus-2025-07-28": { - "cache_creation_input_token_cost": 3.25e-07, - "cache_read_input_token_cost": 5.2e-08, - "deprecation_date": "2026-10-09", - "input_cost_per_token": 2.6e-07, - "input_cost_per_token_above_256k_tokens": 7.8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 32768, - "max_tokens": 32768, + "aihubmix/gemini-3.7-flash": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, "mode": "chat", - "output_cost_per_token": 7.8e-07, - "output_cost_per_token_above_256k_tokens": 2.34e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 3.75e-06, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_sampling_params": false, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/moonshotai/kimi-k2-0905": { - "input_cost_per_token": 6e-07, - "output_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", + "aihubmix/gemma-4-26b-a4b-it": { + "input_cost_per_token": 1.4e-07, + "litellm_provider": "aihubmix", "max_input_tokens": 262144, - "max_output_tokens": 98304, - "max_tokens": 98304, + "max_output_tokens": 131100, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false + "output_cost_per_token": 3.9998e-07, + "source": "https://aihubmix.com/api/v1/models", + "supports_reasoning": true, + "supports_vision": true }, - "openrouter/qwen/qwen3-30b-a3b-thinking-2507": { - "deprecation_date": "2026-10-09", - "input_cost_per_token": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 81920, - "max_output_tokens": 32768, - "max_tokens": 32768, + "aihubmix/gemma-4-31b-it": { + "input_cost_per_token": 1.4e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 262144, + "max_output_tokens": 131100, "mode": "chat", - "output_cost_per_token": 2.4e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, + "output_cost_per_token": 3.9998e-07, + "source": "https://aihubmix.com/api/v1/models", "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_vision": true }, - "openrouter/mistralai/mistral-medium-3.1": { - "input_cost_per_token": 4e-07, - "output_cost_per_token": 2e-06, - "cache_read_input_token_cost": 4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 104857, - "max_tokens": 104857, + "aihubmix/glm-5.2-fast-preview": { + "cache_read_input_token_cost": 5.635e-07, + "input_cost_per_token": 2.254e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 7.889e-06, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false + "supports_reasoning": true, + "supports_response_schema": true }, - "openrouter/z-ai/glm-4.5v": { - "input_cost_per_token": 6e-07, - "output_cost_per_token": 1.8e-06, - "cache_read_input_token_cost": 1.1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 16384, - "max_tokens": 16384, + "aihubmix/glm-5.3": { + "cache_read_input_token_cost": 2.817e-07, + "input_cost_per_token": 1.1268e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 3.9438e-06, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, "supports_prompt_caching": true, - "supports_web_search": false + "supports_reasoning": true, + "supports_response_schema": true }, - "openrouter/mistralai/codestral-2508": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 9e-07, - "cache_read_input_token_cost": 3e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 256000, - "max_output_tokens": 204800, - "max_tokens": 204800, + "aihubmix/glm-5.3-flash": { + "cache_read_input_token_cost": 2.817e-08, + "input_cost_per_token": 1.1268e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 3.9438e-07, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true }, - "openrouter/qwen/qwen3-coder-30b-a3b-instruct": { - "input_cost_per_token": 7e-08, - "output_cost_per_token": 2.8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-30b-a3b-instruct-2507": { - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, + "aihubmix/glm-5v-turbo": { + "cache_read_input_token_cost": 1.69008e-07, + "input_cost_per_token": 7.042e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 200000, + "max_output_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false + "output_cost_per_token": 3.09848e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true }, - "openrouter/z-ai/glm-4.5": { - "input_cost_per_token": 6e-07, - "output_cost_per_token": 2.2e-06, - "cache_read_input_token_cost": 1.1e-07, - "deprecation_date": "2026-12-31", - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 98304, - "max_tokens": 98304, + "aihubmix/gpt-5.3-codex": { + "cache_read_input_token_cost": 1.75e-07, + "input_cost_per_token": 1.75e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 400000, + "max_output_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1.4e-05, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false + "supports_vision": true }, - "openrouter/z-ai/glm-4.5-air": { - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 8.5e-07, - "cache_read_input_token_cost": 2.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 98304, - "max_tokens": 98304, + "aihubmix/gpt-5.4-high": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1.5e-05, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": false, "supports_prompt_caching": true, - "supports_response_schema": false, - "supports_web_search": false - }, - "openrouter/moonshotai/kimi-k2": { - "input_cost_per_token": 5.7e-07, - "output_cost_per_token": 2.3e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 98304, - "max_tokens": 98304, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/minimax/minimax-m1": { - "input_cost_per_token": 4e-07, - "output_cost_per_token": 2.2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 40000, - "max_tokens": 40000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, "supports_reasoning": true, - "supports_response_schema": false, - "supports_vision": false, - "supports_web_search": false + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/openai/o3-pro": { - "input_cost_per_token": 2e-05, - "output_cost_per_token": 8e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "aihubmix/gpt-5.4-low": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1.5e-05, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_tool_choice": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, "supports_web_search": true }, - "openrouter/google/gemini-2.5-pro-preview": { - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-07, - "cache_creation_input_token_cost": 3.75e-07, - "cache_read_input_audio_token_cost": 1.25e-07, - "input_cost_per_audio_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 1.5e-05, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "aihubmix/gpt-5.4-mini": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 400000, + "max_output_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", + "output_cost_per_token": 4.5e-06, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_tool_choice": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "supports_prompt_caching": true, "supports_web_search": true }, - "openrouter/mistralai/mistral-medium-3": { - "input_cost_per_token": 4e-07, - "output_cost_per_token": 2e-06, - "cache_read_input_token_cost": 4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 104857, - "max_tokens": 104857, + "aihubmix/gpt-5.4-nano": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 400000, + "max_output_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1.25e-06, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false + "supports_web_search": true }, - "openrouter/google/gemini-2.5-pro-preview-05-06": { - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-07, - "cache_creation_input_token_cost": 3.75e-07, - "input_cost_per_audio_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 1.5e-05, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "aihubmix/gpt-5.5": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/google/gemini-2.5-pro-preview-05-06", + "output_cost_per_token": 3e-05, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_tool_choice": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "supports_prompt_caching": true + "supports_web_search": true }, - "openrouter/meta-llama/llama-guard-4-12b": { - "input_cost_per_token": 1.8e-07, - "output_cost_per_token": 1.8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 16384, - "max_tokens": 16384, + "aihubmix/gpt-5.5-pro": { + "input_cost_per_token": 3e-05, + "litellm_provider": "aihubmix", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": false, - "supports_response_schema": false, + "output_cost_per_token": 0.00018, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_vision": true, - "supports_web_search": false + "supports_web_search": true }, - "openrouter/qwen/qwen3-30b-a3b": { - "deprecation_date": "2026-10-09", - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, + "aihubmix/gpt-5.6-luna": { + "cache_read_input_token_cost": 2e-08, + "cache_creation_input_token_cost": 2.5e-07, + "input_cost_per_token": 2e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1.2e-06, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false + "supports_vision": true }, - "openrouter/qwen/qwen3-8b": { - "deprecation_date": "2026-10-09", - "input_cost_per_token": 1.17e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 8192, - "max_tokens": 8192, + "aihubmix/gpt-5.6-sol-disc": { + "cache_read_input_token_cost": 4e-07, + "cache_creation_input_token_cost": 5e-06, + "input_cost_per_token": 4e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 4.55e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 2e-05, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_vision": true }, - "openrouter/qwen/qwen3-14b": { - "deprecation_date": "2026-10-09", - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 2.4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, + "aihubmix/gpt-5.6-terra": { + "cache_read_input_token_cost": 2e-07, + "cache_creation_input_token_cost": 2.5e-06, + "input_cost_per_token": 2e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1.2e-05, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false + "supports_vision": true }, - "openrouter/qwen/qwen3-32b": { - "input_cost_per_token": 8e-08, - "output_cost_per_token": 2.8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, + "aihubmix/gpt-chat-latest": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 400000, + "max_output_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 3e-05, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false + "supports_vision": true, + "supports_web_search": true }, - "openrouter/qwen/qwen3-235b-a22b": { - "deprecation_date": "2026-10-09", - "input_cost_per_token": 4.55e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 8192, - "max_tokens": 8192, + "aihubmix/grok-4-20-non-reasoning": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 1.82e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 6e-06, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_vision": true }, - "openrouter/openai/o4-mini-high": { - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 2.75e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "aihubmix/grok-4-20-reasoning": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 6e-06, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_tool_choice": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_web_search": true + "supports_vision": true }, - "openrouter/meta-llama/llama-4-maverick": { - "input_cost_per_token": 1.875e-07, - "output_cost_per_token": 6.525e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 16384, - "max_tokens": 16384, + "aihubmix/grok-4.6": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 500000, + "max_output_tokens": 500000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 6e-06, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false + "supports_vision": true }, - "openrouter/meta-llama/llama-4-scout": { - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1310720, - "max_output_tokens": 16384, - "max_tokens": 16384, + "aihubmix/grok-build-0.1": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 256000, + "max_output_tokens": 256000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 2e-06, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false + "supports_vision": true }, - "openrouter/openai/o1-pro": { - "input_cost_per_token": 0.00015, - "output_cost_per_token": 0.0006, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "aihubmix/hy3": { + "cache_read_input_token_cost": 3.905e-08, + "input_cost_per_token": 1.562e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 256000, + "max_output_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_tool_choice": false, + "output_cost_per_token": 6.248e-07, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, "supports_web_search": true }, - "openrouter/google/gemma-3-4b-it": { - "input_cost_per_token": 5e-08, - "output_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, + "aihubmix/hy4-preview": { + "cache_read_input_token_cost": 4.225e-08, + "input_cost_per_token": 8.45e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 64000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": false, + "output_cost_per_token": 2.535e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false + "supports_web_search": true }, - "openrouter/google/gemma-3-12b-it": { - "input_cost_per_token": 5e-08, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, + "aihubmix/kimi-k2.6": { + "cache_read_input_token_cost": 1.60835e-07, + "input_cost_per_token": 9.5e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 262144, + "max_output_tokens": 32768, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 3.9995e-06, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false + "supports_vision": true }, - "openrouter/google/gemma-3-27b-it": { - "input_cost_per_token": 8e-08, - "output_cost_per_token": 4.5e-07, - "cache_read_input_token_cost": 4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, + "aihubmix/kimi-k2.7-code-highspeed": { + "cache_read_input_token_cost": 3.2167e-07, + "input_cost_per_token": 1.9e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 262144, + "max_output_tokens": 32768, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 7.999e-06, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": true, "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true }, - "openrouter/mistralai/mistral-saba": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 6e-07, - "cache_read_input_token_cost": 2e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 26214, - "max_tokens": 26214, + "aihubmix/kimi-k3": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1.5e-05, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen2.5-vl-72b-instruct": { - "input_cost_per_token": 8e-07, - "output_cost_per_token": 1e-06, - "cache_read_input_token_cost": 4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 115200, - "max_tokens": 115200, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_tool_choice": false, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false + "supports_vision": true }, - "openrouter/qwen/qwen-plus": { - "input_cost_per_token": 2.6e-07, - "output_cost_per_token": 7.8e-07, - "cache_read_input_token_cost": 5.2e-08, - "cache_creation_input_token_cost": 3.25e-07, - "input_cost_per_token_above_256k_tokens": 7.8e-07, - "output_cost_per_token_above_256k_tokens": 2.34e-06, - "cache_read_input_token_cost_above_256k_tokens": 1.56e-07, - "cache_creation_input_token_cost_above_256k_tokens": 9.75e-07, - "litellm_provider": "openrouter", + "aihubmix/longcat-2.0": { + "cache_read_input_token_cost": 1.5492e-08, + "input_cost_per_token": 7.746e-07, + "litellm_provider": "aihubmix", "max_input_tokens": 1000000, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, + "output_cost_per_token": 3.0984e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false + "supports_reasoning": true }, - "openrouter/mistralai/mistral-small-24b-instruct-2501": { - "input_cost_per_token": 5e-08, - "output_cost_per_token": 8e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 16384, - "max_tokens": 16384, + "aihubmix/mai-thinking-1": { + "input_cost_per_token": 2e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 256000, + "max_output_tokens": 64000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": false, + "output_cost_per_token": 8e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_reasoning": true, + "supports_response_schema": true + }, + "aihubmix/mimo-v2-omni": { + "cache_read_input_token_cost": 8.8e-08, + "input_cost_per_token": 4.4e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 2.2e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_prompt_caching": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/mimo-v2-pro": { + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 3.3e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_prompt_caching": true, + "supports_web_search": true + }, + "aihubmix/minimax-m2.7": { + "cache_read_input_token_cost": 5.916e-08, + "input_cost_per_token": 2.958e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 204800, + "max_output_tokens": 204800, + "mode": "chat", + "output_cost_per_token": 1.1832e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true + }, + "aihubmix/minimax-m3": { + "input_cost_per_token": 2.88e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 524288, + "mode": "chat", + "output_cost_per_token": 1.152e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false + "supports_vision": true }, - "openrouter/deepseek/deepseek-r1-distill-llama-70b": { - "deprecation_date": "2026-09-28", - "input_cost_per_token": 8e-07, - "output_cost_per_token": 8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 8192, - "max_output_tokens": 7372, - "max_tokens": 7372, + "aihubmix/muse-spark-1.2": { + "input_cost_per_token": 1.375e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": false, + "output_cost_per_token": 4.675e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, "supports_reasoning": true, - "supports_response_schema": false, - "supports_vision": false, - "supports_web_search": false + "supports_vision": true }, - "openrouter/minimax/minimax-01": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 1.1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000192, - "max_output_tokens": 900172, - "max_tokens": 900172, + "aihubmix/qwen3-coder-next": { + "input_cost_per_token": 1.37e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 262144, + "max_output_tokens": 65536, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, + "output_cost_per_token": 5.48e-07, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_response_schema": true + }, + "aihubmix/qwen3.5-122b-a10b": { + "input_cost_per_token": 1.126e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 9.008e-07, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_vision": true, - "supports_web_search": false + "supports_web_search": true }, - "openrouter/meta-llama/llama-3.3-70b-instruct": { - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3.2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, + "aihubmix/qwen3.5-397b-a17b": { + "input_cost_per_token": 1.644e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 262144, + "max_output_tokens": 65536, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 9.864e-07, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false + "supports_vision": true, + "supports_web_search": true }, - "openrouter/openai/gpt-4o-2024-11-20": { - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "aihubmix/qwen3.6-27b": { + "input_cost_per_token": 4.22e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 262144, + "max_output_tokens": 65536, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 2.532e-06, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_tool_choice": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_web_search": true, "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false + "supports_web_search": true }, - "openrouter/mistralai/mistral-large-2407": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "cache_read_input_token_cost": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 104857, - "max_tokens": 104857, + "aihubmix/qwen3.6-35b-a3b": { + "input_cost_per_token": 2.54e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 262144, + "max_output_tokens": 65536, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1.524e-06, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_tool_choice": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false + "supports_vision": true, + "supports_web_search": true }, - "openrouter/qwen/qwen-2.5-7b-instruct": { - "input_cost_per_token": 1e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 29491, - "max_tokens": 29491, + "aihubmix/qwen3.6-max-preview": { + "cache_read_input_token_cost": 1.268e-07, + "cache_creation_input_token_cost": 1.585e-06, + "input_cost_per_token": 1.268e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 262144, + "max_output_tokens": 65536, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 7.608e-06, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false + "supports_web_search": true }, - "openrouter/meta-llama/llama-3.2-1b-instruct": { - "input_cost_per_token": 2.7e-08, - "output_cost_per_token": 2.01e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 60000, - "max_output_tokens": 54000, - "max_tokens": 54000, + "aihubmix/qwen3.7-plus": { + "cache_read_input_token_cost": 5.64e-08, + "cache_creation_input_token_cost": 3.525e-07, + "input_cost_per_token": 2.82e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false + "output_cost_per_token": 1.128e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/meta-llama/llama-3.2-3b-instruct": { - "input_cost_per_token": 5e-08, - "output_cost_per_token": 3.3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, + "aihubmix/qwen3.8-2.4t-a95b": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": false, + "output_cost_per_token": 6e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false + "supports_web_search": true }, - "openrouter/qwen/qwen-2.5-72b-instruct": { - "input_cost_per_token": 3.6e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 16384, - "max_tokens": 16384, + "aihubmix/qwen3.8-flash": { + "cache_read_input_token_cost": 1.4075e-08, + "cache_creation_input_token_cost": 1.75937e-07, + "input_cost_per_token": 1.126e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 3.80025e-07, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false + "supports_vision": true, + "supports_web_search": true }, - "openrouter/openai/gpt-4o-2024-08-06": { - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "aihubmix/qwen3.8-max": { + "cache_read_input_token_cost": 1.69e-07, + "cache_creation_input_token_cost": 2.1125e-06, + "input_cost_per_token": 1.69e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 5.07e-06, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_web_search": true, "supports_vision": true, - "supports_pdf_input": true, + "supports_web_search": true + }, + "aihubmix/step-3.7-flash": { + "cache_read_input_token_cost": 4.4e-08, + "input_cost_per_token": 2.2e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.32e-06, + "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, - "supports_reasoning": false + "supports_reasoning": true, + "supports_vision": true }, - "openrouter/meta-llama/llama-3.1-70b-instruct": { - "input_cost_per_token": 4e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, + "aiand/deepseek-ai/deepseek-v4-flash": { + "cache_read_input_token_cost": 8e-08, + "deprecation_date": "2026-10-27", + "input_cost_per_token": 1.5e-07, + "litellm_provider": "aiand", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 2.5e-07, + "source": "https://api.aiand.com/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false + "supports_vision": false }, - "openrouter/meta-llama/llama-3.1-8b-instruct": { - "input_cost_per_token": 5e-08, - "output_cost_per_token": 8e-08, - "cache_read_input_token_cost": 2.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, + "aiand/deepseek-ai/deepseek-v4-pro": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "aiand", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 2.5e-06, + "source": "https://api.aiand.com/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "openrouter/mistralai/mistral-nemo": { - "input_cost_per_token": 1.9e-08, - "output_cost_per_token": 3e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, + "aiand/deepseek-ai/deepseek-v4.1-flash": { + "cache_read_input_token_cost": 2e-08, + "deprecation_date": "2026-11-05", + "input_cost_per_token": 3e-07, + "litellm_provider": "aiand", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 6e-07, + "source": "https://api.aiand.com/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false + "supports_vision": true }, - "openrouter/openai/gpt-4o-mini-2024-07-18": { - "input_cost_per_token": 1.5e-07, + "aiand/deepseek-ai/deepseek-v4.1-flash-1017": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "aiand", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "mode": "chat", "output_cost_per_token": 6e-07, - "cache_read_input_token_cost": 7.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "source": "https://api.aiand.com/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "aiand/google/gemma-4-31b-it": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "aiand", + "max_input_tokens": 262144, + "max_output_tokens": 32768, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 5e-07, + "source": "https://api.aiand.com/v1/models", "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_tool_choice": true, - "supports_response_schema": true, - "supports_web_search": true, - "supports_vision": true, - "supports_pdf_input": true, + "supports_vision": true + }, + "aiand/meta/muse-spark-open": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "aiand", + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "mode": "chat", + "output_cost_per_token": 4.25e-06, + "source": "https://api.aiand.com/v1/models", + "supports_function_calling": true, "supports_prompt_caching": true, - "supports_reasoning": false + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true }, - "openrouter/google/gemma-2-27b-it": { - "input_cost_per_token": 6.5e-07, - "output_cost_per_token": 6.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 8192, - "max_output_tokens": 2048, - "max_tokens": 2048, + "aiand/moonshotai/kimi-k2.7-code": { + "cache_read_input_token_cost": 2e-07, + "deprecation_date": "2026-10-27", + "input_cost_per_token": 7.5e-07, + "litellm_provider": "aiand", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false + "output_cost_per_token": 3.5e-06, + "source": "https://api.aiand.com/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true }, - "openrouter/openai/gpt-4-turbo": { - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "aiand/moonshotai/kimi-k3": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "aiand", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1.25e-05, + "source": "https://api.aiand.com/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false + "supports_vision": true }, - "openrouter/openai/gpt-4-turbo-preview": { - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "aiand/motif-technologies/motif-3": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 5e-07, + "litellm_provider": "aiand", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", - "source": "https://openrouter.ai/openai/gpt-4-turbo-preview", + "output_cost_per_token": 2e-06, + "source": "https://api.aiand.com/v1/models", "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_tool_choice": true, - "supports_response_schema": true, "supports_vision": false }, - "openrouter/openai/gpt-3.5-turbo-instruct": { - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 4095, - "max_output_tokens": 3685, - "max_tokens": 3685, + "aiand/openai/gpt-oss-120b": { + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "aiand", + "max_input_tokens": 131072, + "max_output_tokens": 32768, "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false + "output_cost_per_token": 6e-07, + "source": "https://api.aiand.com/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "together_ai/arcee-ai/trinity-mini": { - "input_cost_per_token": 4.5e-08, - "litellm_provider": "together_ai", + "aiand/qwen/qwen3.6-27b": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 3.2e-07, + "litellm_provider": "aiand", + "max_input_tokens": 262144, + "max_output_tokens": 65536, "mode": "chat", - "output_cost_per_token": 1.5e-07, - "source": "https://api.together.ai/v1/models", - "max_input_tokens": 128000, - "max_tokens": 128000 + "output_cost_per_token": 3.2e-06, + "source": "https://api.aiand.com/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true }, - "vertex_ai/gemini-2.5-flash-native-audio": { - "deprecation_date": "2026-12-13", - "input_cost_per_audio_token": 3e-06, - "input_cost_per_image_token": 3e-06, - "input_cost_per_token": 5e-07, - "input_cost_per_video_token": 3e-06, - "litellm_provider": "vertex_ai", - "mode": "realtime", - "output_cost_per_audio_token": 1.2e-05, - "output_cost_per_token": 2e-06, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "aiand/qwen/qwen3.8-27b": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 4e-07, + "litellm_provider": "aiand", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://api.aiand.com/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true }, - "vertex_ai/gemini-2.5-flash-preview-tts": { - "input_cost_per_token": 5e-07, - "input_cost_per_token_batches": 2.5e-07, - "litellm_provider": "vertex_ai", - "mode": "audio_speech", - "output_cost_per_audio_token": 1e-05, - "output_cost_per_token": 1e-05, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "aiand/zai-org/glm-5.2": { + "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2026-10-27", + "input_cost_per_token": 1e-06, + "litellm_provider": "aiand", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://api.aiand.com/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "vertex_ai/gemini-3.1-flash-tts-preview": { + "aiand/zai-org/glm-5.3": { + "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 1e-06, - "input_cost_per_token_batches": 5e-07, - "litellm_provider": "vertex_ai", - "mode": "audio_speech", - "output_cost_per_audio_token": 2e-05, - "output_cost_per_token": 2e-05, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "litellm_provider": "aiand", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://api.aiand.com/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "vertex_ai/gemini-3.5-transcribe": { - "input_cost_per_audio_token": 2e-06, - "input_cost_per_second": 5e-05, - "litellm_provider": "vertex_ai", - "mode": "audio_transcription", - "output_cost_per_token": 1.2e-05, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "aiand/zai-org/glm-5.3-flash": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "aiand", + "max_input_tokens": 1048550, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://api.aiand.com/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true }, - "vertex_ai/gemini-3.5-transcribe-live": { - "input_cost_per_audio_token": 3.5e-06, - "input_cost_per_second": 8.33333333333e-05, - "litellm_provider": "vertex_ai", - "mode": "audio_transcription", - "output_cost_per_token": 2.1e-05, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "bespoke/nimble-latest": { + "input_cost_per_token": 0.0, + "litellm_provider": "bespoke", + "max_input_tokens": 8192, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://github.com/bespokelabsai/nimble", + "supported_endpoints": [ + "/v1/systemone" + ], + "metadata": { + "notes": "Self-hosted decision model; infrastructure costs are paid separately" + } }, - "vertex_ai/gemini-omni-1.1-flash": { - "input_cost_per_token": 1.5e-06, - "litellm_provider": "vertex_ai", - "mode": "chat", - "output_cost_per_reasoning_token": 9e-06, - "output_cost_per_token": 9e-06, - "output_cost_per_video_token": 1.75e-05, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "bespoke/nimble": { + "input_cost_per_token": 0.0, + "litellm_provider": "bespoke", + "max_input_tokens": 8192, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://ollama.com/library/nimble", + "supported_endpoints": [ + "/v1/systemone" + ], + "metadata": { + "notes": "Self-hosted decision model under the name Ollama serves it as; infrastructure costs are paid separately" + } }, - "vertex_ai/gemini-omni-1.1-flash-preview": { - "input_cost_per_token": 1.5e-06, - "litellm_provider": "vertex_ai", - "max_output_tokens": 57920, - "max_tokens": 57920, - "mode": "chat", - "output_cost_per_reasoning_token": 9e-06, - "output_cost_per_token": 9e-06, - "output_cost_per_video_token": 1.75e-05, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "bespoke/bespokelabs/Bespoke-Nimble-9B": { + "input_cost_per_token": 0.0, + "litellm_provider": "bespoke", + "max_input_tokens": 8192, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://github.com/bespokelabsai/nimble", "supported_endpoints": [ - "/v1beta/interactions" + "/v1/systemone" ], - "supported_modalities": [ - "text", - "image", - "video" + "metadata": { + "notes": "Self-hosted decision model; infrastructure costs are paid separately" + } + }, + "laya/english": { + "input_cost_per_token": 0.0, + "litellm_provider": "laya", + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://github.com/NandhaKishorM/laya", + "supported_endpoints": [ + "/v1/systemone" ], - "supported_output_modalities": [ - "text", - "video" + "metadata": { + "notes": "Self-hosted decision model; infrastructure costs are paid separately" + } + }, + "laya/multilingual": { + "input_cost_per_token": 0.0, + "litellm_provider": "laya", + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://github.com/NandhaKishorM/laya", + "supported_endpoints": [ + "/v1/systemone" ], - "supports_reasoning": true, - "supports_video_input": true, - "supports_vision": true + "metadata": { + "notes": "Self-hosted decision model; infrastructure costs are paid separately" + } }, - "vertex_ai/gemma-4-26b-a4b-it": { - "cache_read_input_token_cost": 1.5e-08, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "vertex_ai", - "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "laya/typed-decisions": { + "input_cost_per_token": 0.0, + "litellm_provider": "laya", + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://github.com/NandhaKishorM/laya", + "supported_endpoints": [ + "/v1/systemone" + ], + "metadata": { + "notes": "Self-hosted decision model; infrastructure costs are paid separately" + } }, - "gpt-5.5-cyber": { - "cache_read_input_token_cost": 1.25e-06, - "input_cost_per_token": 1.25e-05, - "litellm_provider": "openai", - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "source": "https://developers.openai.com/api/docs/pricing", - "supports_reasoning": true + "strands_decider/strands-decider-2B-hobson-v19": { + "input_cost_per_token": 0.0, + "litellm_provider": "strands_decider", + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://huggingface.co/StrandsAgents/strands-decider-2B-hobson-v19", + "metadata": { + "notes": "Self-hosted decision model; infrastructure costs are paid separately" + } }, - "gpt-rosalind-research": { - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 5e-06, - "litellm_provider": "openai", - "mode": "chat", - "output_cost_per_token": 2.5e-05, - "source": "https://developers.openai.com/api/docs/pricing" + "nace/drex-v1.0": { + "input_cost_per_token": 4e-08, + "litellm_provider": "nace", + "max_input_tokens": 32768, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://console.nace.ai/docs/drex/reference/models" }, - "together_ai/meta-llama/Llama-3.1-405B-Instruct": { - "input_cost_per_token": 3.5e-06, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 3.5e-06, - "source": "https://api.together.ai/v1/models", - "max_input_tokens": 4096, - "max_tokens": 4096 + "nace/drex-v1.5": { + "input_cost_per_token": 5e-08, + "litellm_provider": "nace", + "max_input_tokens": 131072, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://console.nace.ai/docs/drex/reference/models" }, - "together_ai/meta-llama/Llama-3.2-1B-Instruct": { + "nace/drex-v2.0": { "input_cost_per_token": 6e-08, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 6e-08, - "source": "https://api.together.ai/v1/models", + "litellm_provider": "nace", "max_input_tokens": 131072, - "max_tokens": 131072 + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://console.nace.ai/docs/drex/reference/models" }, - "together_ai/meta-llama/Llama-3.2-3B-Instruct": { + "nace/drex-latest": { "input_cost_per_token": 6e-08, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 6e-08, - "source": "https://api.together.ai/v1/models", + "litellm_provider": "nace", "max_input_tokens": 131072, - "max_tokens": 131072 - }, - "together_ai/Qwen/Qwen2-1.5B-Instruct": { - "input_cost_per_token": 2e-08, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 2e-08, - "source": "https://api.together.ai/v1/models", - "max_input_tokens": 32768, - "max_tokens": 32768 - }, - "together_ai/Qwen/Qwen2.5-14B-Instruct": { - "input_cost_per_token": 8e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 8e-07, - "source": "https://api.together.ai/v1/models", - "max_input_tokens": 32768, - "max_tokens": 32768 - }, - "together_ai/Qwen/Qwen2.5-72B-Instruct": { - "input_cost_per_token": 1.2e-06, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://api.together.ai/v1/models", - "max_input_tokens": 32768, - "max_tokens": 32768 - }, - "together_ai/Salesforce/Llama-Rank-V1": { - "deprecation_date": "2026-02-06", - "input_cost_per_token": 1e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 8192, - "max_tokens": 8192, - "mode": "rerank", + "mode": "evaluation", "output_cost_per_token": 0.0, - "source": "https://api.together.ai/v1/models" + "source": "https://console.nace.ai/docs/drex/reference/models" }, - "together_ai/meta-llama/Meta-Llama-3.1-8B": { - "input_cost_per_token": 2e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 16384, - "max_tokens": 16384, - "mode": "completion", - "output_cost_per_token": 2e-07, - "source": "https://api.together.xyz/v1/models" + "typesafe/jev-1.13.0": { + "input_cost_per_token": 4.2e-08, + "litellm_provider": "typesafe", + "max_input_tokens": 65536, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.typesafe.ai/models" }, - "together_ai/together/Tev1-4B-experimental": { - "cache_read_input_token_cost": 4.2e-08, + "typesafe/jev-1.14.0": { "input_cost_per_token": 4.2e-08, - "litellm_provider": "together_ai", - "max_input_tokens": 32768, - "mode": "chat", + "litellm_provider": "typesafe", + "max_input_tokens": 65536, + "mode": "evaluation", "output_cost_per_token": 0.0, - "source": "https://api.together.ai/v1/models" + "source": "https://docs.typesafe.ai/models", + "supports_box_questions": true }, - "together_ai/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 6e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://api.together.ai/v1/models" + "typesafe/jev-latest": { + "input_cost_per_token": 4.2e-08, + "litellm_provider": "typesafe", + "max_input_tokens": 65536, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.typesafe.ai/models", + "supports_box_questions": true }, - "together_ai/Qwen/QwQ-32B": { - "deprecation_date": "2025-11-13", - "input_cost_per_token": 1.2e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://api.together.ai/v1/models" + "typesafe/jev-preview": { + "input_cost_per_token": 4.2e-08, + "litellm_provider": "typesafe", + "max_input_tokens": 65536, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.typesafe.ai/models", + "supports_box_questions": true }, - "together_ai/Qwen/Qwen2-72B-Instruct": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 9e-07, - "litellm_provider": "together_ai", + "eu_jev/eu-jeff-1.0.0": { + "input_cost_per_token": 4.15e-08, + "litellm_provider": "eu_jev", "max_input_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 9e-07, - "source": "https://api.together.ai/v1/models" + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://eu-jev.com/docs", + "supported_endpoints": [ + "/v1/systemone" + ] }, - "together_ai/Qwen/Qwen2-VL-72B-Instruct": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 1.2e-06, - "litellm_provider": "together_ai", + "eu_jev/eu-jeff-latest": { + "input_cost_per_token": 4.15e-08, + "litellm_provider": "eu_jev", "max_input_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://api.together.ai/v1/models" + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://eu-jev.com/docs", + "supported_endpoints": [ + "/v1/systemone" + ] }, - "together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo": { - "deprecation_date": "2026-02-06", - "input_cost_per_token": 1.2e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 131072, - "max_tokens": 131072, + "wandb/deepseek-ai/DeepSeek-V4.1-Flash": { + "cache_read_input_token_cost": 2e-09, + "input_cost_per_token": 1.3e-07, + "litellm_provider": "wandb", + "max_input_tokens": 1049000, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://api.together.ai/v1/models" + "output_cost_per_token": 6.5e-07, + "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference", + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true }, - "together_ai/Qwen/Qwen2.5-Coder-32B-Instruct": { - "deprecation_date": "2025-11-13", - "input_cost_per_token": 8e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 16384, - "max_tokens": 16384, + "wandb/google/gemma-4-26B-A4B-it": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "wandb", + "max_input_tokens": 262000, + "max_output_tokens": 262144, "mode": "chat", - "output_cost_per_token": 8e-07, - "source": "https://api.together.ai/v1/models" + "output_cost_per_token": 3e-07, + "source": "https://wandb.ai/site/pricing/tokens/", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true }, - "together_ai/Qwen/Qwen2.5-VL-72B-Instruct": { - "deprecation_date": "2026-01-05", - "input_cost_per_token": 1.95e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 32768, - "max_tokens": 32768, + "wandb/zai-org/GLM-5.3-Flash": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 1.2e-07, + "litellm_provider": "wandb", + "max_input_tokens": 1049000, "mode": "chat", - "output_cost_per_token": 8e-06, - "source": "https://api.together.ai/v1/models" + "output_cost_per_token": 3.8e-07, + "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { - "deprecation_date": "2026-06-04", - "input_cost_per_token": 2e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "max_tokens": 262144, + "moonshotai.kimi-k3": { + "supports_regex_lookaround": false, + "cache_creation_input_token_cost": 4.125e-06, + "cache_creation_input_token_cost_flex": 2.0625e-06, + "cache_creation_input_token_cost_priority": 7.21875e-06, + "cache_read_input_token_cost": 3.3e-07, + "cache_read_input_token_cost_flex": 1.65e-07, + "cache_read_input_token_cost_priority": 5.775e-07, + "input_cost_per_token": 3.3e-06, + "input_cost_per_token_flex": 1.65e-06, + "input_cost_per_token_priority": 5.775e-06, + "litellm_provider": "bedrock_converse", + "token_count_framing": 64, + "token_count_tokenizer": "kimi_k3", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://api.together.ai/v1/models" + "output_cost_per_token": 1.65e-05, + "output_cost_per_token_flex": 8.25e-06, + "output_cost_per_token_priority": 2.8875e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_prompt_cache_breakpoint": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, - "together_ai/Qwen/Qwen3-Coder-Next-FP8": { - "deprecation_date": "2026-05-14", - "input_cost_per_token": 5e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "max_tokens": 262144, + "global.moonshotai.kimi-k3": { + "supports_regex_lookaround": false, + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_flex": 1.875e-06, + "cache_creation_input_token_cost_priority": 6.5625e-06, + "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_flex": 1.5e-07, + "cache_read_input_token_cost_priority": 5.25e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_flex": 1.5e-06, + "input_cost_per_token_priority": 5.25e-06, + "litellm_provider": "bedrock_converse", + "token_count_framing": 64, + "token_count_tokenizer": "kimi_k3", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://api.together.ai/v1/models" + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_flex": 7.5e-06, + "output_cost_per_token_priority": 2.625e-05, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_prompt_cache_breakpoint": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, - "together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct": { - "deprecation_date": "2026-04-02", - "input_cost_per_token": 1.5e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://api.together.ai/v1/models" + "bedrock/kimi-latest": { + "alias_of": "global.moonshotai.kimi-k3" }, - "together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking": { - "deprecation_date": "2026-02-25", - "input_cost_per_token": 1.5e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "max_tokens": 262144, + "us.moonshotai.kimi-k3": { + "supports_regex_lookaround": false, + "cache_creation_input_token_cost": 4.125e-06, + "cache_creation_input_token_cost_flex": 2.0625e-06, + "cache_creation_input_token_cost_priority": 7.21875e-06, + "cache_read_input_token_cost": 3.3e-07, + "cache_read_input_token_cost_flex": 1.65e-07, + "cache_read_input_token_cost_priority": 5.775e-07, + "input_cost_per_token": 3.3e-06, + "input_cost_per_token_flex": 1.65e-06, + "input_cost_per_token_priority": 5.775e-06, + "litellm_provider": "bedrock_converse", + "token_count_framing": 64, + "token_count_tokenizer": "kimi_k3", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://api.together.ai/v1/models" + "output_cost_per_token": 1.65e-05, + "output_cost_per_token_flex": 8.25e-06, + "output_cost_per_token_priority": 2.8875e-05, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_prompt_cache_breakpoint": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, - "together_ai/Qwen/Qwen3-VL-32B-Instruct": { - "deprecation_date": "2026-02-25", - "input_cost_per_token": 5e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "max_tokens": 262144, + "xiaomi_mimo/mimo-v2.6-pro": { + "cache_read_input_token_cost": 3.6e-09, + "input_cost_per_token": 4.35e-07, + "litellm_provider": "xiaomi_mimo", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://api.together.ai/v1/models" + "output_cost_per_token": 8.7e-07, + "source": "https://platform.xiaomimimo.com/static/docs/price/pay-as-you-go.md", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true }, - "together_ai/Qwen/Qwen3-VL-8B-Instruct": { - "deprecation_date": "2026-04-16", - "input_cost_per_token": 1.8e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "max_tokens": 262144, + "xiaomi_mimo/mimo-v2.6-flash": { + "cache_read_input_token_cost": 2.8e-09, + "input_cost_per_token": 1.4e-07, + "litellm_provider": "xiaomi_mimo", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 6.8e-07, - "source": "https://api.together.ai/v1/models" + "output_cost_per_token": 2.8e-07, + "source": "https://platform.xiaomimimo.com/static/docs/price/pay-as-you-go.md", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true }, - "together_ai/Qwen/Qwen3.5-397B-A17B": { - "cache_read_input_token_cost": 3.5e-07, - "deprecation_date": "2026-06-29", - "input_cost_per_token": 6e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "max_tokens": 262144, + "xai/grok-4.20-0309": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 3.6e-06, - "source": "https://api.together.ai/v1/models" - }, - "together_ai/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { - "deprecation_date": "2025-12-23", - "input_cost_per_token": 2e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://api.together.ai/v1/models" - }, - "together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 1.8e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.8e-07, - "source": "https://api.together.ai/v1/models" + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_prompt_caching": true, + "supports_response_schema": true }, - "together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": { - "deprecation_date": "2025-11-13", - "input_cost_per_token": 1.6e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 131072, - "max_tokens": 131072, + "xai/grok-4.20-beta": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 1.6e-06, - "source": "https://api.together.ai/v1/models" + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_prompt_caching": true, + "supports_response_schema": true }, - "together_ai/deepseek-ai/DeepSeek-V3.1": { - "deprecation_date": "2026-05-14", - "input_cost_per_token": 6e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 131072, - "max_tokens": 131072, + "xai/grok-4.20-beta-0309": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 1.7e-06, - "source": "https://api.together.ai/v1/models" + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_prompt_caching": true, + "supports_response_schema": true }, - "together_ai/deepseek-ai/deepseek-coder-33b-instruct": { - "deprecation_date": "2024-08-22", - "input_cost_per_token": 8e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 16384, - "max_tokens": 16384, + "xai/grok-4.20-beta-latest": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 8e-07, - "source": "https://api.together.ai/v1/models" + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_prompt_caching": true, + "supports_response_schema": true }, - "together_ai/google/gemma-2-27b-it": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 8e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 8192, - "max_tokens": 8192, + "xai/grok-4.20-beta-latest-non-reasoning": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 8e-07, - "source": "https://api.together.ai/v1/models" + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_response_schema": true }, - "together_ai/google/gemma-4-31B-it": { - "deprecation_date": "2026-09-15", - "input_cost_per_token": 3.9e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "max_tokens": 262144, + "xai/grok-4.20-beta-latest-reasoning": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 9.7e-07, - "source": "https://api.together.ai/v1/models" + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_prompt_caching": true, + "supports_response_schema": true }, - "together_ai/meta-llama/Llama-3-8b-chat-hf": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 2e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 8192, - "max_tokens": 8192, + "xai/grok-4.20-beta-non-reasoning": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://api.together.ai/v1/models" + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_response_schema": true }, - "together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct": { - "deprecation_date": "2026-02-06", - "input_cost_per_token": 1.8e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 1048576, - "max_tokens": 1048576, + "xai/grok-4.20-beta-reasoning": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 5.9e-07, - "source": "https://api.together.ai/v1/models" + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_prompt_caching": true, + "supports_response_schema": true }, - "together_ai/meta-llama/Meta-Llama-3-70B-Instruct-Turbo": { - "deprecation_date": "2025-12-23", - "input_cost_per_token": 8.8e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 8192, - "max_tokens": 8192, + "xai/grok-4.20-experimental-beta-0304": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 8.8e-07, - "source": "https://api.together.ai/v1/models" + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_prompt_caching": true, + "supports_response_schema": true }, - "together_ai/meta-llama/Meta-Llama-3-8B-Instruct": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 2e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 8192, - "max_tokens": 8192, + "xai/grok-4.20-experimental-beta-0304-non-reasoning": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://api.together.ai/v1/models" + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_response_schema": true }, - "together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { - "deprecation_date": "2026-02-25", - "input_cost_per_token": 8.8e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 131072, - "max_tokens": 131072, + "xai/grok-4.20-experimental-beta-0304-reasoning": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 8.8e-07, - "source": "https://api.together.ai/v1/models" + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_prompt_caching": true, + "supports_response_schema": true }, - "together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { - "deprecation_date": "2026-03-06", - "input_cost_per_token": 1.8e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 131072, - "max_tokens": 131072, + "xai/grok-4.20-experimental-beta-latest": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 1.8e-07, - "source": "https://api.together.ai/v1/models" + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_prompt_caching": true, + "supports_response_schema": true }, - "together_ai/mistralai/Mistral-7B-Instruct-v0.1": { - "deprecation_date": "2025-11-13", - "input_cost_per_token": 2e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 32768, - "max_tokens": 32768, + "xai/grok-4.20-experimental-beta-non-reasoning-latest": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://api.together.ai/v1/models" + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_response_schema": true }, - "together_ai/mistralai/Mistral-Small-24B-Instruct-2501": { - "deprecation_date": "2026-04-02", - "input_cost_per_token": 1e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 32768, - "max_tokens": 32768, + "xai/grok-4.20-experimental-beta-reasoning-latest": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://api.together.ai/v1/models" + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_prompt_caching": true, + "supports_response_schema": true }, - "together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1": { - "deprecation_date": "2026-04-16", - "input_cost_per_token": 6e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://api.together.ai/v1/models" + "xai/grok-4.20-multi-agent-beta-latest": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "mode": "responses", + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_response_schema": true, + "supported_endpoints": [ + "/v1/responses" + ] }, - "together_ai/moonshotai/Kimi-K2.6": { + "xai/grok-4.20-multi-agent-experimental-beta-0304": { "cache_read_input_token_cost": 2e-07, - "deprecation_date": "2026-08-19", - "input_cost_per_token": 1.2e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 4.5e-06, - "source": "https://api.together.ai/v1/models" + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "mode": "responses", + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_response_schema": true, + "supported_endpoints": [ + "/v1/responses" + ] }, - "together_ai/moonshotai/Kimi-K2.7-Code": { - "cache_read_input_token_cost": 1.9e-07, - "deprecation_date": "2026-08-27", - "input_cost_per_token": 9.5e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 4e-06, - "source": "https://api.together.ai/v1/models" + "xai/grok-4.20-multi-agent-experimental-beta-latest": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "mode": "responses", + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_response_schema": true, + "supported_endpoints": [ + "/v1/responses" + ] }, - "together_ai/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 8.8e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 32768, - "max_tokens": 32768, + "xai/grok-4.20-non-reasoning-gv2": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 8.8e-07, - "source": "https://api.together.ai/v1/models" + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_response_schema": true }, - "together_ai/nvidia/nemotron-3-ultra-550b-a55b": { + "xai/grok-4.20-reasoning-gv2": { "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 6e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 512288, - "max_tokens": 512288, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 3.6e-06, - "source": "https://api.together.ai/v1/models" + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_prompt_caching": true, + "supports_response_schema": true }, - "together_ai/openai/gpt-oss-20b": { - "deprecation_date": "2026-09-15", - "input_cost_per_token": 5e-08, - "litellm_provider": "together_ai", - "max_input_tokens": 131072, - "max_tokens": 131072, + "baseten/deepseek-ai/DeepSeek-V4.1-Flash": { + "cache_read_input_token_cost": 7e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://api.together.ai/v1/models" + "output_cost_per_token": 1.2e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "together_ai/zai-org/GLM-4.5-Air-FP8": { - "deprecation_date": "2026-04-02", - "input_cost_per_token": 2e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 131072, - "max_tokens": 131072, + "baseten/moonshotai/Kimi-K2.6": { + "deprecation_date": "2026-10-16", + "cache_read_input_token_cost": 1.6e-07, + "input_cost_per_token": 9.5e-07, + "litellm_provider": "baseten", + "max_input_tokens": 262000, + "max_output_tokens": 262000, "mode": "chat", - "output_cost_per_token": 1.1e-06, - "source": "https://api.together.ai/v1/models" + "output_cost_per_token": 4e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "together_ai/zai-org/GLM-4.7": { - "deprecation_date": "2026-04-02", - "input_cost_per_token": 4.5e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 202752, - "max_tokens": 202752, + "baseten/moonshotai/Kimi-K2.7-Code": { + "deprecation_date": "2026-10-16", + "cache_read_input_token_cost": 1.6e-07, + "input_cost_per_token": 9.5e-07, + "litellm_provider": "baseten", + "max_input_tokens": 262000, + "max_output_tokens": 262000, "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://api.together.ai/v1/models" + "output_cost_per_token": 4e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "together_ai/zai-org/GLM-5": { - "deprecation_date": "2026-06-22", - "input_cost_per_token": 1e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 202752, - "max_tokens": 202752, + "baseten/moonshotai/Kimi-K3": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, "mode": "chat", - "output_cost_per_token": 3.2e-06, - "source": "https://api.together.ai/v1/models" + "output_cost_per_token": 1.5e-05, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "together_ai/zai-org/GLM-5.1": { - "cache_read_input_token_cost": 2.6e-07, - "deprecation_date": "2026-07-10", - "input_cost_per_token": 1.4e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 202752, - "max_tokens": 202752, + "baseten/kimi-latest": { + "alias_of": "baseten/moonshotai/Kimi-K3" + }, + "baseten/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": { + "cache_read_input_token_cost": 1.2e-07, + "input_cost_per_token": 6e-07, + "litellm_provider": "baseten", + "max_input_tokens": 202800, + "max_output_tokens": 202800, "mode": "chat", - "output_cost_per_token": 4.4e-06, - "source": "https://api.together.ai/v1/models" + "output_cost_per_token": 2.4e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false }, - "azure/eu/codex-mini": { - "deprecation_date": "2026-11-15", - "cache_read_input_token_cost": 4.13e-07, - "input_cost_per_token": 1.65e-06, - "litellm_provider": "azure", + "baseten/thinkingmachines/inkling": { + "deprecation_date": "2026-10-16", + "cache_read_input_token_cost": 1.7e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 32768, "mode": "chat", - "output_cost_per_token": 6.6e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "output_cost_per_token": 4.05e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "azure/eu/computer-use-preview": { - "input_cost_per_token": 3.3e-06, - "litellm_provider": "azure", + "baseten/thinkingmachines/inkling-small": { + "deprecation_date": "2026-10-16", + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 5e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 32768, "mode": "chat", - "output_cost_per_token": 1.32e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "output_cost_per_token": 1.2e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "azure/eu/gpt-4.1": { - "deprecation_date": "2027-04-14", - "cache_read_input_token_cost": 5.5e-07, - "cache_read_input_token_cost_priority": 9.63e-07, - "input_cost_per_token": 2.2e-06, - "input_cost_per_token_batches": 1.1e-06, - "input_cost_per_token_priority": 3.85e-06, - "litellm_provider": "azure", + "baseten/zai-org/GLM-5.2": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, "mode": "chat", - "output_cost_per_token": 8.8e-06, - "output_cost_per_token_batches": 4.4e-06, - "output_cost_per_token_priority": 1.54e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "output_cost_per_token": 4.4e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "azure/eu/gpt-4.1-mini": { - "deprecation_date": "2027-04-14", - "cache_read_input_token_cost": 1.1e-07, - "cache_read_input_token_cost_priority": 1.93e-07, - "input_cost_per_token": 4.4e-07, - "input_cost_per_token_batches": 2.2e-07, - "input_cost_per_token_priority": 7.7e-07, - "litellm_provider": "azure", + "baseten/zai-org/GLM-5.3-Flash": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 1.76e-06, - "output_cost_per_token_batches": 8.8e-07, - "output_cost_per_token_priority": 3.08e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "output_cost_per_token": 5e-07, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "azure/eu/gpt-4.1-nano": { - "deprecation_date": "2027-04-14", + "baseten/glm-flash-latest": { + "alias_of": "baseten/zai-org/GLM-5.3-Flash" + }, + "baseten/deepseek-ai/DeepSeek-V4-Flash-0731": { "cache_read_input_token_cost": 2.8e-08, - "input_cost_per_token": 1.1e-07, - "input_cost_per_token_batches": 5.5e-08, - "litellm_provider": "azure", + "input_cost_per_token": 1.3e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, "mode": "chat", - "output_cost_per_token": 4.4e-07, - "output_cost_per_token_batches": 2.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "output_cost_per_token": 2.6e-07, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false }, - "azure/eu/gpt-4o-2024-05-13": { - "deprecation_date": "2026-12-09", - "input_cost_per_token": 5.5e-06, - "input_cost_per_token_batches": 2.75e-06, - "litellm_provider": "azure", - "mode": "chat", - "output_cost_per_token": 1.65e-05, - "output_cost_per_token_batches": 8.25e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "baseten/deepseek-flash-latest": { + "alias_of": "baseten/deepseek-ai/DeepSeek-V4-Flash-0731" }, - "azure/eu/gpt-5": { - "deprecation_date": "2027-02-09", - "cache_read_input_token_cost": 1.375e-07, - "cache_read_input_token_cost_batches": 6.875e-08, - "cache_read_input_token_cost_priority": 2.75e-07, - "input_cost_per_token": 1.375e-06, - "input_cost_per_token_batches": 6.875e-07, - "input_cost_per_token_priority": 2.75e-06, - "litellm_provider": "azure", + "baseten/deepseek-ai/DeepSeek-V4-Pro": { + "deprecation_date": "2026-10-16", + "cache_read_input_token_cost": 1.45e-07, + "input_cost_per_token": 1.74e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, "mode": "chat", - "output_cost_per_token": 1.1e-05, - "output_cost_per_token_batches": 5.5e-06, - "output_cost_per_token_priority": 2.2e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "output_cost_per_token": 3.48e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false }, - "azure/eu/gpt-5-codex": { - "deprecation_date": "2027-03-17", - "cache_read_input_token_cost": 1.38e-07, - "input_cost_per_token": 1.375e-06, - "litellm_provider": "azure", + "baseten/deepseek-ai/DeepSeek-V4-Pro-0813": { + "cache_read_input_token_cost": 1.32e-07, + "input_cost_per_token": 1.32e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, "mode": "chat", - "output_cost_per_token": 1.1e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "output_cost_per_token": 3.96e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false }, - "azure/eu/gpt-5-mini": { - "deprecation_date": "2027-02-09", - "cache_read_input_token_cost": 2.75e-08, - "cache_read_input_token_cost_batches": 1.375e-08, - "cache_read_input_token_cost_priority": 4.95e-08, - "input_cost_per_token": 2.75e-07, - "input_cost_per_token_batches": 1.375e-07, - "input_cost_per_token_priority": 4.95e-07, - "litellm_provider": "azure", - "mode": "chat", - "output_cost_per_token": 2.2e-06, - "output_cost_per_token_batches": 1.1e-06, - "output_cost_per_token_priority": 3.96e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "baseten/deepseek-pro-latest": { + "alias_of": "baseten/deepseek-ai/DeepSeek-V4-Pro-0813" }, - "azure/eu/gpt-5-nano": { - "deprecation_date": "2027-02-09", - "cache_read_input_token_cost": 5.5e-09, - "cache_read_input_token_cost_batches": 2.75e-09, - "input_cost_per_token": 5.5e-08, - "input_cost_per_token_batches": 2.75e-08, - "litellm_provider": "azure", + "baseten/zai-org/GLM-5.2-Fast": { + "cache_read_input_token_cost": 2.1e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, "mode": "chat", - "output_cost_per_token": 4.4e-07, - "output_cost_per_token_batches": 2.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "output_cost_per_token": 6.6e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "azure/eu/gpt-5-pro": { - "deprecation_date": "2027-04-07", - "input_cost_per_token": 1.65e-05, - "input_cost_per_token_batches": 8.25e-06, - "litellm_provider": "azure", + "xai/grok-code-fast": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_200k_tokens": 2e-06, + "litellm_provider": "xai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, "mode": "chat", - "output_cost_per_token": 0.000132, - "output_cost_per_token_batches": 6.6e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "output_cost_per_token": 2e-06, + "output_cost_per_token_above_200k_tokens": 4e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "azure/eu/gpt-5.1-codex-max": { - "deprecation_date": "2027-05-18", - "cache_read_input_token_cost": 1.375e-07, - "input_cost_per_token": 1.375e-06, - "litellm_provider": "azure", + "xai/grok-code-fast-1": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "deprecation_date": "2026-05-15", + "deprecation_source": "https://docs.x.ai/developers/migration/may-15-retirement", + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_200k_tokens": 2e-06, + "litellm_provider": "xai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, "mode": "chat", - "output_cost_per_token": 1.1e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "output_cost_per_token": 2e-06, + "output_cost_per_token_above_200k_tokens": 4e-06, + "source": "https://api.x.ai/v1/language-models", + "successor_model": "xai/grok-build-0.1", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "azure/eu/gpt-5.2": { - "deprecation_date": "2027-06-08", - "cache_read_input_token_cost": 1.925e-07, - "cache_read_input_token_cost_batches": 9.625e-08, - "cache_read_input_token_cost_priority": 3.85e-07, - "input_cost_per_token": 1.925e-06, - "input_cost_per_token_batches": 9.625e-07, - "input_cost_per_token_priority": 3.85e-06, - "litellm_provider": "azure", + "xai/grok-code-fast-1-0825": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_200k_tokens": 2e-06, + "litellm_provider": "xai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, "mode": "chat", - "output_cost_per_token": 1.54e-05, - "output_cost_per_token_batches": 7.7e-06, - "output_cost_per_token_priority": 3.08e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "output_cost_per_token": 2e-06, + "output_cost_per_token_above_200k_tokens": 4e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "azure/eu/gpt-5.2-codex": { - "deprecation_date": "2027-07-13", - "cache_read_input_token_cost": 1.925e-07, - "input_cost_per_token": 1.925e-06, - "litellm_provider": "azure", + "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro": { + "cache_read_input_token_cost": 6e-07, + "cache_read_input_token_cost_priority": 6e-07, + "deprecation_date": "2026-08-27", + "input_cost_per_token": 1.2e-06, + "input_cost_per_token_priority": 1.2e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 1.54e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_priority": 1.2e-06, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false }, - "azure/eu/gpt-5.2-pro": { - "input_cost_per_token": 2.31e-05, - "input_cost_per_token_batches": 1.155e-05, - "litellm_provider": "azure", + "fireworks_ai/accounts/fireworks/models/minimax-m2p7": { + "cache_read_input_token_cost_priority": 6e-07, + "deprecation_date": "2026-08-27", + "input_cost_per_token_priority": 1.2e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 196608, + "max_output_tokens": 196608, "mode": "chat", - "output_cost_per_token": 0.0001848, - "output_cost_per_token_batches": 9.24e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "output_cost_per_token_priority": 1.2e-06, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "azure/eu/gpt-5.3-codex": { - "deprecation_date": "2027-08-24", - "cache_read_input_token_cost": 1.925e-07, - "cache_read_input_token_cost_priority": 3.85e-07, - "input_cost_per_token": 1.925e-06, - "input_cost_per_token_priority": 3.85e-06, - "litellm_provider": "azure", - "mode": "chat", - "output_cost_per_token": 1.54e-05, - "output_cost_per_token_priority": 3.08e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "fireworks_ai/accounts/fireworks/routers/rune": { + "cache_read_input_token_cost": 8.4e-09, + "input_cost_per_token": 4.2e-08, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 262144, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.fireworks.ai" }, - "azure/eu/gpt-5.4-mini": { - "deprecation_date": "2027-09-21", - "cache_read_input_token_cost": 8.25e-08, - "cache_read_input_token_cost_batches": 4.125e-08, - "cache_read_input_token_cost_priority": 1.65e-07, - "input_cost_per_token": 8.25e-07, - "input_cost_per_token_batches": 4.125e-07, - "input_cost_per_token_priority": 1.65e-06, - "litellm_provider": "azure", + "fireworks_ai/accounts/fireworks/models/ember-1": { + "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_priority": 3.75e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_priority": 3.75e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 4.95e-06, - "output_cost_per_token_batches": 2.475e-06, - "output_cost_per_token_priority": 9.9e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_priority": 1.875e-05, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "azure/eu/gpt-5.4-nano": { - "deprecation_date": "2027-09-21", - "cache_read_input_token_cost": 2.2e-08, - "cache_read_input_token_cost_batches": 1.1e-08, - "input_cost_per_token": 2.2e-07, - "input_cost_per_token_batches": 1.1e-07, - "litellm_provider": "azure", + "vertex_ai/gemini-2.0-flash": { + "deprecation_date": "2026-06-01", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "successor_model": "vertex_ai/gemini-3.5-flash-lite", + "input_cost_per_audio_token": 1e-06, + "input_cost_per_audio_token_batches": 5e-07, + "input_cost_per_character": 3.75e-08, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "litellm_provider": "vertex_ai", "mode": "chat", - "output_cost_per_token": 1.375e-06, - "output_cost_per_token_batches": 6.875e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, - "azure/eu/gpt-5.4-pro": { - "deprecation_date": "2027-09-07", - "input_cost_per_token": 3.3e-05, - "input_cost_per_token_above_272k_tokens": 6.6e-05, - "input_cost_per_token_above_272k_tokens_batches": 3.3e-05, - "input_cost_per_token_batches": 1.65e-05, - "litellm_provider": "azure", + "vertex_ai/gemini-2.0-flash-lite": { + "deprecation_date": "2026-06-01", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "successor_model": "vertex_ai/gemini-3.5-flash-lite", + "input_cost_per_audio_token": 7.5e-08, + "input_cost_per_audio_token_batches": 3.75e-08, + "input_cost_per_character": 1.875e-08, + "input_cost_per_token": 7.5e-08, + "input_cost_per_token_batches": 3.75e-08, + "litellm_provider": "vertex_ai", "mode": "chat", - "output_cost_per_token": 0.000198, - "output_cost_per_token_above_272k_tokens": 0.000297, - "output_cost_per_token_above_272k_tokens_batches": 0.0001485, - "output_cost_per_token_batches": 9.9e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, - "azure/eu/gpt-6-astra": { - "deprecation_date": "2028-01-11", - "cache_creation_input_token_cost": 1.5e-05, - "cache_creation_input_token_cost_above_272k_tokens": 3e-05, - "cache_read_input_token_cost": 1.2e-06, - "cache_read_input_token_cost_above_272k_tokens": 2.4e-06, - "input_cost_per_token": 1.2e-05, - "input_cost_per_token_above_272k_tokens": 2.4e-05, - "litellm_provider": "azure", + "output_cost_per_token": 3e-07, + "output_cost_per_token_batches": 1.5e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/zai-org/glm-5.2-maas": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "vertex_ai-zai_models", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, "mode": "chat", - "output_cost_per_token": 6e-05, - "output_cost_per_token_above_272k_tokens": 9e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'swedencentral'%20and%20priceType%20eq%20'Consumption'", - "supports_reasoning": true + "output_cost_per_token": 4.4e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_regions": ["global"], + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "azure/eu/gpt-6-luna": { - "deprecation_date": "2028-03-11", - "cache_creation_input_token_cost": 1.5e-07, - "cache_creation_input_token_cost_above_272k_tokens": 3e-07, - "cache_read_input_token_cost": 1.2e-08, - "cache_read_input_token_cost_above_272k_tokens": 2.4e-08, - "input_cost_per_token": 1.2e-07, - "input_cost_per_token_above_272k_tokens": 2.4e-07, - "litellm_provider": "azure", - "max_input_tokens": 922000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "vertex_ai/meta/llama-3.3-70b-instruct-maas": { + "deprecation_date": "2026-10-21", + "input_cost_per_token": 7.2e-07, + "input_cost_per_token_batches": 3.6e-07, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 128000, + "max_output_tokens": 8192, "mode": "chat", - "output_cost_per_token": 6e-07, - "output_cost_per_token_above_272k_tokens": 9e-07, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" + "output_cost_per_token": 7.2e-07, + "output_cost_per_token_batches": 3.6e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_modalities": [ + "text" ], + "supported_output_modalities": [ + "text", + "code" + ], + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/veo-3.0-generate-001": { + "deprecation_date": "2026-06-30", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "successor_model": "vertex_ai/veo-3.1-generate-001", + "litellm_provider": "vertex_ai-video-models", + "max_input_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.4, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#veo", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ - "text" + "video" + ] + }, + "vertex_ai/veo-3.0-fast-generate-001": { + "deprecation_date": "2026-06-30", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "successor_model": "vertex_ai/veo-3.1-fast-generate-001", + "litellm_provider": "vertex_ai-video-models", + "max_input_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_1080p": 0.12, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#veo", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "vertex_ai/veo-2.0-generate-001": { + "deprecation_date": "2026-06-30", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "successor_model": "vertex_ai/veo-3.1-generate-001", + "litellm_provider": "vertex_ai-video-models", + "max_input_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.5, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#veo", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "vertex_ai/virtual-try-on-001": { + "deprecation_date": "2027-03-15", + "litellm_provider": "vertex_ai", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_modalities": [ + "image" ], + "supported_output_modalities": [ + "image" + ] + }, + "vertex_ai/gemini-2.5-flash-tts": { + "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "litellm_provider": "vertex_ai", + "mode": "audio_speech", + "output_cost_per_audio_token": 1e-05, + "output_cost_per_token": 1e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/gemini-2.5-pro-tts": { + "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, + "litellm_provider": "vertex_ai", + "mode": "audio_speech", + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 2e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "anthropic.claude-mythos-5-1": { + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, - "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": false, - "supports_native_streaming": true, - "supports_none_reasoning_effort": true, - "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost": 1.25e-05, + "cache_read_input_token_cost": 2.5e-07, + "output_cost_per_token": 5e-05, + "input_cost_per_token": 1e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, - "azure/eu/gpt-6-sol": { - "deprecation_date": "2028-03-11", - "cache_creation_input_token_cost": 3e-06, - "cache_creation_input_token_cost_above_272k_tokens": 6e-06, - "cache_read_input_token_cost": 2.4e-07, - "cache_read_input_token_cost_above_272k_tokens": 4.8e-07, - "input_cost_per_token": 2.4e-06, - "input_cost_per_token_above_272k_tokens": 4.8e-06, - "litellm_provider": "azure", - "max_input_tokens": 922000, + "global.anthropic.claude-mythos-5-1": { + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.2e-05, - "output_cost_per_token_above_272k_tokens": 1.8e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, - "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": false, - "supports_native_streaming": true, - "supports_none_reasoning_effort": true, - "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "supports_xhigh_reasoning_effort": true - }, - "azure/eu/o1-mini": { - "cache_read_input_token_cost": 6.05e-07, - "input_cost_per_token": 1.21e-06, - "input_cost_per_token_batches": 6.05e-07, - "litellm_provider": "azure", - "mode": "chat", - "output_cost_per_token": 4.84e-06, - "output_cost_per_token_batches": 2.42e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "cache_read_input_token_cost": 2.5e-07, + "cache_creation_input_token_cost": 1.25e-05, + "input_cost_per_token": 1e-05, + "output_cost_per_token": 5e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, - "azure/eu/o3-2025-04-16": { - "deprecation_date": "2026-11-19", - "cache_read_input_token_cost": 5.5e-07, - "input_cost_per_token": 2.2e-06, - "input_cost_per_token_batches": 1.1e-06, - "litellm_provider": "azure", + "us.anthropic.claude-mythos-5-1": { + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 8.8e-06, - "output_cost_per_token_batches": 4.4e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, - "azure/eu/o3-deep-research": { - "deprecation_date": "2026-11-19", - "cache_read_input_token_cost": 2.75e-06, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, "input_cost_per_token": 1.1e-05, - "litellm_provider": "azure", - "mode": "chat", - "output_cost_per_token": 4.4e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "output_cost_per_token": 5.5e-05, + "cache_read_input_token_cost": 2.75e-07, + "cache_creation_input_token_cost": 1.375e-05, + "cache_creation_input_token_cost_above_1hr": 2.2e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, - "azure/eu/o4-mini-2025-04-16": { - "deprecation_date": "2026-11-19", - "cache_read_input_token_cost": 3.03e-07, - "input_cost_per_token": 1.21e-06, - "input_cost_per_token_batches": 6.05e-07, - "litellm_provider": "azure", + "us.anthropic.claude-mythos-5": { + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 4.84e-06, - "output_cost_per_token_batches": 2.42e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, - "azure/eu/text-embedding-3-large": { - "deprecation_date": "2028-02-09", - "input_cost_per_token": 1.43e-07, - "litellm_provider": "azure", - "mode": "embedding", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, - "azure/eu/text-embedding-3-small": { - "deprecation_date": "2028-02-09", - "input_cost_per_token": 2.2e-08, - "litellm_provider": "azure", - "mode": "embedding", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, - "azure/eu/text-embedding-ada-002": { - "deprecation_date": "2028-02-09", - "input_cost_per_token": 1.1e-07, - "litellm_provider": "azure", - "mode": "embedding", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, - "gemini/gemini-3.8-live": { - "input_cost_per_audio_token": 3e-06, - "input_cost_per_image_token": 1e-06, - "input_cost_per_token": 7.5e-07, - "input_cost_per_video_token": 1e-06, - "litellm_provider": "gemini", - "max_input_tokens": 131072, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "realtime", - "output_cost_per_audio_token": 1.2e-05, - "output_cost_per_token": 4.5e-06, - "source": "https://ai.google.dev/gemini-api/docs/pricing", - "supports_audio_input": true, - "tpm": 250000, - "rpm": 10, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, - "supports_response_schema": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "cache_creation_input_token_cost": 1.375e-05, + "input_cost_per_token": 1.1e-05, + "cache_read_input_token_cost": 1.1e-06, + "output_cost_per_token": 5.5e-05, + "cache_creation_input_token_cost_above_1hr": 2.2e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-mythos-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, - "gemini/gemini-3.8-live-extended-thinking": { - "input_cost_per_audio_token": 3e-06, - "input_cost_per_image_token": 1e-06, - "input_cost_per_token": 7.5e-07, - "input_cost_per_video_token": 1e-06, - "litellm_provider": "gemini", - "max_input_tokens": 131072, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "realtime", - "output_cost_per_audio_token": 1.2e-05, - "output_cost_per_token": 4.5e-06, - "source": "https://ai.google.dev/gemini-api/docs/pricing", - "supports_audio_input": true, - "tpm": 250000, - "rpm": 10, + "apac.anthropic.claude-fable-5": { + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, - "supports_response_schema": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "output_cost_per_token": 5.5e-05, + "cache_creation_input_token_cost": 1.375e-05, + "cache_read_input_token_cost": 1.1e-06, + "input_cost_per_token": 1.1e-05, + "cache_creation_input_token_cost_above_1hr": 2.2e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, - "azure/us/codex-mini": { - "deprecation_date": "2026-11-15", - "cache_read_input_token_cost": 4.13e-07, - "input_cost_per_token": 1.65e-06, - "litellm_provider": "azure", + "au.anthropic.claude-fable-5": { + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 6.6e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "output_cost_per_token": 5.5e-05, + "cache_creation_input_token_cost": 1.375e-05, + "cache_read_input_token_cost": 1.1e-06, + "input_cost_per_token": 1.1e-05, + "cache_creation_input_token_cost_above_1hr": 2.2e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, - "azure/us/computer-use-preview": { - "input_cost_per_token": 3.3e-06, - "litellm_provider": "azure", + "apac.anthropic.claude-opus-4-7": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.32e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, - "azure/us/gpt-4.1": { - "deprecation_date": "2027-04-14", + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 2048, + "output_cost_per_token": 2.75e-05, + "cache_creation_input_token_cost": 6.875e-06, + "input_cost_per_token": 5.5e-06, + "cache_creation_input_token_cost_above_1hr": 1.1e-05, "cache_read_input_token_cost": 5.5e-07, - "cache_read_input_token_cost_priority": 9.63e-07, - "input_cost_per_token": 2.2e-06, - "input_cost_per_token_batches": 1.1e-06, - "input_cost_per_token_priority": 3.85e-06, - "litellm_provider": "azure", - "mode": "chat", - "output_cost_per_token": 8.8e-06, - "output_cost_per_token_batches": 4.4e-06, - "output_cost_per_token_priority": 1.54e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-4-7", + "litellm_provider": "bedrock_mantle", + "region": "ap-northeast-1" + } }, - "azure/us/gpt-4.1-mini": { - "deprecation_date": "2027-04-14", - "cache_read_input_token_cost": 1.1e-07, - "cache_read_input_token_cost_priority": 1.93e-07, - "input_cost_per_token": 4.4e-07, - "input_cost_per_token_batches": 2.2e-07, - "input_cost_per_token_priority": 7.7e-07, - "litellm_provider": "azure", + "apac.anthropic.claude-opus-4-8": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.76e-06, - "output_cost_per_token_batches": 8.8e-07, - "output_cost_per_token_priority": 3.08e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, - "azure/us/gpt-4.1-nano": { - "deprecation_date": "2027-04-14", - "cache_read_input_token_cost": 2.8e-08, - "input_cost_per_token": 1.1e-07, - "input_cost_per_token_batches": 5.5e-08, - "litellm_provider": "azure", - "mode": "chat", - "output_cost_per_token": 4.4e-07, - "output_cost_per_token_batches": 2.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, - "azure/us/gpt-4o-2024-05-13": { - "deprecation_date": "2026-12-09", - "input_cost_per_token": 5.5e-06, - "input_cost_per_token_batches": 2.75e-06, - "litellm_provider": "azure", - "mode": "chat", - "output_cost_per_token": 1.65e-05, - "output_cost_per_token_batches": 8.25e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, - "azure/us/gpt-5": { - "deprecation_date": "2027-02-09", - "cache_read_input_token_cost": 1.375e-07, - "cache_read_input_token_cost_batches": 6.875e-08, - "cache_read_input_token_cost_priority": 2.75e-07, - "input_cost_per_token": 1.375e-06, - "input_cost_per_token_batches": 6.875e-07, - "input_cost_per_token_priority": 2.75e-06, - "litellm_provider": "azure", - "mode": "chat", - "output_cost_per_token": 1.1e-05, - "output_cost_per_token_batches": 5.5e-06, - "output_cost_per_token_priority": 2.2e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, - "azure/us/gpt-5-codex": { - "deprecation_date": "2027-03-17", - "cache_read_input_token_cost": 1.38e-07, - "input_cost_per_token": 1.375e-06, - "litellm_provider": "azure", - "mode": "chat", - "output_cost_per_token": 1.1e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, - "azure/us/gpt-5-mini": { - "deprecation_date": "2027-02-09", - "cache_read_input_token_cost": 2.75e-08, - "cache_read_input_token_cost_batches": 1.375e-08, - "cache_read_input_token_cost_priority": 4.95e-08, - "input_cost_per_token": 2.75e-07, - "input_cost_per_token_batches": 1.375e-07, - "input_cost_per_token_priority": 4.95e-07, - "litellm_provider": "azure", - "mode": "chat", - "output_cost_per_token": 2.2e-06, - "output_cost_per_token_batches": 1.1e-06, - "output_cost_per_token_priority": 3.96e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, - "azure/us/gpt-5-nano": { - "deprecation_date": "2027-02-09", - "cache_read_input_token_cost": 5.5e-09, - "cache_read_input_token_cost_batches": 2.75e-09, - "input_cost_per_token": 5.5e-08, - "input_cost_per_token_batches": 2.75e-08, - "litellm_provider": "azure", - "mode": "chat", - "output_cost_per_token": 4.4e-07, - "output_cost_per_token_batches": 2.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, - "azure/us/gpt-5-pro": { - "deprecation_date": "2027-04-07", - "input_cost_per_token": 1.65e-05, - "input_cost_per_token_batches": 8.25e-06, - "litellm_provider": "azure", - "mode": "chat", - "output_cost_per_token": 0.000132, - "output_cost_per_token_batches": 6.6e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, - "azure/us/gpt-5.1-codex-max": { - "deprecation_date": "2027-05-18", - "cache_read_input_token_cost": 1.375e-07, - "input_cost_per_token": 1.375e-06, - "litellm_provider": "azure", - "mode": "chat", - "output_cost_per_token": 1.1e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, - "azure/us/gpt-5.2": { - "deprecation_date": "2027-06-08", - "cache_read_input_token_cost": 1.925e-07, - "cache_read_input_token_cost_batches": 9.625e-08, - "cache_read_input_token_cost_priority": 3.85e-07, - "input_cost_per_token": 1.925e-06, - "input_cost_per_token_batches": 9.625e-07, - "input_cost_per_token_priority": 3.85e-06, - "litellm_provider": "azure", - "mode": "chat", - "output_cost_per_token": 1.54e-05, - "output_cost_per_token_batches": 7.7e-06, - "output_cost_per_token_priority": 3.08e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, - "azure/us/gpt-5.2-codex": { - "deprecation_date": "2027-07-13", - "cache_read_input_token_cost": 1.925e-07, - "input_cost_per_token": 1.925e-06, - "litellm_provider": "azure", - "mode": "chat", - "output_cost_per_token": 1.54e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, - "azure/us/gpt-5.2-pro": { - "input_cost_per_token": 2.31e-05, - "input_cost_per_token_batches": 1.155e-05, - "litellm_provider": "azure", - "mode": "chat", - "output_cost_per_token": 0.0001848, - "output_cost_per_token_batches": 9.24e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, - "azure/us/gpt-5.3-codex": { - "deprecation_date": "2027-08-24", - "cache_read_input_token_cost": 1.925e-07, - "cache_read_input_token_cost_priority": 3.85e-07, - "input_cost_per_token": 1.925e-06, - "input_cost_per_token_priority": 3.85e-06, - "litellm_provider": "azure", - "mode": "chat", - "output_cost_per_token": 1.54e-05, - "output_cost_per_token_priority": 3.08e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, - "azure/us/gpt-5.4-mini": { - "deprecation_date": "2027-09-21", - "cache_read_input_token_cost": 8.25e-08, - "cache_read_input_token_cost_batches": 4.125e-08, - "cache_read_input_token_cost_priority": 1.65e-07, - "input_cost_per_token": 8.25e-07, - "input_cost_per_token_batches": 4.125e-07, - "input_cost_per_token_priority": 1.65e-06, - "litellm_provider": "azure", - "mode": "chat", - "output_cost_per_token": 4.95e-06, - "output_cost_per_token_batches": 2.475e-06, - "output_cost_per_token_priority": 9.9e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, - "azure/us/gpt-5.4-nano": { - "deprecation_date": "2027-09-21", - "cache_read_input_token_cost": 2.2e-08, - "cache_read_input_token_cost_batches": 1.1e-08, - "input_cost_per_token": 2.2e-07, - "input_cost_per_token_batches": 1.1e-07, - "litellm_provider": "azure", - "mode": "chat", - "output_cost_per_token": 1.375e-06, - "output_cost_per_token_batches": 6.875e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, - "azure/us/gpt-5.4-pro": { - "deprecation_date": "2027-09-07", - "input_cost_per_token": 3.3e-05, - "input_cost_per_token_above_272k_tokens": 6.6e-05, - "input_cost_per_token_above_272k_tokens_batches": 3.3e-05, - "input_cost_per_token_batches": 1.65e-05, - "litellm_provider": "azure", - "mode": "chat", - "output_cost_per_token": 0.000198, - "output_cost_per_token_above_272k_tokens": 0.000297, - "output_cost_per_token_above_272k_tokens_batches": 0.0001485, - "output_cost_per_token_batches": 9.9e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, - "azure/us/o1-mini": { - "cache_read_input_token_cost": 6.05e-07, - "input_cost_per_token": 1.21e-06, - "input_cost_per_token_batches": 6.05e-07, - "litellm_provider": "azure", - "mode": "chat", - "output_cost_per_token": 4.84e-06, - "output_cost_per_token_batches": 2.42e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, - "azure/us/o3-deep-research": { - "deprecation_date": "2026-11-19", - "cache_read_input_token_cost": 2.75e-06, - "input_cost_per_token": 1.1e-05, - "litellm_provider": "azure", - "mode": "chat", - "output_cost_per_token": 4.4e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, - "azure/us/text-embedding-3-large": { - "deprecation_date": "2028-02-09", - "input_cost_per_token": 1.43e-07, - "litellm_provider": "azure", - "mode": "embedding", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, - "azure/us/text-embedding-3-small": { - "deprecation_date": "2028-02-09", - "input_cost_per_token": 2.2e-08, - "litellm_provider": "azure", - "mode": "embedding", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, - "azure/us/text-embedding-ada-002": { - "deprecation_date": "2028-02-09", - "input_cost_per_token": 1.1e-07, - "litellm_provider": "azure", - "mode": "embedding", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, - "azure/gpt-realtime-2": { - "cache_creation_input_audio_token_cost": 4e-07, - "cache_read_input_audio_token_cost": 4e-07, - "cache_read_input_token_cost": 4e-07, - "deprecation_date": "2026-10-31", - "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image_token": 5e-06, - "input_cost_per_token": 4e-06, - "litellm_provider": "azure", - "max_input_tokens": 32000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "realtime", - "output_cost_per_audio_token": 6.4e-05, - "output_cost_per_token": 2.4e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supported_endpoints": [ - "/v1/realtime" - ], - "supported_modalities": [ - "text", - "image", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_audio_input": true, - "supports_audio_output": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "azure/gpt-live-1": { - "deprecation_date": "2027-09-10", - "input_cost_per_second": 0.000833333333333, - "litellm_provider": "azure", - "mode": "realtime", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true - }, - "azure/gpt-live-transcribe": { - "deprecation_date": "2028-02-01", - "input_cost_per_second": 0.000283333333333, - "litellm_provider": "azure", - "max_input_tokens": 32000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "audio_transcription", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supported_endpoints": [ - "/v1/realtime", - "/v1/realtime/transcription_sessions" - ], - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true - }, - "azure/gpt-transcribe": { - "deprecation_date": "2028-02-01", - "input_cost_per_second": 7.5e-05, - "litellm_provider": "azure", - "mode": "audio_transcription", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supported_endpoints": [ - "/v1/audio/transcriptions", - "/v1/realtime/transcription_sessions" - ], - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true - }, - "azure/gpt-realtime-translate": { - "deprecation_date": "2027-05-06", - "input_cost_per_second": 0.000566666666667, - "litellm_provider": "azure", - "max_input_tokens": 32000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "realtime", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supported_modalities": [ - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_audio_input": true, - "supports_audio_output": true - }, - "aihubmix/agnes-2.5-flash": { - "input_cost_per_token": 3e-08, - "litellm_provider": "aihubmix", - "max_input_tokens": 512000, - "max_output_tokens": 65500, - "max_tokens": 65500, - "mode": "chat", - "output_cost_per_token": 1.5e-07, - "source": "https://aihubmix.com/api/v1/models", - "supports_reasoning": true, - "supports_vision": true - }, - "aihubmix/agnes-2.5-pro": { - "cache_read_input_token_cost": 3.78e-09, - "input_cost_per_token": 4.5e-07, - "litellm_provider": "aihubmix", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 9e-07, - "source": "https://aihubmix.com/api/v1/models", + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_vision": true - }, - "aihubmix/cc-glm-5.1": { - "input_cost_per_token": 6e-08, - "litellm_provider": "aihubmix", - "max_input_tokens": 200000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.2e-07, - "source": "https://aihubmix.com/api/v1/models", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 1024, + "input_cost_per_token": 5.5e-06, + "cache_creation_input_token_cost_above_1hr": 1.1e-05, + "output_cost_per_token": 2.75e-05, + "cache_read_input_token_cost": 5.5e-07, + "cache_creation_input_token_cost": 6.875e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "ap-northeast-1" + } }, - "aihubmix/claude-fable-5": { - "cache_read_input_token_cost": 1.1e-06, - "cache_creation_input_token_cost": 1.375e-05, - "input_cost_per_token": 1.1e-05, - "litellm_provider": "aihubmix", + "apac.anthropic.claude-opus-5": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "thinking_on_by_default": true, + "supports_mid_conversation_system": true, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 5.5e-05, - "source": "https://aihubmix.com/api/v1/models", + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "supports_adaptive_thinking": true, - "thinking_always_on": true, - "supports_sampling_params": false + "cache_creation_input_token_cost_above_1hr": 1.1e-05, + "cache_creation_input_token_cost": 6.875e-06, + "input_cost_per_token": 5.5e-06, + "cache_read_input_token_cost": 5.5e-07, + "output_cost_per_token": 2.75e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/ap-northeast-1/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + }, + "input_cost_per_token_batches": 2.75e-06, + "output_cost_per_token_batches": 1.375e-05 }, - "aihubmix/claude-haiku-4-5": { - "cache_read_input_token_cost": 1.1e-07, - "cache_creation_input_token_cost": 1.375e-06, - "input_cost_per_token": 1.1e-06, - "litellm_provider": "aihubmix", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "apac.anthropic.claude-opus-5-5": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 5.5e-06, - "source": "https://aihubmix.com/api/v1/models", + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 4096 + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "thinking_always_on": true, + "supports_forced_tool_use": false, + "cache_creation_input_token_cost_above_1hr": 8.8e-06, + "cache_creation_input_token_cost": 5.5e-06, + "input_cost_per_token": 4.4e-06, + "output_cost_per_token": 2.2e-05, + "cache_read_input_token_cost": 2.2e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + } }, - "aihubmix/claude-opus-4-8-think": { - "cache_read_input_token_cost": 5e-07, - "cache_creation_input_token_cost": 6.25e-06, - "input_cost_per_token": 5e-06, - "litellm_provider": "aihubmix", + "apac.anthropic.claude-sonnet-4-6": { + "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 64000, "mode": "chat", - "output_cost_per_token": 2.5e-05, - "source": "https://aihubmix.com/api/v1/models", + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_max_reasoning_effort": true, + "supports_tool_choice": true, "supports_vision": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "supports_adaptive_thinking": true, - "supports_sampling_params": false + "output_cost_per_token": 1.65e-05, + "cache_creation_input_token_cost_above_1hr": 6.6e-06, + "cache_read_input_token_cost": 3.3e-07, + "cache_creation_input_token_cost": 4.125e-06, + "input_cost_per_token": 3.3e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-6", + "litellm_provider": "bedrock" + } }, - "aihubmix/claude-opus-5": { - "cache_read_input_token_cost": 5e-07, - "cache_creation_input_token_cost": 6.25e-06, - "input_cost_per_token": 5e-06, - "litellm_provider": "aihubmix", + "apac.anthropic.claude-sonnet-5": { + "bedrock_converse_supports_strict_tools": false, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2.5e-05, - "source": "https://aihubmix.com/api/v1/models", + "supports_adaptive_thinking": true, + "thinking_on_by_default": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "supports_adaptive_thinking": true, - "prompt_cache_min_tokens": 512, - "supports_sampling_params": false - }, - "aihubmix/claude-sonnet-5": { - "cache_read_input_token_cost": 2e-07, - "cache_creation_input_token_cost": 2.5e-06, - "input_cost_per_token": 2e-06, - "litellm_provider": "aihubmix", + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 1024, + "cache_creation_input_token_cost_above_1hr": 4.4e-06, + "cache_creation_input_token_cost": 2.75e-06, + "input_cost_per_token": 2.2e-06, + "output_cost_per_token": 1.1e-05, + "cache_read_input_token_cost": 2.2e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + } + }, + "us.anthropic.claude-mythos-preview": { + "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://aihubmix.com/api/v1/models", + "thinking_always_on": true, "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, "supports_vision": true, - "prompt_cache_min_tokens": 1024, - "supports_adaptive_thinking": true, - "supports_sampling_params": false - }, - "aihubmix/coding-glm-5.3": { - "cache_read_input_token_cost": 1.5e-08, - "input_cost_per_token": 6e-08, - "litellm_provider": "aihubmix", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.2e-07, - "source": "https://aihubmix.com/api/v1/models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true - }, - "aihubmix/coding-kimi-k3": { - "cache_read_input_token_cost": 6.6e-08, - "input_cost_per_token": 4.4e-07, - "litellm_provider": "aihubmix", - "max_input_tokens": 1048576, - "max_output_tokens": 1048576, - "max_tokens": 1048576, - "mode": "chat", - "output_cost_per_token": 1.61333e-06, - "source": "https://aihubmix.com/api/v1/models", - "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true + "supports_tool_choice": true, + "supports_output_config": true, + "cache_creation_input_token_cost_above_1hr": 5.5e-05, + "cache_read_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost": 3.4375e-05, + "output_cost_per_token": 0.0001375, + "input_cost_per_token": 2.75e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, - "aihubmix/coding-xiaomi-mimo-v2-omni": { - "cache_read_input_token_cost": 1.6e-08, - "input_cost_per_token": 8e-08, - "litellm_provider": "aihubmix", + "apac.anthropic.claude-mythos-preview": { + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 4e-07, - "source": "https://aihubmix.com/api/v1/models", + "thinking_always_on": true, "supports_function_calling": true, + "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true + "supports_tool_choice": true, + "supports_output_config": true, + "input_cost_per_token": 2.75e-05, + "cache_creation_input_token_cost": 3.4375e-05, + "output_cost_per_token": 0.0001375, + "cache_creation_input_token_cost_above_1hr": 5.5e-05, + "cache_read_input_token_cost": 2.75e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, - "aihubmix/coding-xiaomi-mimo-v2.5": { - "cache_read_input_token_cost": 1.6e-09, - "input_cost_per_token": 8e-08, - "litellm_provider": "aihubmix", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, + "au.anthropic.claude-mythos-preview": { + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.6e-07, - "source": "https://aihubmix.com/api/v1/models", + "thinking_always_on": true, "supports_function_calling": true, + "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true + "supports_tool_choice": true, + "supports_output_config": true, + "input_cost_per_token": 2.75e-05, + "cache_creation_input_token_cost": 3.4375e-05, + "output_cost_per_token": 0.0001375, + "cache_creation_input_token_cost_above_1hr": 5.5e-05, + "cache_read_input_token_cost": 2.75e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, - "aihubmix/coding-xiaomi-mimo-v2.5-pro": { - "cache_read_input_token_cost": 1.6e-09, - "input_cost_per_token": 2e-07, - "litellm_provider": "aihubmix", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, + "deepseek.r1-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-r1.html", + "input_cost_per_token": 1.35e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 8192, "mode": "chat", - "output_cost_per_token": 4e-07, - "source": "https://aihubmix.com/api/v1/models", - "supports_function_calling": true, - "supports_prompt_caching": true, + "output_cost_per_token": 5.4e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-r1.html", + "supports_function_calling": false, "supports_reasoning": true, - "supports_response_schema": true + "supports_tool_choice": false }, - "aihubmix/command-a-plus-05-2026": { - "input_cost_per_token": 2.5e-06, - "litellm_provider": "aihubmix", + "mistral.pixtral-large-2502-v1:0": { + "input_cost_per_token": 2e-06, + "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_output_tokens": 16384, "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 6e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true + "supports_tool_choice": false }, - "aihubmix/deepseek-v4-flash": { - "cache_read_input_token_cost": 2.84e-08, - "input_cost_per_token": 1.42e-07, - "litellm_provider": "aihubmix", - "max_input_tokens": 1000000, - "max_output_tokens": 384000, - "max_tokens": 384000, + "azure_ai/MAI-Cyber-1-Flash": { + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 6e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 256000, + "max_output_tokens": 64000, "mode": "chat", - "output_cost_per_token": 2.84e-07, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 3.5e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true + "supports_tool_choice": true }, - "aihubmix/deepseek-v4-pro": { - "cache_read_input_token_cost": 1.4027e-07, - "input_cost_per_token": 1.69e-06, - "litellm_provider": "aihubmix", - "max_input_tokens": 1000000, - "max_output_tokens": 384000, - "max_tokens": 384000, - "mode": "chat", - "output_cost_per_token": 3.38e-06, - "source": "https://aihubmix.com/api/v1/models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true + "azure_ai/mistral-ocr-2505": { + "litellm_provider": "azure_ai", + "mode": "ocr", + "ocr_cost_per_page": 0.001, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/mistral-ai/" }, - "aihubmix/doubao-seed-2-0-code-preview": { - "cache_read_input_token_cost": 9.644e-08, - "input_cost_per_token": 4.822e-07, - "litellm_provider": "aihubmix", - "max_input_tokens": 256000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.411e-06, - "source": "https://aihubmix.com/api/v1/models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_vision": true, - "supports_web_search": true + "azure_ai/mistral-ocr-2512": { + "litellm_provider": "azure_ai", + "mode": "ocr", + "ocr_cost_per_page": 0.002, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/mistral-ai/" }, - "aihubmix/doubao-seed-2-0-lite-260428": { - "cache_read_input_token_cost": 1.8082e-08, - "input_cost_per_token": 9.041e-08, - "litellm_provider": "aihubmix", - "max_input_tokens": 256000, + "anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "bedrock_converse", + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + }, + "supports_tool_search": true, + "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 5.4246e-07, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, - "aihubmix/doubao-seed-2-0-mini": { - "cache_read_input_token_cost": 6.027e-09, - "input_cost_per_token": 3.0136e-08, - "litellm_provider": "aihubmix", - "max_input_tokens": 256000, + "apac.anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3.0136e-07, - "source": "https://aihubmix.com/api/v1/models", + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "cache_creation_input_token_cost_above_1hr": 4.4e-06, + "cache_creation_input_token_cost": 2.75e-06, + "input_cost_per_token": 2.2e-06, + "output_cost_per_token": 1.1e-05, + "cache_read_input_token_cost": 1.1e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, - "aihubmix/doubao-seed-2-0-pro": { - "cache_read_input_token_cost": 9.644e-08, - "input_cost_per_token": 4.822e-07, - "litellm_provider": "aihubmix", - "max_input_tokens": 256000, + "au.anthropic.claude-sonnet-5-5": { + "token_count_model": { + "model": "au.anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + }, + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_1hr": 4.4e-06, + "cache_read_input_token_cost": 1.1e-07, + "input_cost_per_token": 2.2e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2.411e-06, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 1.1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, - "aihubmix/doubao-seed-2-1-turbo": { - "cache_read_input_token_cost": 9.295e-08, - "input_cost_per_token": 4.6475e-07, - "litellm_provider": "aihubmix", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "azure_ai/claude-sonnet-5-5": { + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_read_input_token_cost": 1e-07, + "deprecation_date": "2027-09-29", + "input_cost_per_token": 2e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2.32375e-06, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "supports_forced_tool_use": false, + "supports_web_search": true, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://management.azure.com/subscriptions/c873328e-b572-4770-8dff-aaeb6f1f0e79/providers/Microsoft.CognitiveServices/locations/eastus2/models?api-version=2024-10-01" }, - "aihubmix/ernie-5.1": { - "cache_read_input_token_cost": 5.634e-07, - "input_cost_per_token": 5.634e-07, - "litellm_provider": "aihubmix", - "max_input_tokens": 119000, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 2.5353e-06, - "source": "https://aihubmix.com/api/v1/models", - "supports_prompt_caching": true, - "supports_reasoning": true + "azure_ai/claude-sonnet-latest": { + "alias_of": "azure_ai/claude-sonnet-5-5" }, - "aihubmix/gemini-3-flash-preview": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 5e-07, - "litellm_provider": "aihubmix", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "bedrock/us-gov-east-1/anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 3e-06, + "cache_creation_input_token_cost_above_1hr": 4.8e-06, + "cache_read_input_token_cost": 1.2e-07, + "input_cost_per_token": 2.4e-06, + "litellm_provider": "bedrock", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3e-06, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 1.2e-05, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_xhigh_reasoning_effort": true }, - "aihubmix/gemini-3-flash-preview-search": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 5e-07, - "litellm_provider": "aihubmix", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "bedrock/us-gov-west-1/anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 3e-06, + "cache_creation_input_token_cost_above_1hr": 4.8e-06, + "cache_read_input_token_cost": 1.2e-07, + "input_cost_per_token": 2.4e-06, + "litellm_provider": "bedrock", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3e-06, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 1.2e-05, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-sonnet-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, - "aihubmix/gemini-3.1-pro-preview": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 2e-06, - "litellm_provider": "aihubmix", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "eu.anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_1hr": 4.4e-06, + "cache_read_input_token_cost": 1.1e-07, + "input_cost_per_token": 2.2e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.2e-05, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 1.1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, - "aihubmix/gemini-3.1-pro-preview-customtools": { - "cache_read_input_token_cost": 2e-07, + "global.anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 2e-06, - "litellm_provider": "aihubmix", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "litellm_provider": "bedrock_converse", + "token_count_model": { + "model": "global.anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + }, + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.2e-05, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, - "aihubmix/gemini-3.5-flash-lite": { - "cache_read_input_token_cost": 3e-08, - "input_cost_per_token": 3e-07, - "litellm_provider": "aihubmix", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "bedrock/claude-sonnet-latest": { + "alias_of": "global.anthropic.claude-sonnet-5-5" + }, + "jp.anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_1hr": 4.4e-06, + "cache_read_input_token_cost": 1.1e-07, + "input_cost_per_token": 2.2e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2.499999e-06, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 1.1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, - "aihubmix/gemini-3.7-flash": { - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_token": 7.5e-07, - "litellm_provider": "aihubmix", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 3.75e-06, - "source": "https://aihubmix.com/api/v1/models", + "perplexity/anthropic/claude-sonnet-5-5": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_adaptive_thinking": true, + "supports_web_search": true, "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": true + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, - "aihubmix/gemma-4-26b-a4b-it": { - "input_cost_per_token": 1.4e-07, - "litellm_provider": "aihubmix", - "max_input_tokens": 262144, - "max_output_tokens": 131100, - "max_tokens": 131100, - "mode": "chat", - "output_cost_per_token": 3.9998e-07, - "source": "https://aihubmix.com/api/v1/models", - "supports_reasoning": true, - "supports_vision": true + "perplexity/anthropic/claude-fable-5-1": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 1e-05, + "output_cost_per_token": 5e-05, + "cache_read_input_token_cost": 2.5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, - "aihubmix/gemma-4-31b-it": { - "input_cost_per_token": 1.4e-07, - "litellm_provider": "aihubmix", - "max_input_tokens": 262144, - "max_output_tokens": 131100, - "max_tokens": 131100, - "mode": "chat", - "output_cost_per_token": 3.9998e-07, - "source": "https://aihubmix.com/api/v1/models", - "supports_reasoning": true, - "supports_vision": true + "perplexity/anthropic/claude-opus-5-5": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 4e-06, + "output_cost_per_token": 2e-05, + "cache_read_input_token_cost": 2e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, - "aihubmix/glm-5.2-fast-preview": { - "cache_read_input_token_cost": 5.635e-07, - "input_cost_per_token": 2.254e-06, - "litellm_provider": "aihubmix", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 7.889e-06, - "source": "https://aihubmix.com/api/v1/models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true + "perplexity/openai/gpt-6.1-sol": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token_above_272k_tokens": 4e-06, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, - "aihubmix/glm-5.3": { - "cache_read_input_token_cost": 2.817e-07, - "input_cost_per_token": 1.1268e-06, - "litellm_provider": "aihubmix", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 3.9438e-06, - "source": "https://aihubmix.com/api/v1/models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true + "perplexity/openai/gpt-6-sol": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token_above_272k_tokens": 4e-06, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, - "aihubmix/glm-5.3-flash": { - "cache_read_input_token_cost": 2.817e-08, - "input_cost_per_token": 1.1268e-07, - "litellm_provider": "aihubmix", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 3.9438e-07, - "source": "https://aihubmix.com/api/v1/models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true + "perplexity/openai/gpt-6-astra": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 1e-05, + "output_cost_per_token": 5e-05, + "cache_read_input_token_cost": 1e-06, + "cache_creation_input_token_cost": 1.25e-05, + "input_cost_per_token_above_272k_tokens": 2e-05, + "output_cost_per_token_above_272k_tokens": 7.5e-05, + "cache_read_input_token_cost_above_272k_tokens": 2e-06, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, - "aihubmix/glm-5v-turbo": { - "cache_read_input_token_cost": 1.69008e-07, - "input_cost_per_token": 7.042e-07, - "litellm_provider": "aihubmix", - "max_input_tokens": 200000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 3.09848e-06, - "source": "https://aihubmix.com/api/v1/models", - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_vision": true + "perplexity/openai/gpt-6-luna": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 1e-07, + "output_cost_per_token": 5e-07, + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token_above_272k_tokens": 2e-07, + "output_cost_per_token_above_272k_tokens": 7.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, - "aihubmix/gpt-5.3-codex": { - "cache_read_input_token_cost": 1.75e-07, - "input_cost_per_token": 1.75e-06, - "litellm_provider": "aihubmix", - "max_input_tokens": 400000, + "perplexity/google/gemini-3.8-flash": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_sampling_params": false, + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 3.75e-06, + "cache_read_input_token_cost": 7.5e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/xai/grok-4.7": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token_above_200k_tokens": 4e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "us-gov.anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 3e-06, + "cache_creation_input_token_cost_above_1hr": 4.8e-06, + "cache_read_input_token_cost": 1.2e-07, + "input_cost_per_token": 2.4e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.4e-05, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 1.2e-05, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-sonnet-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, - "aihubmix/gpt-5.4-high": { - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 2.5e-06, - "litellm_provider": "aihubmix", - "max_input_tokens": 1050000, + "us.anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_1hr": 4.4e-06, + "cache_read_input_token_cost": 1.1e-07, + "input_cost_per_token": 2.2e-06, + "litellm_provider": "bedrock_converse", + "token_count_model": { + "model": "us.anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + }, + "supports_tool_search": true, + "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 1.1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, - "aihubmix/gpt-5.4-low": { - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 2.5e-06, - "litellm_provider": "aihubmix", - "max_input_tokens": 1050000, + "vertex_ai/claude-sonnet-5-5": { + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_creation_input_token_cost_batches": 1.25e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, - "aihubmix/gpt-5.4-mini": { - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_token": 7.5e-07, - "litellm_provider": "aihubmix", - "max_input_tokens": 400000, + "vertex_ai/claude-sonnet-latest": { + "alias_of": "vertex_ai/claude-sonnet-5-5" + }, + "vertex_ai/claude-sonnet-5-5@default": { + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_creation_input_token_cost_batches": 1.25e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 4.5e-06, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, - "aihubmix/gpt-5.4-nano": { - "cache_read_input_token_cost": 2e-08, - "input_cost_per_token": 2e-07, - "litellm_provider": "aihubmix", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "prism/deepseek-v4.1-flash": { + "cache_read_input_token_cost": 7e-08, + "input_cost_per_token": 1.7e-07, + "litellm_provider": "prism", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, "mode": "chat", - "output_cost_per_token": 1.25e-06, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 6.3e-07, + "source": "https://prisminference.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, - "aihubmix/gpt-5.5": { - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 5e-06, - "litellm_provider": "aihubmix", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "prism/deepseek-v4-flash": { + "cache_read_input_token_cost": 7e-08, + "input_cost_per_token": 1.7e-07, + "litellm_provider": "prism", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, "mode": "chat", - "output_cost_per_token": 3e-05, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 2.1e-07, + "source": "https://prisminference.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false }, - "aihubmix/gpt-5.5-pro": { - "input_cost_per_token": 3e-05, - "litellm_provider": "aihubmix", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "global.xai.grok-4.7": { + "supports_regex_lookaround": false, + "supported_endpoints": ["/v1/chat/completions"], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_response_format": true, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_flex": 2.5e-07, + "cache_read_input_token_cost_priority": 8.75e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.5e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 524288, + "max_output_tokens": 524288, "mode": "chat", - "output_cost_per_token": 0.00018, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 6e-06, + "output_cost_per_token_flex": 3e-06, + "output_cost_per_token_priority": 1.05e-05, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-xai-grok-4-7.html", "supports_function_calling": true, + "supports_prompt_caching": false, "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": true + "supports_tool_choice": true, + "supports_vision": true }, - "aihubmix/gpt-5.6-luna": { - "cache_read_input_token_cost": 2e-08, - "cache_creation_input_token_cost": 2.5e-07, - "input_cost_per_token": 2e-07, - "litellm_provider": "aihubmix", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "bedrock/grok-latest": { + "alias_of": "global.xai.grok-4.7" + }, + "us.xai.grok-4.7": { + "supports_regex_lookaround": false, + "supported_endpoints": ["/v1/chat/completions"], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_response_format": true, + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_flex": 2.75e-07, + "cache_read_input_token_cost_priority": 9.625e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_flex": 1.1e-06, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 524288, + "max_output_tokens": 524288, "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 6.6e-06, + "output_cost_per_token_flex": 3.3e-06, + "output_cost_per_token_priority": 1.155e-05, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-xai-grok-4-7.html", "supports_function_calling": true, - "supports_prompt_caching": true, + "supports_prompt_caching": false, "supports_reasoning": true, - "supports_response_schema": true, + "supports_tool_choice": true, "supports_vision": true }, - "aihubmix/gpt-5.6-sol-disc": { - "cache_read_input_token_cost": 4e-07, - "cache_creation_input_token_cost": 5e-06, - "input_cost_per_token": 4e-06, - "litellm_provider": "aihubmix", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "us-gov.xai.grok-4.7": { + "supports_regex_lookaround": false, + "supported_endpoints": ["/v1/chat/completions"], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_response_format": true, + "cache_read_input_token_cost": 6.6e-07, + "cache_read_input_token_cost_flex": 3.3e-07, + "cache_read_input_token_cost_priority": 1.155e-06, + "input_cost_per_token": 2.64e-06, + "input_cost_per_token_batches": 1.32e-06, + "input_cost_per_token_flex": 1.32e-06, + "input_cost_per_token_priority": 4.62e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 524288, + "max_output_tokens": 524288, "mode": "chat", - "output_cost_per_token": 2e-05, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 7.92e-06, + "output_cost_per_token_batches": 3.96e-06, + "output_cost_per_token_flex": 3.96e-06, + "output_cost_per_token_priority": 1.386e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supports_function_calling": true, - "supports_prompt_caching": true, + "supports_prompt_caching": false, "supports_reasoning": true, - "supports_response_schema": true, + "supports_tool_choice": true, "supports_vision": true }, - "aihubmix/gpt-5.6-terra": { - "cache_read_input_token_cost": 2e-07, - "cache_creation_input_token_cost": 2.5e-06, - "input_cost_per_token": 2e-06, - "litellm_provider": "aihubmix", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "baseten/deepseek-ai/DeepSeek-V4.1-Flash-Fast": { + "cache_read_input_token_cost": 1.4e-08, + "input_cost_per_token": 6e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 1.2e-05, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 2.4e-06, + "source": "https://inference.baseten.co/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_tool_choice": true, "supports_vision": true }, - "aihubmix/gpt-chat-latest": { - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 5e-06, - "litellm_provider": "aihubmix", - "max_input_tokens": 400000, + "gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_12hr": 5e-06, + "cache_creation_input_token_cost_above_12hr_ultrafast": 3e-05, + "cache_creation_input_token_cost_above_12hr_batches": 2.5e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 1e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 5e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 5e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 2e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_ultrafast": 6e-05, + "cache_creation_input_token_cost_above_12hr_flex": 2.5e-06, + "cache_creation_input_token_cost_above_12hr_priority": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_batches": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 3e-05, + "cache_creation_input_token_cost_batches": 1.25e-06, + "cache_creation_input_token_cost_flex": 1.25e-06, + "cache_creation_input_token_cost_priority": 5e-06, + "cache_creation_input_token_cost_ultrafast": 1.5e-05, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "cache_read_input_token_cost_above_272k_tokens_batches": 1e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 1e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.2e-06, + "cache_read_input_token_cost_batches": 5e-08, + "cache_read_input_token_cost_flex": 5e-08, + "cache_read_input_token_cost_priority": 2e-07, + "cache_read_input_token_cost_ultrafast": 6e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_batches": 2e-06, + "input_cost_per_token_above_272k_tokens_flex": 2e-06, + "input_cost_per_token_above_272k_tokens_priority": 8e-06, + "input_cost_per_token_above_272k_tokens_ultrafast": 2.4e-05, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 4e-06, + "input_cost_per_token_ultrafast": 1.2e-05, + "litellm_provider": "openai", + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3e-05, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "output_cost_per_token_above_272k_tokens_batches": 7.5e-06, + "output_cost_per_token_above_272k_tokens_flex": 7.5e-06, + "output_cost_per_token_above_272k_tokens_priority": 3e-05, + "output_cost_per_token_above_272k_tokens_ultrafast": 9e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_flex": 5e-06, + "output_cost_per_token_priority": 2e-05, + "output_cost_per_token_ultrafast": 6e-05, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard", + "pro" + ], + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true }, - "aihubmix/grok-4-20-non-reasoning": { - "cache_read_input_token_cost": 2e-07, + "gpt-sol-latest": { + "alias_of": "gpt-6.1-sol" + }, + "global.openai.gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 3e-05, + "cache_creation_input_token_cost_ultrafast": 1.5e-05, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.2e-06, + "cache_read_input_token_cost_ultrafast": 6e-07, "input_cost_per_token": 2e-06, - "litellm_provider": "aihubmix", + "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_ultrafast": 2.4e-05, + "input_cost_per_token_ultrafast": 1.2e-05, + "litellm_provider": "bedrock_converse", + "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1000000, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 6e-06, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "output_cost_per_token_above_272k_tokens_ultrafast": 9e-05, + "output_cost_per_token_ultrafast": 6e-05, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_bedrock_runtime_chat_completions_response_format": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_sampling_params": false, + "supports_xhigh_reasoning_effort": true + }, + "bedrock/gpt-sol-latest": { + "alias_of": "global.openai.gpt-6.1-sol" + }, + "bedrock_mantle/openai.gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 3.3e-05, + "cache_creation_input_token_cost_ultrafast": 1.65e-05, + "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2.2e-07, + "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.32e-06, + "cache_read_input_token_cost_ultrafast": 6.6e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_above_272k_tokens": 4.4e-06, + "input_cost_per_token_above_272k_tokens_ultrafast": 2.64e-05, + "input_cost_per_token_ultrafast": 1.32e-05, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "mode": "responses", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_above_272k_tokens": 1.65e-05, + "output_cost_per_token_above_272k_tokens_ultrafast": 9.9e-05, + "output_cost_per_token_ultrafast": 6.6e-05, + "search_context_cost_per_query": {"search_context_size_high":0.012,"search_context_size_low":0.012,"search_context_size_medium":0.012}, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, "supports_prompt_caching": true, + "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true, + "use_openai_responses_path": true }, - "aihubmix/grok-4-20-reasoning": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 2e-06, - "litellm_provider": "aihubmix", + "bedrock_mantle/gpt-sol-latest": { + "alias_of": "bedrock_mantle/openai.gpt-6.1-sol" + }, + "us.openai.gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 3.3e-05, + "cache_creation_input_token_cost_ultrafast": 1.65e-05, + "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2.2e-07, + "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.32e-06, + "cache_read_input_token_cost_ultrafast": 6.6e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_above_272k_tokens": 4.4e-06, + "input_cost_per_token_above_272k_tokens_ultrafast": 2.64e-05, + "input_cost_per_token_ultrafast": 1.32e-05, + "litellm_provider": "bedrock_converse", + "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1000000, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 6e-06, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_above_272k_tokens": 1.65e-05, + "output_cost_per_token_above_272k_tokens_ultrafast": 9.9e-05, + "output_cost_per_token_ultrafast": 6.6e-05, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_bedrock_runtime_chat_completions_response_format": true, "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_sampling_params": false, + "supports_xhigh_reasoning_effort": true }, - "aihubmix/grok-4.6": { + "vertex_ai/gemini-3.8-flash-tts": { + "input_cost_per_token": 5e-07, + "litellm_provider": "vertex_ai", + "max_input_tokens": 8192, + "max_output_tokens": 16384, + "mode": "audio_speech", + "output_cost_per_audio_token": 9e-06, + "output_cost_per_token": 9e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "vertex_ai/gemini-3.8-flash-lite-tts": { + "input_cost_per_token": 5e-07, + "litellm_provider": "vertex_ai", + "max_input_tokens": 8192, + "max_output_tokens": 16384, + "mode": "audio_speech", + "output_cost_per_audio_token": 6e-06, + "output_cost_per_token": 6e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "vertex_ai/xai/grok-4.7": { "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, "input_cost_per_token": 2e-06, - "litellm_provider": "aihubmix", - "max_input_tokens": 500000, - "max_output_tokens": 500000, - "max_tokens": 500000, + "input_cost_per_token_above_200k_tokens": 4e-06, + "litellm_provider": "vertex_ai", + "max_input_tokens": 524288, + "max_output_tokens": 524288, "mode": "chat", "output_cost_per_token": 6e-06, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_tool_choice": true, "supports_vision": true }, - "aihubmix/grok-build-0.1": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1e-06, - "litellm_provider": "aihubmix", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "vertex_ai/grok-latest": { + "alias_of": "vertex_ai/xai/grok-4.7" + }, + "azure_ai/kimi-k2-thinking": { + "deprecation_date": "2026-03-29", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", + "successor_model": "azure_ai/kimi-k2.5", + "input_cost_per_token": 6e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 2.5e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, - "supports_prompt_caching": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true + "supports_tool_choice": true, + "supports_video_input": false, + "supports_vision": false }, - "aihubmix/hy3": { - "cache_read_input_token_cost": 3.905e-08, - "input_cost_per_token": 1.562e-07, - "litellm_provider": "aihubmix", - "max_input_tokens": 256000, + "global.zai.glm-5.3": { + "cache_creation_input_token_cost": 2.1e-06, + "cache_creation_input_token_cost_batches": 1.05e-06, + "cache_creation_input_token_cost_flex": 1.05e-06, + "cache_creation_input_token_cost_priority": 3.675e-06, + "cache_read_input_token_cost": 3.12e-07, + "cache_read_input_token_cost_batches": 1.56e-07, + "cache_read_input_token_cost_flex": 1.56e-07, + "cache_read_input_token_cost_priority": 5.46e-07, + "input_cost_per_token": 1.68e-06, + "input_cost_per_token_batches": 8.4e-07, + "input_cost_per_token_flex": 8.4e-07, + "input_cost_per_token_priority": 2.94e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 6.248e-07, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 5.28e-06, + "output_cost_per_token_batches": 2.64e-06, + "output_cost_per_token_flex": 2.64e-06, + "output_cost_per_token_priority": 9.24e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, "supports_function_calling": true, + "supports_native_structured_output": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_web_search": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false }, - "aihubmix/hy4-preview": { - "cache_read_input_token_cost": 4.225e-08, - "input_cost_per_token": 8.45e-07, - "litellm_provider": "aihubmix", - "max_input_tokens": 1048576, - "max_output_tokens": 64000, - "max_tokens": 64000, + "bedrock/glm-latest": { + "alias_of": "global.zai.glm-5.3" + }, + "us.zai.glm-5.3": { + "cache_creation_input_token_cost": 2.31e-06, + "cache_creation_input_token_cost_batches": 1.155e-06, + "cache_creation_input_token_cost_flex": 1.155e-06, + "cache_creation_input_token_cost_priority": 4.0425e-06, + "cache_read_input_token_cost": 3.432e-07, + "cache_read_input_token_cost_batches": 1.716e-07, + "cache_read_input_token_cost_flex": 1.716e-07, + "cache_read_input_token_cost_priority": 6.006e-07, + "input_cost_per_token": 1.848e-06, + "input_cost_per_token_batches": 9.24e-07, + "input_cost_per_token_flex": 9.24e-07, + "input_cost_per_token_priority": 3.234e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2.535e-06, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 5.808e-06, + "output_cost_per_token_batches": 2.904e-06, + "output_cost_per_token_flex": 2.904e-06, + "output_cost_per_token_priority": 1.0164e-05, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, "supports_function_calling": true, + "supports_native_structured_output": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_web_search": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false }, - "aihubmix/kimi-k2.6": { - "cache_read_input_token_cost": 1.60835e-07, - "input_cost_per_token": 9.5e-07, - "litellm_provider": "aihubmix", - "max_input_tokens": 262144, + "amazon.nova-2-5-sonic": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_token": 3.3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 256000, + "max_output_tokens": 64000, + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 2.75e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-2-5-sonic.md", + "supports_audio_input": true, + "supports_audio_output": true + }, + "azure/model-router": { + "comment": "The flat $0.14 per M input tokens is the router's own fee, the routed model is priced on top of it", + "deprecation_date": "2027-05-20", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_token": 1.4e-07, + "litellm_provider": "azure", + "max_input_tokens": 200000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 3.9995e-06, - "source": "https://aihubmix.com/api/v1/models", - "supports_function_calling": true, + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/model-router/", + "supports_vision": true + }, + "azure/whisper": { + "deprecation_date": "2027-02-26", + "deprecation_source": "https://management.azure.com/subscriptions/a88257a5-3323-4ef9-95bf-5681a46c9624/providers/Microsoft.CognitiveServices/locations/eastus/models?api-version=2024-10-01", + "input_cost_per_second": 0.0001, + "litellm_provider": "azure", + "mode": "audio_transcription", + "output_cost_per_second": 0.0001, + "source": "https://management.azure.com/subscriptions/a88257a5-3323-4ef9-95bf-5681a46c9624/providers/Microsoft.CognitiveServices/locations/eastus/models?api-version=2024-10-01" + }, + "gemini/gemini-nano-banana-2.1": { + "input_cost_per_token": 1.5e-06, + "input_cost_per_token_batches": 7.5e-07, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "mode": "image_generation", + "output_cost_per_image": 0.0336, + "output_cost_per_image_token": 3e-05, + "output_cost_per_image_token_batches": 1.5e-05, + "output_cost_per_token": 7.5e-06, + "output_cost_per_token_batches": 3.75e-06, + "rpm": 1000.0, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/images/generations", + "/v1/images/edits" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 4000000.0, + "web_search_billing_unit": "per_query" + }, + "gemini-nano-banana-2.1": { + "cache_read_input_token_cost": 1.5e-07, + "cache_read_input_token_cost_batches": 7.5e-08, + "cache_read_input_token_cost_priority": 2.7e-07, + "input_cost_per_image": 0.00168, + "input_cost_per_token": 1.5e-06, + "input_cost_per_token_batches": 7.5e-07, + "input_cost_per_token_priority": 2.7e-06, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "mode": "image_generation", + "output_cost_per_image": 0.0336, + "output_cost_per_image_token": 3e-05, + "output_cost_per_image_token_batches": 1.5e-05, + "output_cost_per_image_token_priority": 5.4e-05, + "output_cost_per_token": 7.5e-06, + "output_cost_per_token_batches": 3.75e-06, + "output_cost_per_token_priority": 1.35e-05, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/images/generations", + "/v1/images/edits", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true + "supports_response_schema": false, + "supports_system_messages": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "web_search_billing_unit": "per_query" }, - "aihubmix/kimi-k2.7-code-highspeed": { - "cache_read_input_token_cost": 3.2167e-07, - "input_cost_per_token": 1.9e-06, - "litellm_provider": "aihubmix", - "max_input_tokens": 262144, + "vertex_ai/gemini-nano-banana-2.1": { + "cache_read_input_token_cost": 1.5e-07, + "cache_read_input_token_cost_batches": 7.5e-08, + "cache_read_input_token_cost_priority": 2.7e-07, + "input_cost_per_image": 0.00168, + "input_cost_per_token": 1.5e-06, + "input_cost_per_token_batches": 7.5e-07, + "input_cost_per_token_priority": 2.7e-06, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 7.999e-06, - "source": "https://aihubmix.com/api/v1/models", - "supports_function_calling": true, + "mode": "image_generation", + "output_cost_per_image": 0.0336, + "output_cost_per_image_token": 3e-05, + "output_cost_per_image_token_batches": 1.5e-05, + "output_cost_per_image_token_priority": 5.4e-05, + "output_cost_per_token": 7.5e-06, + "output_cost_per_token_batches": 3.75e-06, + "output_cost_per_token_priority": 1.35e-05, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/images/generations", + "/v1/images/edits", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true + "supports_response_schema": false, + "supports_system_messages": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "web_search_billing_unit": "per_query" }, - "aihubmix/kimi-k3": { - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "litellm_provider": "aihubmix", - "max_input_tokens": 1048576, - "max_output_tokens": 1048576, - "max_tokens": 1048576, + "azure_ai/grok-4.7": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "deprecation_date": "2027-10-05", + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 500000, + "max_output_tokens": 500000, "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "source": "https://docs.x.ai/developers/models/grok-4.7", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "aihubmix/longcat-2.0": { - "cache_read_input_token_cost": 1.5492e-08, - "input_cost_per_token": 7.746e-07, - "litellm_provider": "aihubmix", + "azure_ai/grok-latest": { + "alias_of": "azure_ai/grok-4.7" + }, + "in.moonshotai.kimi-k3": { + "cache_creation_input_token_cost": 4.125e-06, + "cache_creation_input_token_cost_flex": 2.0625e-06, + "cache_creation_input_token_cost_priority": 7.21875e-06, + "cache_read_input_token_cost": 3.3e-07, + "cache_read_input_token_cost_flex": 1.65e-07, + "cache_read_input_token_cost_priority": 5.775e-07, + "input_cost_per_token": 3.3e-06, + "input_cost_per_token_flex": 1.65e-06, + "input_cost_per_token_priority": 5.775e-06, + "litellm_provider": "bedrock_converse", + "token_count_framing": 64, + "token_count_tokenizer": "kimi_k3", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 3.0984e-06, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 1.65e-05, + "output_cost_per_token_flex": 8.25e-06, + "output_cost_per_token_priority": 2.8875e-05, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k3.md", + "supports_audio_input": false, "supports_function_calling": true, + "supports_prompt_cache_breakpoint": false, "supports_prompt_caching": true, - "supports_reasoning": true - }, - "aihubmix/mai-thinking-1": { - "input_cost_per_token": 2e-06, - "litellm_provider": "aihubmix", - "max_input_tokens": 256000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 8e-06, - "source": "https://aihubmix.com/api/v1/models", "supports_reasoning": true, - "supports_response_schema": true + "supports_regex_lookaround": false, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, - "aihubmix/mimo-v2-omni": { - "cache_read_input_token_cost": 8.8e-08, - "input_cost_per_token": 4.4e-07, - "litellm_provider": "aihubmix", - "max_input_tokens": 256000, +"claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens_batches": 2.5e-07, + "output_cost_per_token_above_100k_tokens_batches": 1.25e-06, + "cache_creation_input_token_cost_above_100k_tokens_batches": 3.125e-07, + "cache_read_input_token_cost_above_100k_tokens_batches": 2.5e-08, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_1hr": 2e-07, + "cache_creation_input_token_cost_batches": 6.25e-08, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_batches": 5e-09, + "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "litellm_provider": "anthropic", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2.2e-06, - "source": "https://aihubmix.com/api/v1/models", - "supports_prompt_caching": true, - "supports_vision": true, - "supports_web_search": true - }, - "aihubmix/mimo-v2-pro": { - "cache_read_input_token_cost": 2.2e-07, - "input_cost_per_token": 1.1e-06, - "litellm_provider": "aihubmix", - "max_input_tokens": 1000000, - "mode": "chat", - "output_cost_per_token": 3.3e-06, - "source": "https://aihubmix.com/api/v1/models", - "supports_prompt_caching": true, - "supports_web_search": true - }, - "aihubmix/minimax-m2.7": { - "cache_read_input_token_cost": 5.916e-08, - "input_cost_per_token": 2.958e-07, - "litellm_provider": "aihubmix", - "max_input_tokens": 204800, - "max_output_tokens": 204800, - "max_tokens": 204800, - "mode": "chat", - "output_cost_per_token": 1.1832e-06, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 5e-07, + "output_cost_per_token_batches": 2.5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_on_by_default": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true - }, - "aihubmix/minimax-m3": { - "input_cost_per_token": 2.88e-07, - "litellm_provider": "aihubmix", - "max_input_tokens": 1000000, - "max_output_tokens": 524288, - "max_tokens": 524288, - "mode": "chat", - "output_cost_per_token": 1.152e-06, - "source": "https://aihubmix.com/api/v1/models", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true - }, - "aihubmix/muse-spark-1.2": { - "input_cost_per_token": 1.375e-06, - "litellm_provider": "aihubmix", - "max_input_tokens": 1048576, - "mode": "chat", - "output_cost_per_token": 4.675e-06, - "source": "https://aihubmix.com/api/v1/models", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_vision": true - }, - "aihubmix/qwen3-coder-next": { - "input_cost_per_token": 1.37e-07, - "litellm_provider": "aihubmix", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 5.48e-07, - "source": "https://aihubmix.com/api/v1/models", - "supports_function_calling": true, - "supports_response_schema": true - }, - "aihubmix/qwen3.5-122b-a10b": { - "input_cost_per_token": 1.126e-07, - "litellm_provider": "aihubmix", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 9.008e-07, - "source": "https://aihubmix.com/api/v1/models", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": true - }, - "aihubmix/qwen3.5-397b-a17b": { - "input_cost_per_token": 1.644e-07, - "litellm_provider": "aihubmix", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 9.864e-07, - "source": "https://aihubmix.com/api/v1/models", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": true - }, - "aihubmix/qwen3.6-27b": { - "input_cost_per_token": 4.22e-07, - "litellm_provider": "aihubmix", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 2.532e-06, - "source": "https://aihubmix.com/api/v1/models", - "supports_function_calling": true, - "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true - }, - "aihubmix/qwen3.6-35b-a3b": { - "input_cost_per_token": 2.54e-07, - "litellm_provider": "aihubmix", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, + "prompt_cache_min_tokens": 512, + "source": "https://platform.claude.com/docs/en/models/haiku-5-5/overview", + "supports_web_search": true, + "input_cost_per_token_above_100k_tokens": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5e-08 + }, + "claude-haiku-latest": { + "alias_of": "claude-haiku-5-5" + }, + "bedrock_mantle/anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 5.5e-07, + "output_cost_per_token_above_100k_tokens": 2.75e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5.5e-08, + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 1.375e-07, + "cache_creation_input_token_cost_above_1hr": 2.2e-07, + "cache_read_input_token_cost": 1.1e-08, + "input_cost_per_token": 1.1e-07, + "litellm_provider": "bedrock_mantle", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.524e-06, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 5.5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_on_by_default": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, + "prompt_cache_min_tokens": 512, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-5-5.html" }, - "aihubmix/qwen3.6-max-preview": { - "cache_read_input_token_cost": 1.268e-07, - "cache_creation_input_token_cost": 1.585e-06, - "input_cost_per_token": 1.268e-06, - "litellm_provider": "aihubmix", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 7.608e-06, - "source": "https://aihubmix.com/api/v1/models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_web_search": true + "bedrock_mantle/claude-haiku-latest": { + "alias_of": "bedrock_mantle/anthropic.claude-haiku-5-5" }, - "aihubmix/qwen3.7-plus": { - "cache_read_input_token_cost": 5.64e-08, - "cache_creation_input_token_cost": 3.525e-07, - "input_cost_per_token": 2.82e-07, - "litellm_provider": "aihubmix", + "bedrock_mantle/us-gov-west-1/anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 6e-07, + "output_cost_per_token_above_100k_tokens": 3e-06, + "cache_creation_input_token_cost_above_100k_tokens": 7.5e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06, + "cache_read_input_token_cost_above_100k_tokens": 6e-08, + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.5e-07, + "cache_creation_input_token_cost_above_1hr": 2.4e-07, + "cache_read_input_token_cost": 1.2e-08, + "input_cost_per_token": 1.2e-07, + "litellm_provider": "bedrock_mantle", + "supports_tool_search": true, "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.128e-06, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 6e-07, + "supports_forced_tool_use": true, + "thinking_always_on": false, + "prompt_cache_min_tokens": 512, + "supports_adaptive_thinking": true, + "thinking_on_by_default": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true - }, - "aihubmix/qwen3.8-2.4t-a95b": { - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 2e-06, - "litellm_provider": "aihubmix", + "supports_xhigh_reasoning_effort": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-5-5.html", + "token_count_model": {"model":"anthropic.claude-haiku-5-5","litellm_provider":"bedrock_mantle","region":"us-gov-west-1"} + }, + "anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5e-08, + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_1hr": 2e-07, + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "bedrock_converse", + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + }, + "supports_tool_search": true, "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 6e-06, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_on_by_default": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_web_search": true + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, - "aihubmix/qwen3.8-flash": { - "cache_read_input_token_cost": 1.4075e-08, - "cache_creation_input_token_cost": 1.75937e-07, - "input_cost_per_token": 1.126e-07, - "litellm_provider": "aihubmix", + "apac.anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 5.5e-07, + "output_cost_per_token_above_100k_tokens": 2.75e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5.5e-08, + "bedrock_converse_supports_strict_tools": false, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3.80025e-07, - "source": "https://aihubmix.com/api/v1/models", + "supports_adaptive_thinking": true, + "thinking_on_by_default": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, + "prompt_cache_min_tokens": 512, + "cache_creation_input_token_cost_above_1hr": 2.2e-07, + "cache_creation_input_token_cost": 1.375e-07, + "input_cost_per_token": 1.1e-07, + "output_cost_per_token": 5.5e-07, + "cache_read_input_token_cost": 1.1e-08, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, - "aihubmix/qwen3.8-max": { - "cache_read_input_token_cost": 1.69e-07, - "cache_creation_input_token_cost": 2.1125e-06, - "input_cost_per_token": 1.69e-06, - "litellm_provider": "aihubmix", + "au.anthropic.claude-haiku-5-5": { + "token_count_model": { + "model": "au.anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + }, + "input_cost_per_token_above_100k_tokens": 5.5e-07, + "output_cost_per_token_above_100k_tokens": 2.75e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5.5e-08, + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 1.375e-07, + "cache_creation_input_token_cost_above_1hr": 2.2e-07, + "cache_read_input_token_cost": 1.1e-08, + "input_cost_per_token": 1.1e-07, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 5.07e-06, - "source": "https://aihubmix.com/api/v1/models", + "output_cost_per_token": 5.5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_on_by_default": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": true - }, - "aihubmix/step-3.7-flash": { - "cache_read_input_token_cost": 4.4e-08, - "input_cost_per_token": 2.2e-07, - "litellm_provider": "aihubmix", - "max_input_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 1.32e-06, - "source": "https://aihubmix.com/api/v1/models", - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_vision": true - }, - "openrouter/typesafe/jev-1.13": { - "input_cost_per_token": 4.2e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 32000, - "max_output_tokens": 28800, - "max_tokens": 28800, - "mode": "evaluation", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/typesafe/jev-1.13" - }, - "openrouter/typesafe/jev-router": { - "input_cost_per_token": 0, - "output_cost_per_token": 0, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_tokens": 1000000, - "mode": "chat", - "source": "https://openrouter.ai/typesafe/jev-router", - "supports_function_calling": true, + "supports_sampling_params": false, "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "supports_video_input": true - }, - "typesafe/jev-1.13.0": { - "input_cost_per_token": 4.2e-08, - "litellm_provider": "typesafe", - "mode": "evaluation", - "output_cost_per_token": 0.0, - "source": "https://docs.typesafe.ai/models" - }, - "typesafe/jev-latest": { - "input_cost_per_token": 4.2e-08, - "litellm_provider": "typesafe", - "mode": "evaluation", - "output_cost_per_token": 0.0, - "source": "https://docs.typesafe.ai/models" - }, - "typesafe/jev-preview": { - "input_cost_per_token": 4.2e-08, - "litellm_provider": "typesafe", - "mode": "evaluation", - "output_cost_per_token": 0.0, - "source": "https://docs.typesafe.ai/models" - }, - "wandb/deepseek-ai/DeepSeek-V4.1-Flash": { - "cache_read_input_token_cost": 3e-08, - "input_cost_per_token": 2e-07, - "litellm_provider": "wandb", - "max_input_tokens": 1049000, - "max_tokens": 1048576, - "mode": "chat", - "output_cost_per_token": 6.5e-07, - "source": "https://wandb.ai/site/pricing/tokens/", - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_vision": true + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, - "wandb/google/gemma-4-26B-A4B-it": { - "cache_read_input_token_cost": 5e-08, + "azure_ai/claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5e-08, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_1hr": 2e-07, + "cache_read_input_token_cost": 1e-08, + "deprecation_date": "2027-09-29", "input_cost_per_token": 1e-07, - "litellm_provider": "wandb", - "max_input_tokens": 262000, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://wandb.ai/site/pricing/tokens/", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "wandb/zai-org/GLM-5.3-Flash": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "wandb", - "max_input_tokens": 1049000, - "mode": "chat", - "output_cost_per_token": 5e-07, - "source": "https://wandb.ai/site/pricing/tokens/", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "openrouter/~anthropic/claude-fable-latest": { - "cache_creation_input_token_cost": 1.25e-05, - "cache_creation_input_token_cost_above_1hr": 2e-05, - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 1e-05, - "litellm_provider": "openrouter", + "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_on_by_default": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "supports_forced_tool_use": true, + "supports_web_search": true, + "thinking_always_on": false, + "prompt_cache_min_tokens": 512, + "source": "https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide" }, - "openrouter/~anthropic/claude-haiku-latest": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost_above_1hr": 2e-06, - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "azure_ai/claude-haiku-latest": { + "alias_of": "azure_ai/claude-haiku-5-5" + }, + "bedrock/us-gov-east-1/anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 6e-07, + "output_cost_per_token_above_100k_tokens": 3e-06, + "cache_creation_input_token_cost_above_100k_tokens": 7.5e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06, + "cache_read_input_token_cost_above_100k_tokens": 6e-08, + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.5e-07, + "cache_creation_input_token_cost_above_1hr": 2.4e-07, + "cache_read_input_token_cost": 1.2e-08, + "input_cost_per_token": 1.2e-07, + "litellm_provider": "bedrock", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 6e-07, + "supports_forced_tool_use": true, + "thinking_always_on": false, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "thinking_on_by_default": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_xhigh_reasoning_effort": true }, - "openrouter/~anthropic/claude-opus-latest": { - "cache_creation_input_token_cost": 5e-06, - "cache_creation_input_token_cost_above_1hr": 8e-06, - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 4e-06, - "litellm_provider": "openrouter", + "bedrock/us-gov-west-1/anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 6e-07, + "output_cost_per_token_above_100k_tokens": 3e-06, + "cache_creation_input_token_cost_above_100k_tokens": 7.5e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06, + "cache_read_input_token_cost_above_100k_tokens": 6e-08, + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.5e-07, + "cache_creation_input_token_cost_above_1hr": 2.4e-07, + "cache_read_input_token_cost": 1.2e-08, + "input_cost_per_token": 1.2e-07, + "litellm_provider": "bedrock", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 6e-07, + "supports_forced_tool_use": true, + "thinking_always_on": false, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "thinking_on_by_default": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-haiku-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, - "openrouter/~anthropic/claude-sonnet-latest": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_1hr": 4e-06, - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 2e-06, - "litellm_provider": "openrouter", + "eu.anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 5.5e-07, + "output_cost_per_token_above_100k_tokens": 2.75e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5.5e-08, + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 1.375e-07, + "cache_creation_input_token_cost_above_1hr": 2.2e-07, + "cache_read_input_token_cost": 1.1e-08, + "input_cost_per_token": 1.1e-07, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 5.5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_on_by_default": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, - "openrouter/~deepseek/deepseek-flash-latest": { - "cache_read_input_token_cost": 6e-09, - "input_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, + "global.anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5e-08, + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_1hr": 2e-07, + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "bedrock_converse", + "token_count_model": { + "model": "global.anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + }, + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_on_by_default": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, - "supports_pdf_input": false, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": false - }, - "openrouter/~deepseek/deepseek-pro-latest": { - "cache_read_input_token_cost": 4.4e-08, - "input_cost_per_token": 1.32e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, - "mode": "chat", - "off_peak_pricing": {"windows":[{"weekdays":["saturday","sunday"],"hours_utc":"00:00-00:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"00:00-01:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"04:00-06:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"10:00-00:00"}],"input_cost_per_token":6.6e-7,"output_cost_per_token":0.00000198,"cache_read_input_token_cost":2.2e-8}, - "output_cost_per_token": 3.96e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, - "openrouter/~deepseek/deepseek-v4-flash-latest": { - "cache_read_input_token_cost": 1.6e-08, - "input_cost_per_token": 4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 1310720, - "max_output_tokens": 943718, - "max_tokens": 943718, - "mode": "chat", - "output_cost_per_token": 6.4e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "bedrock/claude-haiku-latest": { + "alias_of": "global.anthropic.claude-haiku-5-5" }, - "openrouter/~google/gemini-flash-latest": { - "cache_creation_input_token_cost": 4.16666666666667e-08, - "cache_read_input_audio_token_cost": 7.5e-08, - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_audio_token": 7.5e-07, - "input_cost_per_token": 7.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "jp.anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 5.5e-07, + "output_cost_per_token_above_100k_tokens": 2.75e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5.5e-08, + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 1.375e-07, + "cache_creation_input_token_cost_above_1hr": 2.2e-07, + "cache_read_input_token_cost": 1.1e-08, + "input_cost_per_token": 1.1e-07, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3.75e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, + "output_cost_per_token": 5.5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_on_by_default": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, - "openrouter/~google/gemini-pro-latest": { - "cache_creation_input_token_cost": 3.75e-07, - "cache_read_input_audio_token_cost": 2e-07, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_audio_token": 2e-06, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_200k_tokens": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1.2e-05, - "output_cost_per_token_above_200k_tokens": 1.8e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, + "perplexity/anthropic/claude-haiku-5-5": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_adaptive_thinking": true, + "supports_web_search": true, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "input_cost_per_token": 1e-07, + "output_cost_per_token": 5e-07, + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token_above_100k_tokens": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "cache_read_input_token_cost_above_100k_tokens": 5e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, - "openrouter/~moonshotai/kimi-latest": { - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, + "us-gov.anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 6e-07, + "output_cost_per_token_above_100k_tokens": 3e-06, + "cache_creation_input_token_cost_above_100k_tokens": 7.5e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06, + "cache_read_input_token_cost_above_100k_tokens": 6e-08, + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.5e-07, + "cache_creation_input_token_cost_above_1hr": 2.4e-07, + "cache_read_input_token_cost": 1.2e-08, + "input_cost_per_token": 1.2e-07, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 6e-07, + "supports_forced_tool_use": true, + "thinking_always_on": false, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "thinking_on_by_default": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, - "supports_pdf_input": false, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": false + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-haiku-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, - "openrouter/~openai/gpt-astra-latest": { - "cache_creation_input_token_cost": 1.25e-05, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, - "cache_read_input_token_cost": 1e-06, - "cache_read_input_token_cost_above_272k_tokens": 2e-06, - "input_cost_per_token": 1e-05, - "input_cost_per_token_above_272k_tokens": 2e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, + "us.anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 5.5e-07, + "output_cost_per_token_above_100k_tokens": 2.75e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5.5e-08, + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 1.375e-07, + "cache_creation_input_token_cost_above_1hr": 2.2e-07, + "cache_read_input_token_cost": 1.1e-08, + "input_cost_per_token": 1.1e-07, + "litellm_provider": "bedrock_converse", + "token_count_model": { + "model": "us.anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + }, + "supports_tool_search": true, + "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 5e-05, - "output_cost_per_token_above_272k_tokens": 7.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 5.5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_on_by_default": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, - "openrouter/~openai/gpt-luna-latest": { + "vertex_ai/claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5e-08, + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 1.25e-07, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, + "cache_creation_input_token_cost_above_1hr": 2e-07, + "cache_creation_input_token_cost_batches": 6.25e-08, "cache_read_input_token_cost": 1e-08, - "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "cache_read_input_token_cost_batches": 5e-09, "input_cost_per_token": 1e-07, - "input_cost_per_token_above_272k_tokens": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, + "input_cost_per_token_batches": 5e-08, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, - "output_cost_per_token_above_272k_tokens": 7.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token_batches": 2.5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_on_by_default": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, - "openrouter/~openai/gpt-mini-latest": { - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_token": 7.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, + "vertex_ai/claude-haiku-latest": { + "alias_of": "vertex_ai/claude-haiku-5-5" + }, + "vertex_ai/claude-haiku-5-5@default": { + "input_cost_per_token_above_100k_tokens": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5e-08, + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_1hr": 2e-07, + "cache_creation_input_token_cost_batches": 6.25e-08, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_batches": 5e-09, + "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 4.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 5e-07, + "output_cost_per_token_batches": 2.5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_on_by_default": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, - "openrouter/~openai/gpt-sol-latest": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_272k_tokens": 4e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "microsoft_365_copilot/chat": { + "litellm_provider": "microsoft_365_copilot", "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "supports_mid_conversation_system": true, + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0 + }, + "us.twelvelabs.pegasus-1-5-v1:0": { + "input_cost_per_video_per_second": 0.00049, + "litellm_provider": "bedrock", + "max_input_tokens": 261120, + "max_output_tokens": 98304, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-5.html", + "supports_video_input": true + }, + "global.twelvelabs.pegasus-1-5-v1:0": { + "input_cost_per_video_per_second": 0.00049, + "litellm_provider": "bedrock", + "max_input_tokens": 261120, + "max_output_tokens": 98304, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-5.html", + "supports_video_input": true + }, + "twelvelabs.pegasus-1-5-v1:0": { + "input_cost_per_video_per_second": 0.00049, + "litellm_provider": "bedrock", + "max_input_tokens": 261120, + "max_output_tokens": 98304, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-5.html", + "supports_video_input": true + }, + "azure_ai/Microsoft-Decision-1": { + "input_cost_per_token": 4.2e-08, + "litellm_provider": "azure_ai", + "max_input_tokens": 32768, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" + }, + "gpt-rosalind-discovery": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://developers.openai.com/api/docs/pricing" + }, + "chatgpt/gpt-rosalind-discovery": { + "litellm_provider": "chatgpt", + "mode": "responses", + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/responses" + ] + }, + "azure_ai/Cohere-Embed-V5-Fast": { + "deprecation_date": "2027-01-23", + "input_cost_per_image_token": 4e-07, + "input_cost_per_token": 8e-08, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 2048.0, + "source": "https://prices.azure.com/api/retail/prices?$filter=productName%20eq%20'Cohere%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/embeddings" + ], + "supported_modalities": [ + "text", + "image" + ], + "supports_embedding_image_input": true + }, + "azure_ai/Cohere-Embed-V5-Pro": { + "deprecation_date": "2027-01-23", + "input_cost_per_image_token": 4e-07, + "input_cost_per_token": 1.2e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 2048.0, + "source": "https://prices.azure.com/api/retail/prices?$filter=productName%20eq%20'Cohere%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/embeddings" + ], + "supported_modalities": [ + "text", + "image" + ], + "supports_embedding_image_input": true + }, + "scaledown/extract": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "scaledown", + "mode": "chat", + "supports_response_schema": false, + "supports_system_messages": false, + "supports_vision": false, + "supports_function_calling": false + }, + "scaledown/summarize": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "scaledown", + "mode": "chat", + "supports_system_messages": true, + "supports_vision": false, + "supports_function_calling": false + }, + "scaledown/compress": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "scaledown", + "mode": "chat", + "supports_system_messages": true, + "supports_function_calling": false, + "supports_vision": false + }, + "scaledown/classify": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "scaledown", + "mode": "chat", + "supports_system_messages": false, + "supports_vision": false, + "supports_function_calling": false + }, + "scaledown/decisions": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "scaledown", + "mode": "chat", + "supports_system_messages": false, + "supports_vision": false, + "supports_function_calling": false + }, + "vertex_ai/gemini-robotics-er-2-preview": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 1e-06, + "litellm_provider": "vertex_ai", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 5e-06, + "output_cost_per_token": 5e-06, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "web_search_billing_unit": "per_query" }, - "openrouter/~openai/gpt-terra-latest": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_272k_tokens": 4e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "gemini-robotics-er-2-preview": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 1e-06, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 131072, + "max_output_tokens": 65536, "mode": "chat", - "output_cost_per_token": 1.2e-05, - "output_cost_per_token_above_272k_tokens": 1.8e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_reasoning_token": 5e-06, + "output_cost_per_token": 5e-06, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "web_search_billing_unit": "per_query" }, - "openrouter/~x-ai/grok-latest": { - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "gemini/gemini-4-argon": { + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "cache_read_input_token_cost_flex": 5e-08, + "cache_read_input_token_cost_priority": 1.8e-07, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token": 2e-06, - "input_cost_per_token_above_200k_tokens": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 500000, - "max_output_tokens": 450000, - "max_tokens": 450000, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.6e-06, + "litellm_provider": "gemini", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 6e-06, - "output_cost_per_token_above_200k_tokens": 1.2e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_reasoning_token": 1e-05, + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_flex": 5e-06, + "output_cost_per_token_priority": 1.8e-05, + "prompt_cache_min_tokens": 4096.0, + "rpm": 2000.0, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_computer_use": true, + "supports_continuation": true, "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "tpm": 800000.0, + "web_search_billing_unit": "per_query" }, - "openrouter/~z-ai/glm-flash-latest": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1310720, - "max_output_tokens": 943718, - "max_tokens": 943718, + "vertex_ai/gemini-4-argon": { + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "cache_read_input_token_cost_flex": 5e-08, + "cache_read_input_token_cost_priority": 1.8e-07, + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token": 2e-06, + "input_cost_per_audio_token_batches": 1e-06, + "input_cost_per_audio_token_priority": 3.6e-06, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.6e-06, + "litellm_provider": "vertex_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_reasoning_token": 1e-05, + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_flex": 5e-06, + "output_cost_per_token_priority": 1.8e-05, + "prompt_cache_min_tokens": 6144.0, + "regional_endpoint_uplift_multiplier": 1.1, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_computer_use": true, + "supports_continuation": true, "supports_function_calling": true, - "supports_pdf_input": false, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, "supports_vision": true, - "supports_web_search": false + "supports_web_search": true, + "web_search_billing_unit": "per_query" }, - "openrouter/~z-ai/glm-latest": { - "cache_read_input_token_cost": 1.2142e-07, - "input_cost_per_token": 6.538e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1310720, - "max_output_tokens": 131072, - "max_tokens": 131072, + "vertex_ai/gemini-4-argon-cyber-permissive": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "cache_read_input_token_cost_flex": 1e-07, + "cache_read_input_token_cost_priority": 3.6e-07, + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token": 4e-06, + "input_cost_per_audio_token_batches": 2e-06, + "input_cost_per_audio_token_priority": 7.2e-06, + "input_cost_per_token": 4e-06, + "input_cost_per_token_batches": 2e-06, + "input_cost_per_token_flex": 2e-06, + "input_cost_per_token_priority": 7.2e-06, + "litellm_provider": "vertex_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 2.0548e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_reasoning_token": 2e-05, + "output_cost_per_token": 2e-05, + "output_cost_per_token_batches": 1e-05, + "output_cost_per_token_flex": 1e-05, + "output_cost_per_token_priority": 3.6e-05, + "prompt_cache_min_tokens": 6144.0, + "regional_endpoint_uplift_multiplier": 1.1, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_continuation": true, "supports_function_calling": true, - "supports_pdf_input": false, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "web_search_billing_unit": "per_query" }, - "openrouter/aion-labs/aion-2.0": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "github_copilot/gemini-4-argon": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 65536, "mode": "chat", - "output_cost_per_token": 1.6e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions" + ], "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, + "supports_parallel_function_calling": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_vision": true }, - "openrouter/aion-labs/aion-3.0": { - "cache_read_input_token_cost": 7.5e-07, - "input_cost_per_token": 3e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "openinfer/@oi/GLM-5.3-Flash": { + "max_input_tokens": 393216, + "max_output_tokens": 393216, + "input_cost_per_token": 1.95e-07, + "output_cost_per_token": 1.56e-06, + "litellm_provider": "openinfer", "mode": "chat", - "output_cost_per_token": 6e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "source": "https://api.openinfer.ai/v1/models" }, - "openrouter/aion-labs/aion-3.0-mini": { - "cache_read_input_token_cost": 1.8e-07, - "input_cost_per_token": 7e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, + "openinfer/@oi/Qwen3.5-27B": { + "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, + "input_cost_per_token": 1.95e-07, + "output_cost_per_token": 1.56e-06, + "litellm_provider": "openinfer", "mode": "chat", - "output_cost_per_token": 1.4e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "source": "https://api.openinfer.ai/v1/models" }, - "openrouter/aion-labs/aion-3.5": { - "cache_read_input_token_cost": 7.5e-07, - "input_cost_per_token": 3e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, + "openinfer/@oi/Qwen3.5-9B": { + "max_input_tokens": 100000, + "max_output_tokens": 100000, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 1.5e-07, + "litellm_provider": "openinfer", "mode": "chat", - "output_cost_per_token": 6e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "source": "https://api.openinfer.ai/v1/models" }, - "openrouter/aion-labs/aion-3.5-mini": { - "cache_read_input_token_cost": 1.8e-07, - "input_cost_per_token": 7e-07, - "litellm_provider": "openrouter", + "xai/grok-voice-3.0": { + "input_cost_per_second": 0.001333333333333, + "input_cost_per_text_message": 0.004, + "litellm_provider": "xai", + "mode": "realtime", + "source": "https://docs.x.ai/developers/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true + }, + "xai/grok-voice-latest": { + "input_cost_per_second": 0.001333333333333, + "input_cost_per_text_message": 0.004, + "litellm_provider": "xai", + "mode": "realtime", + "source": "https://docs.x.ai/developers/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true + }, + "xai/grok-voice-2.0": { + "input_cost_per_second": 0.001333333333333, + "input_cost_per_text_message": 0.004, + "litellm_provider": "xai", + "mode": "realtime", + "source": "https://docs.x.ai/developers/pricing", + "successor_model": "xai/grok-voice-3.0", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true + }, + "together_ai/nvidia/NVIDIA-Nemotron-3.5-Super-VL": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 262144, "mode": "chat", - "output_cost_per_token": 1.4e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 5e-07, + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, + "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/aion-labs/aion-rp-llama-3.1-8b": { - "input_cost_per_token": 8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 29491, - "max_tokens": 29491, - "mode": "chat", - "output_cost_per_token": 1.6e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false + "supports_vision": true }, - "openrouter/amazon/nova-2-lite-v1": { - "input_cost_per_token": 3e-07, - "litellm_provider": "openrouter", + "jp.amazon.nova-2-lite-v1:0": { + "cache_read_input_token_cost": 9.9e-08, + "cache_read_input_token_cost_flex": 4.95e-08, + "cache_read_input_token_cost_priority": 1.7325e-07, + "input_cost_per_token": 3.96e-07, + "input_cost_per_token_batches": 1.98e-07, + "input_cost_per_token_flex": 1.98e-07, + "input_cost_per_token_priority": 6.93e-07, + "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 64000, "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 3.311e-06, + "output_cost_per_token_batches": 1.6555e-06, + "output_cost_per_token_flex": 1.6555e-06, + "output_cost_per_token_priority": 5.79425e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/ap-northeast-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, - "supports_prompt_caching": false, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": false, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/amazon/nova-lite-v1": { - "input_cost_per_token": 6e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 300000, - "max_output_tokens": 5120, - "max_tokens": 5120, - "mode": "chat", - "output_cost_per_token": 2.4e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/amazon/nova-micro-v1": { - "input_cost_per_token": 3.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 5120, - "max_tokens": 5120, - "mode": "chat", - "output_cost_per_token": 1.4e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false + "supports_video_input": true, + "supports_vision": true }, - "openrouter/amazon/nova-premier-v1": { - "cache_read_input_token_cost": 6.25e-07, - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "vertex_ai/deepseek-ai/deepseek-v4.1-flash-maas": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "vertex_ai-deepseek_models", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 1.25e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1.2e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_regions": [ + "global" + ], + "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_pdf_input": false, "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/amazon/nova-pro-v1": { - "input_cost_per_token": 8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 300000, - "max_output_tokens": 5120, - "max_tokens": 5120, - "mode": "chat", - "output_cost_per_token": 3.2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/anthracite-org/magnum-v4-72b": { - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, + "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false + "supports_tool_choice": true, + "supports_vision": true }, - "openrouter/anthropic/claude-fable-5:batch": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 5e-06, - "litellm_provider": "openrouter", + "azure_ai/claude-opus-5-5-fast": { + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_read_input_token_cost": 4e-07, + "deprecation_date": "2027-01-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "input_cost_per_token": 8e-06, + "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 4e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": {"search_context_size_high":0.02,"search_context_size_low":0.02,"search_context_size_medium":0.02}, + "source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_xhigh_reasoning_effort": true, + "supports_web_search": true, + "thinking_always_on": true }, - "openrouter/anthropic/claude-fable-5.1:batch": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "cache_read_input_token_cost": 1.25e-07, - "input_cost_per_token": 5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "baseten/meta-models/muse-spark-open": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 2.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 4.25e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_audio_input": true, "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, + "supports_response_schema": false, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_vision": true }, - "openrouter/anthropic/claude-haiku-4.5:batch": { - "cache_creation_input_token_cost": 6.25e-07, - "cache_creation_input_token_cost_above_1hr": 1e-06, - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "baseten/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 5e-07, + "source": "https://inference.baseten.co/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_vision": true }, - "openrouter/anthropic/claude-opus-4.1:batch": { - "cache_creation_input_token_cost": 9.375e-06, - "cache_creation_input_token_cost_above_1hr": 1.5e-05, - "cache_read_input_token_cost": 7.5e-07, - "input_cost_per_token": 7.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "wandb/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "wandb", + "max_input_tokens": 1049000, + "max_output_tokens": 943718, "mode": "chat", - "output_cost_per_token": 3.75e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 5e-07, + "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference", "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_vision": true }, - "openrouter/anthropic/claude-opus-4.5:batch": { - "cache_creation_input_token_cost": 3.125e-06, - "cache_creation_input_token_cost_above_1hr": 5e-06, - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "together_ai/reflection/Beam-1.0-501B-A23B": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 4e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 1.25e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1.2e-06, + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_response_schema": true }, - "openrouter/anthropic/claude-opus-4.6:batch": { - "cache_creation_input_token_cost": 3.125e-06, - "cache_creation_input_token_cost_above_1hr": 5e-06, - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "baseten/reflection/Beam-1.0": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 4e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 1.25e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1.2e-06, + "source": "https://inference.baseten.co/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_tool_choice": true }, - "openrouter/anthropic/claude-opus-4.7:batch": { - "cache_creation_input_token_cost": 3.125e-06, - "cache_creation_input_token_cost_above_1hr": 5e-06, - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "nebius/reflection/beam": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "nebius", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 1.25e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1e-06, + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "supports_function_calling": true, + "supports_reasoning": true, + "cache_read_input_token_cost": 5e-08 + }, + "baseten/deepseek-ai/DeepSeek-V4.1-Flash-1017": { + "cache_read_input_token_cost": 7e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://inference.baseten.co/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_vision": true }, - "openrouter/anthropic/claude-opus-4.8:batch": { - "cache_creation_input_token_cost": 3.125e-06, - "cache_creation_input_token_cost_above_1hr": 5e-06, - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "baseten/deepseek-ai/DeepSeek-V4.1-Flash-1017-Fast": { + "cache_read_input_token_cost": 1.4e-08, + "input_cost_per_token": 6e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, "mode": "chat", - "output_cost_per_token": 1.25e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 2.4e-06, + "source": "https://inference.baseten.co/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_vision": true }, - "openrouter/anthropic/claude-opus-5:batch": { - "cache_creation_input_token_cost": 3.125e-06, - "cache_creation_input_token_cost_above_1hr": 5e-06, - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017": { + "cache_read_input_token_cost": 6e-09, + "cache_read_input_token_cost_priority": 7.5e-09, + "input_cost_per_token": 3e-07, + "input_cost_per_token_priority": 3.75e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, "mode": "chat", - "output_cost_per_token": 1.25e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_priority": 1.5e-06, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, - "supports_pdf_input": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_vision": true }, - "openrouter/anthropic/claude-sonnet-4.5:batch": { - "cache_creation_input_token_cost": 1.875e-06, - "cache_creation_input_token_cost_above_1hr": 3e-06, - "cache_creation_input_token_cost_above_200k_tokens": 3.75e-06, - "cache_read_input_token_cost": 1.5e-07, - "cache_read_input_token_cost_above_200k_tokens": 3e-07, - "input_cost_per_token": 1.5e-06, - "input_cost_per_token_above_200k_tokens": 3e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "fireworks_ai/accounts/fireworks/routers/deepseek-flash-latest": { + "cache_read_input_token_cost": 6e-09, + "cache_read_input_token_cost_priority": 7.5e-09, + "input_cost_per_token": 3e-07, + "input_cost_per_token_priority": 3.75e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, "mode": "chat", - "output_cost_per_token": 7.5e-06, - "output_cost_per_token_above_200k_tokens": 1.125e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_priority": 1.5e-06, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, - "supports_pdf_input": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_vision": true }, - "openrouter/anthropic/claude-sonnet-4.6:batch": { - "cache_creation_input_token_cost": 1.875e-06, - "cache_creation_input_token_cost_above_1hr": 3e-06, - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 1.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "github_copilot/claude-sonnet-4.6": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2026-09-01", + "input_cost_per_token": 3e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 64000, "mode": "chat", - "output_cost_per_token": 7.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/messages" + ], + "supports_adaptive_thinking": true, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_legacy_thinking": true, + "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_vision": true }, - "openrouter/anthropic/claude-sonnet-5:batch": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost_above_1hr": 2e-06, - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, + "github_copilot/gpt-5.4-nano": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "github_copilot", + "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "mode": "responses", + "output_cost_per_token": 1.25e-06, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/responses" + ], "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/arcee-ai/trinity-large-thinking": { - "cache_read_input_token_cost": 6e-08, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 80000, - "max_tokens": 80000, - "mode": "chat", - "output_cost_per_token": 8e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/baidu/ernie-4.5-vl-424b-a47b": { - "deprecation_date": "2026-10-08", - "input_cost_per_token": 4.2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 123000, - "max_output_tokens": 16000, - "max_tokens": 16000, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": false + "supports_vision": true }, - "openrouter/bytedance-seed/seed-1.6": { - "deprecation_date": "2026-11-11", - "input_cost_per_token": 2.5e-07, - "input_cost_per_token_above_128k_tokens": 5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, + "github_copilot/grok-4.5": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "deprecation_date": "2026-10-19", + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 500000, + "max_output_tokens": 500000, "mode": "chat", - "output_cost_per_token": 2e-06, - "output_cost_per_token_above_128k_tokens": 4e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions" + ], "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, + "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "supports_vision": true }, - "openrouter/bytedance-seed/seed-1.6-flash": { - "deprecation_date": "2026-11-11", - "input_cost_per_token": 7.5e-08, - "input_cost_per_token_above_128k_tokens": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, + "github_copilot/grok-4.6": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 500000, + "max_output_tokens": 500000, "mode": "chat", - "output_cost_per_token": 3e-07, - "output_cost_per_token_above_128k_tokens": 8e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions" + ], "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, + "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "supports_vision": true }, - "openrouter/bytedance-seed/seed-2-1-turbo": { - "input_cost_per_token": 5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, + "github_copilot/grok-4.7": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 500000, + "max_output_tokens": 500000, "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions" + ], "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, + "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "supports_vision": true }, - "openrouter/bytedance-seed/seed-2.0-code": { - "deprecation_date": "2026-11-11", - "input_cost_per_token": 5e-07, - "input_cost_per_token_above_128k_tokens": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 131072, - "max_tokens": 131072, + "github_copilot/grok-latest": { + "alias_of": "github_copilot/grok-4.7" + }, + "together_ai/deepseek-ai/DeepSeek-V4.1-Flash-1017": { + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 3e-06, - "output_cost_per_token_above_128k_tokens": 6e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1.2e-06, + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "supports_vision": true }, - "openrouter/bytedance-seed/seed-2.0-lite": { - "input_cost_per_token": 2.5e-07, - "input_cost_per_token_above_128k_tokens": 5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 131072, - "max_tokens": 131072, + "meta/muse-image-1.0": { + "litellm_provider": "meta", + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://dev.meta.ai/docs/pricing-rate-limits", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "image" + ] + }, + "fireworks_ai/accounts/fireworks/models/minimax-m3p1-flash": { + "cache_read_input_token_cost": 1.5e-08, + "cache_read_input_token_cost_priority": 2.25e-08, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_priority": 2.25e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 2e-06, - "output_cost_per_token_above_128k_tokens": 4e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 6e-07, + "output_cost_per_token_priority": 9e-07, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "supports_vision": true }, - "openrouter/bytedance-seed/seed-2.0-mini": { - "input_cost_per_token": 1e-07, - "input_cost_per_token_above_128k_tokens": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 131072, - "max_tokens": 131072, + "meta/sam-3.1": { + "input_cost_per_image": 0.0025, + "litellm_provider": "meta", + "mode": "responses", + "source": "https://dev.meta.ai/docs/pricing-rate-limits.md", + "supported_endpoints": [ + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text" + ] + }, + "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017-us": { + "cache_read_input_token_cost": 9e-09, + "cache_read_input_token_cost_priority": 1.125e-08, + "input_cost_per_token": 4.5e-07, + "input_cost_per_token_priority": 5.625e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, "mode": "chat", - "output_cost_per_token": 4e-07, - "output_cost_per_token_above_128k_tokens": 8e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1.8e-06, + "output_cost_per_token_priority": 2.25e-06, + "source": "https://docs.fireworks.ai/serverless/us-only-serverless", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/cognitivecomputations/dolphin-mistral-24b-venice-edition": { - "input_cost_per_token": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 9e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/cohere/command-a": { - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 256000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false + "supports_vision": true }, - "openrouter/cohere/command-r-08-2024": { - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "wandb/reflection/Beam-1.0-501B-A23B": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "wandb", + "max_input_tokens": 1049000, "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1e-06, + "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_vision": false }, - "openrouter/cohere/command-r-plus-08-2024": { - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "wandb/zai-org/GLM-5.3": { + "cache_read_input_token_cost": 1.9e-07, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "wandb", + "max_input_tokens": 1049000, "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 3e-06, + "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference", "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/cohere/command-r7b-12-2024": { - "input_cost_per_token": 3.75e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 4000, - "max_tokens": 4000, - "mode": "chat", - "output_cost_per_token": 1.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false + "supports_vision": false }, - "openrouter/cohere/north-mini-code:free": { - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", + "azure_ai/MAI-Code-1.1-Flash": { + "cache_read_input_token_cost": 2e-08, + "deprecation_date": "2026-12-09", + "input_cost_per_token": 2e-07, + "litellm_provider": "azure_ai", "max_input_tokens": 256000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": false, "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_vision": true }, - "openrouter/dots-studio/dots-3-note-preview:free": { - "deprecation_date": "2026-12-31", - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 512000, - "max_output_tokens": 460800, - "max_tokens": 460800, - "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "opencode_go/grok-4.7": { + "litellm_provider": "opencode_go", + "mode": "responses", + "supported_endpoints": [ + "/v1/responses" + ], + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 5e-07, + "max_output_tokens": 500000, + "max_input_tokens": 500000, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": false + "tiered_pricing": [ + { + "range": [ + 0, + 200000 + ], + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 5e-07 + }, + { + "range": [ + 200000, + 500000 + ], + "input_cost_per_token": 4e-06, + "output_cost_per_token": 1.2e-05, + "cache_read_input_token_cost": 1e-06 + } + ], + "source": "https://opencode.ai/v2/docs/console/go/" }, - "openrouter/google/gemini-2.5-flash-lite:batch": { - "cache_read_input_audio_token_cost": 3e-08, + "opencode_go/gpt-6-luna": { + "litellm_provider": "opencode_go", + "mode": "responses", + "supported_endpoints": [ + "/v1/responses" + ], + "input_cost_per_token": 1.0000000000000001e-07, + "output_cost_per_token": 5e-07, "cache_read_input_token_cost": 1e-08, - "input_cost_per_audio_token": 1.5e-07, - "input_cost_per_token": 5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, + "cache_creation_input_token_cost": 1.25e-07, + "max_output_tokens": 128000, + "max_input_tokens": 922000, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true + "tiered_pricing": [ + { + "range": [ + 0, + 272000 + ], + "input_cost_per_token": 1.0000000000000001e-07, + "output_cost_per_token": 5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_creation_input_token_cost": 1.25e-07 + }, + { + "range": [ + 272000, + 1050000 + ], + "input_cost_per_token": 2.0000000000000002e-07, + "output_cost_per_token": 7.5e-07, + "cache_read_input_token_cost": 2e-08, + "cache_creation_input_token_cost": 2.5e-07 + } + ], + "source": "https://opencode.ai/v2/docs/console/go/" }, - "openrouter/google/gemini-2.5-flash:batch": { - "cache_read_input_audio_token_cost": 1e-07, - "cache_read_input_token_cost": 3e-08, - "deprecation_date": "2026-10-20", - "input_cost_per_audio_token": 5e-07, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, + "opencode_go/gpt-5.6-luna": { + "litellm_provider": "opencode_go", + "mode": "responses", + "supported_endpoints": [ + "/v1/responses" + ], + "input_cost_per_token": 2.0000000000000002e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 2e-08, + "cache_creation_input_token_cost": 2.5e-07, + "max_output_tokens": 128000, + "max_input_tokens": 922000, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true + "tiered_pricing": [ + { + "range": [ + 0, + 272000 + ], + "input_cost_per_token": 2.0000000000000002e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 2e-08, + "cache_creation_input_token_cost": 2.5e-07 + }, + { + "range": [ + 272000, + 1050000 + ], + "input_cost_per_token": 4.0000000000000003e-07, + "output_cost_per_token": 1.8000000000000001e-06, + "cache_read_input_token_cost": 4e-08, + "cache_creation_input_token_cost": 5e-07 + } + ], + "source": "https://opencode.ai/v2/docs/console/go/" }, - "openrouter/google/gemini-2.5-pro:batch": { - "cache_read_input_audio_token_cost": 1.25e-07, - "cache_read_input_token_cost": 1.25e-07, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, - "deprecation_date": "2026-10-20", - "input_cost_per_audio_token": 6.25e-07, - "input_cost_per_token": 6.25e-07, - "input_cost_per_token_above_200k_tokens": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "opencode_go/claude-haiku-5-5": { + "litellm_provider": "opencode_go", "mode": "chat", - "output_cost_per_token": 5e-06, - "output_cost_per_token_above_200k_tokens": 7.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, + "supported_endpoints": [ + "/v1/messages" + ], + "input_cost_per_token": 1.0000000000000001e-07, + "output_cost_per_token": 5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_creation_input_token_cost": 1.25e-07, + "max_output_tokens": 128000, + "max_input_tokens": 1000000, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-3-flash-preview:batch": { - "input_cost_per_audio_token": 5e-07, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true + "tiered_pricing": [ + { + "range": [ + 0, + 100000 + ], + "input_cost_per_token": 1.0000000000000001e-07, + "output_cost_per_token": 5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_creation_input_token_cost": 1.25e-07 + }, + { + "range": [ + 100000, + 1000000 + ], + "input_cost_per_token": 5e-07, + "output_cost_per_token": 2.5e-06, + "cache_read_input_token_cost": 5.0000000000000004e-08, + "cache_creation_input_token_cost": 6.25e-07 + } + ], + "source": "https://opencode.ai/v2/docs/console/go/" }, - "openrouter/google/gemini-3.1-flash-lite:batch": { - "cache_read_input_audio_token_cost": 2.5e-08, - "cache_read_input_token_cost": 1.25e-08, - "input_cost_per_audio_token": 2.5e-07, - "input_cost_per_token": 1.25e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "opencode_go/gemini-4-argon": { + "litellm_provider": "opencode_go", "mode": "chat", - "output_cost_per_token": 7.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, + "supported_endpoints": [ + "/v1beta/models" + ], + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1e-07, + "max_output_tokens": 65536, + "max_input_tokens": 1048576, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true + "source": "https://opencode.ai/v2/docs/console/go/" }, - "openrouter/google/gemini-3.1-pro-preview:batch": { - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_200k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "opencode_go/glm-5.3-flash": { + "litellm_provider": "opencode_go", "mode": "chat", - "output_cost_per_token": 6e-06, - "output_cost_per_token_above_200k_tokens": 9e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 5e-07, + "cache_read_input_token_cost": 3e-08, + "max_output_tokens": 131072, + "max_input_tokens": 1000000, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true + "source": "https://opencode.ai/v2/docs/console/go/" }, - "openrouter/google/gemini-3.5-flash-lite:batch": { - "cache_read_input_audio_token_cost": 1.5e-08, - "cache_read_input_token_cost": 1.5e-08, - "input_cost_per_audio_token": 1.5e-07, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "opencode_go/glm-5.3": { + "litellm_provider": "opencode_go", "mode": "chat", - "output_cost_per_token": 1.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "cache_read_input_token_cost": 2.6e-07, + "max_output_tokens": 131072, + "max_input_tokens": 1000000, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true + "supports_vision": false, + "source": "https://opencode.ai/v2/docs/console/go/" }, - "openrouter/google/gemini-3.5-flash:batch": { - "cache_read_input_audio_token_cost": 1.5e-07, - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_audio_token": 1.5e-06, - "input_cost_per_token": 7.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "opencode_go/glm-5.2": { + "litellm_provider": "opencode_go", "mode": "chat", - "output_cost_per_token": 4.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "cache_read_input_token_cost": 2.6e-07, + "max_output_tokens": 131072, + "max_input_tokens": 1000000, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true + "supports_vision": false, + "source": "https://opencode.ai/v2/docs/console/go/" }, - "openrouter/google/gemini-3.6-flash:batch": { - "cache_creation_input_token_cost": 4.16666666666667e-08, - "cache_read_input_audio_token_cost": 3.75e-08, - "cache_read_input_token_cost": 3.75e-08, - "input_cost_per_audio_token": 3.75e-07, - "input_cost_per_token": 3.75e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "opencode_go/kimi-k3.1-pro": { + "litellm_provider": "opencode_go", "mode": "chat", - "output_cost_per_token": 1.875e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 2.0000000000000002e-07, + "cache_creation_input_token_cost": 2e-06, + "max_output_tokens": 131072, + "max_input_tokens": 1048576, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true + "source": "https://opencode.ai/v2/docs/console/go/" }, - "openrouter/google/gemini-3.7-flash:batch": { - "cache_creation_input_token_cost": 4.16666666666667e-08, - "cache_read_input_audio_token_cost": 3.75e-08, - "cache_read_input_token_cost": 3.75e-08, - "input_cost_per_audio_token": 3.75e-07, - "input_cost_per_token": 3.75e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "opencode_go/kimi-k3": { + "litellm_provider": "opencode_go", "mode": "chat", - "output_cost_per_token": 1.875e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "cache_read_input_token_cost": 3e-07, + "cache_creation_input_token_cost": 3e-06, + "max_output_tokens": 131072, + "max_input_tokens": 1048576, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true + "source": "https://opencode.ai/v2/docs/console/go/" }, - "openrouter/google/gemini-3.8-flash:batch": { - "cache_creation_input_token_cost": 4.16666666666667e-08, - "cache_read_input_audio_token_cost": 3.75e-08, - "cache_read_input_token_cost": 3.75e-08, - "input_cost_per_audio_token": 3.75e-07, - "input_cost_per_token": 3.75e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "opencode_go/kimi-k2.7-code": { + "litellm_provider": "opencode_go", "mode": "chat", - "output_cost_per_token": 1.875e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 9.499999999999999e-07, + "output_cost_per_token": 4e-06, + "cache_read_input_token_cost": 1.9e-07, + "max_output_tokens": 262144, + "max_input_tokens": 262144, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true + "source": "https://opencode.ai/v2/docs/console/go/" }, - "openrouter/ibm-granite/granite-4.0-h-micro": { - "input_cost_per_token": 1.7e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131000, - "max_output_tokens": 117900, - "max_tokens": 117900, + "opencode_go/longcat-2.0": { + "litellm_provider": "opencode_go", "mode": "chat", - "output_cost_per_token": 1.12e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 6e-09, + "max_output_tokens": 131072, + "max_input_tokens": 1000000, + "supports_function_calling": true, + "supports_reasoning": true, "supports_vision": false, - "supports_web_search": false + "source": "https://opencode.ai/v2/docs/console/go/" }, - "openrouter/ibm-granite/granite-4.2-8b": { - "cache_read_input_token_cost": 1.5e-08, - "input_cost_per_token": 6e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, + "opencode_go/deepseek-v4.1-flash": { + "litellm_provider": "opencode_go", "mode": "chat", - "output_cost_per_token": 2.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 6e-09, + "max_output_tokens": 384000, + "max_input_tokens": 1000000, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_vision": true, + "source": "https://opencode.ai/v2/docs/console/go/" }, - "openrouter/inception/mercury-2": { - "cache_read_input_token_cost": 2.5e-08, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 50000, - "max_tokens": 50000, + "opencode_go/deepseek-v4-pro": { + "litellm_provider": "opencode_go", "mode": "chat", - "output_cost_per_token": 7.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 1.32e-06, + "output_cost_per_token": 3.96e-06, + "cache_read_input_token_cost": 4.4e-08, + "max_output_tokens": 384000, + "max_input_tokens": 1000000, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, "supports_vision": false, - "supports_web_search": false + "source": "https://opencode.ai/v2/docs/console/go/" }, - "openrouter/inception/mercury-2.5": { - "cache_read_input_token_cost": 4e-09, - "input_cost_per_token": 4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 260000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "opencode_go/mimo-v2.6-flash": { + "litellm_provider": "opencode_go", "mode": "chat", - "output_cost_per_token": 1.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 2.8e-07, + "cache_read_input_token_cost": 2.8e-09, + "max_output_tokens": 131072, + "max_input_tokens": 1048576, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_vision": true, + "source": "https://opencode.ai/v2/docs/console/go/" }, - "openrouter/inclusionai/ling-3.0-flash": { - "cache_read_input_token_cost": 4.2e-09, - "input_cost_per_token": 2.1e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, + "opencode_go/mimo-v2.6-pro": { + "litellm_provider": "opencode_go", "mode": "chat", - "output_cost_per_token": 6.3e-08, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 4.35e-07, + "output_cost_per_token": 8.7e-07, + "cache_read_input_token_cost": 3.625e-09, + "max_output_tokens": 131072, + "max_input_tokens": 1048576, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_vision": true, + "source": "https://opencode.ai/v2/docs/console/go/" }, - "openrouter/inclusionai/ling-3.0-flash-fin": { - "cache_read_input_token_cost": 1.2e-08, - "input_cost_per_token": 6e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, + "opencode_go/mimo-v2.5": { + "litellm_provider": "opencode_go", "mode": "chat", - "output_cost_per_token": 1.8e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 2.8e-07, + "cache_read_input_token_cost": 2.8e-09, + "max_output_tokens": 128000, + "max_input_tokens": 1000000, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_vision": true, + "source": "https://opencode.ai/v2/docs/console/go/" }, - "openrouter/inclusionai/ling-3.0-flash-fin:free": { - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, + "opencode_go/mimo-v2.5-pro": { + "litellm_provider": "opencode_go", "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 4.35e-07, + "output_cost_per_token": 8.7e-07, + "cache_read_input_token_cost": 3.625e-09, + "max_output_tokens": 128000, + "max_input_tokens": 1048576, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, "supports_vision": false, - "supports_web_search": false + "source": "https://opencode.ai/v2/docs/console/go/" }, - "openrouter/inclusionai/ling-3.0-flash-sante:free": { - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, + "opencode_go/minimax-m3.1-flash": { + "litellm_provider": "opencode_go", "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "cache_read_input_token_cost": 1.5e-08, + "max_output_tokens": 512000, + "max_input_tokens": 1000000, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_vision": true, + "source": "https://opencode.ai/v2/docs/console/go/" }, - "openrouter/inclusionai/ling-3.0-flash-vl": { - "cache_read_input_token_cost": 4.2e-09, - "input_cost_per_token": 2.1e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, + "opencode_go/minimax-m3": { + "litellm_provider": "opencode_go", "mode": "chat", - "output_cost_per_token": 6.16e-08, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "supported_endpoints": [ + "/v1/messages" + ], + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 6e-08, + "max_output_tokens": 131072, + "max_input_tokens": 1000000, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": false + "source": "https://opencode.ai/v2/docs/console/go/" }, - "openrouter/inclusionai/ling-3.0-flash-vl:free": { - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "opencode_go/muse-spark-1.3-contributor": { + "litellm_provider": "opencode_go", + "mode": "responses", + "supported_endpoints": [ + "/v1/responses" + ], + "input_cost_per_token": 1.0000000000000001e-07, + "output_cost_per_token": 2.0000000000000002e-07, + "cache_read_input_token_cost": 2e-09, + "max_output_tokens": 131072, + "max_input_tokens": 1048576, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": false + "source": "https://opencode.ai/v2/docs/console/go/" }, - "openrouter/inference-net/schematron-v2-small": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "opencode_go/muse-spark-1.2-contributor": { + "litellm_provider": "opencode_go", + "mode": "responses", + "supported_endpoints": [ + "/v1/responses" + ], + "input_cost_per_token": 1.0000000000000001e-07, + "output_cost_per_token": 2.0000000000000002e-07, + "cache_read_input_token_cost": 2e-09, + "max_output_tokens": 131072, + "max_input_tokens": 1048576, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "opencode_go/qwen3.8-max": { + "litellm_provider": "opencode_go", "mode": "chat", - "output_cost_per_token": 2.3e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false + "supported_endpoints": [ + "/v1/messages" + ], + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 2.5e-07, + "cache_creation_input_token_cost": 2.5e-06, + "max_output_tokens": 131072, + "max_input_tokens": 1000000, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://opencode.ai/v2/docs/console/go/" }, - "openrouter/inference-net/schematron-v2-turbo": { - "cache_read_input_token_cost": 3e-08, - "input_cost_per_token": 3e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "opencode_go/qwen3.8-flash": { + "litellm_provider": "opencode_go", "mode": "chat", - "output_cost_per_token": 1.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false + "supported_endpoints": [ + "/v1/messages" + ], + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 4.6999999999999995e-07, + "cache_read_input_token_cost": 1.6e-08, + "cache_creation_input_token_cost": 2.0000000000000002e-07, + "max_output_tokens": 131072, + "max_input_tokens": 1000000, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://opencode.ai/v2/docs/console/go/" }, - "openrouter/kwaipilot/kat-coder-pro-v2.5": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 7.4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, + "opencode_go/qwen3.7-plus": { + "litellm_provider": "opencode_go", "mode": "chat", - "output_cost_per_token": 2.96e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "supported_endpoints": [ + "/v1/messages" + ], + "input_cost_per_token": 4.0000000000000003e-07, + "output_cost_per_token": 1.6000000000000001e-06, + "cache_read_input_token_cost": 4e-08, + "cache_creation_input_token_cost": 5e-07, + "max_output_tokens": 65536, + "max_input_tokens": 1000000, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_reasoning": true, + "supports_vision": true, + "tiered_pricing": [ + { + "range": [ + 0, + 256000 + ], + "input_cost_per_token": 4.0000000000000003e-07, + "output_cost_per_token": 1.6000000000000001e-06, + "cache_read_input_token_cost": 4e-08, + "cache_creation_input_token_cost": 5e-07 + }, + { + "range": [ + 256000, + 1000000 + ], + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 4.8e-06, + "cache_read_input_token_cost": 1.2e-07, + "cache_creation_input_token_cost": 1.5e-06 + } + ], + "source": "https://opencode.ai/v2/docs/console/go/" }, - "openrouter/liquid/lfm-2.5-2.6b:free": { - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 8192, - "max_tokens": 8192, + "opencode_go/hy4-preview": { + "litellm_provider": "opencode_go", "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 8.34e-07, + "output_cost_per_token": 2.501e-06, + "cache_read_input_token_cost": 4.2000000000000006e-08, + "max_output_tokens": 64000, + "max_input_tokens": 1024000, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, "supports_vision": false, - "supports_web_search": false + "source": "https://opencode.ai/v2/docs/console/go/" }, - "openrouter/meituan/longcat-2.0": { - "cache_read_input_token_cost": 6e-09, - "input_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048756, - "max_output_tokens": 262144, - "max_tokens": 262144, + "opencode_go/hy3": { + "litellm_provider": "opencode_go", "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 5.8e-07, + "cache_read_input_token_cost": 3.5e-08, + "max_output_tokens": 128000, + "max_input_tokens": 192000, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, "supports_vision": false, - "supports_web_search": false + "source": "https://opencode.ai/v2/docs/console/go/" }, - "openrouter/meta/muse-glimmer-30b": { - "cache_read_input_token_cost": 4e-08, - "input_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, + "opencode_go/longcat-2.5-preview-free": { + "litellm_provider": "opencode_go", "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 0, + "output_cost_per_token": 0, + "cache_read_input_token_cost": 0, + "max_output_tokens": 131072, + "max_input_tokens": 1000000, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": false + "source": "https://opencode.ai/v2/docs/console/go/" }, - "openrouter/meta/muse-spark-1.1": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, + "opencode_go/step-5-preview": { + "litellm_provider": "opencode_go", "mode": "chat", - "output_cost_per_token": 4.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 1e-06, + "output_cost_per_token": 2.7e-06, + "cache_read_input_token_cost": 1.0000000000000001e-07, + "max_output_tokens": 65536, + "max_input_tokens": 1000000, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "source": "https://opencode.ai/v2/docs/console/go/" }, - "openrouter/meta/muse-spark-1.2": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", + "opencode_go/beam-free": { + "litellm_provider": "opencode_go", + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 0, + "output_cost_per_token": 0, + "cache_read_input_token_cost": 0, + "max_output_tokens": 131072, "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "bedrock/claude_platform/claude-fable-5": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, + "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_batches": 5e-07, + "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 4.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, + "output_cost_per_token": 5e-05, + "output_cost_per_token_batches": 2.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "prompt_cache_min_tokens": 512, + "supports_native_structured_output": true, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" }, - "openrouter/meta/muse-spark-1.2-contributor": { - "cache_read_input_token_cost": 2e-09, - "input_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, + "bedrock/claude_platform/claude-fable-5-1": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, + "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_batches": 1.25e-07, + "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, + "output_cost_per_token": 5e-05, + "output_cost_per_token_batches": 2.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "prompt_cache_min_tokens": 512, + "supports_native_structured_output": true, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" }, - "openrouter/meta/muse-spark-1.3": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, + "bedrock/claude_platform/claude-haiku-4-5": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_1hr": 2e-06, + "cache_creation_input_token_cost_batches": 6.25e-07, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 64000, "mode": "chat", - "output_cost_per_token": 4.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, + "output_cost_per_token": 5e-06, + "output_cost_per_token_batches": 2.5e-06, + "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "prompt_cache_min_tokens": 4096, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" }, - "openrouter/meta/muse-spark-1.3-contributor": { - "cache_read_input_token_cost": 2e-09, + "bedrock/claude_platform/claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens_batches": 2.5e-07, + "output_cost_per_token_above_100k_tokens_batches": 1.25e-06, + "cache_creation_input_token_cost_above_100k_tokens_batches": 3.125e-07, + "cache_read_input_token_cost_above_100k_tokens_batches": 2.5e-08, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_1hr": 2e-07, + "cache_creation_input_token_cost_batches": 6.25e-08, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_batches": 5e-09, "input_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, + "input_cost_per_token_batches": 5e-08, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, + "output_cost_per_token": 5e-07, + "output_cost_per_token_batches": 2.5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_on_by_default": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true - }, - "openrouter/microsoft/phi-4": { - "input_cost_per_token": 7e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 16384, - "max_output_tokens": 14745, - "max_tokens": 14745, - "mode": "chat", - "output_cost_per_token": 1.4e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/microsoft/wizardlm-2-8x22b": { - "input_cost_per_token": 6.2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 65535, - "max_output_tokens": 8000, - "max_tokens": 8000, - "mode": "chat", - "output_cost_per_token": 6.2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, + "prompt_cache_min_tokens": 512, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing", + "supports_web_search": true, + "input_cost_per_token_above_100k_tokens": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5e-08 }, - "openrouter/mistralai/codestral-2508:batch": { - "cache_read_input_token_cost": 1.5e-08, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 256000, - "max_output_tokens": 204800, - "max_tokens": 204800, + "bedrock/claude_platform/claude-opus-4-5": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, + "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 64000, "mode": "chat", - "output_cost_per_token": 4.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": false, + "supports_thinking_cache_preservation": true, + "supports_reasoning": true, "supports_response_schema": true, + "supports_native_structured_output": true, "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_vision": true, + "supports_output_config": true, + "prompt_cache_min_tokens": 4096, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" }, - "openrouter/mistralai/ministral-8b-2512:batch": { - "cache_read_input_token_cost": 7.5e-09, - "input_cost_per_token": 7.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, + "bedrock/claude_platform/claude-opus-4-6": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, + "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 7.5e-08, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, - "supports_pdf_input": false, + "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": false, + "supports_thinking_cache_preservation": true, + "supports_reasoning": true, "supports_response_schema": true, + "supports_native_structured_output": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": false + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "supports_max_reasoning_effort": true, + "prompt_cache_min_tokens": 4096, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" }, - "openrouter/mistralai/mistral-large-2512": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, + "bedrock/claude_platform/claude-opus-4-7": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, + "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": false, + "supports_thinking_cache_preservation": true, + "supports_reasoning": true, "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": false + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "prompt_cache_min_tokens": 2048, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" }, - "openrouter/mistralai/mistral-large-2512:batch": { - "cache_read_input_token_cost": 2.5e-08, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, + "bedrock/claude_platform/claude-opus-4-8": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, + "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 7.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": false, + "supports_thinking_cache_preservation": true, + "supports_reasoning": true, "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": false + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "prompt_cache_min_tokens": 1024, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" }, - "openrouter/mistralai/mistral-medium-3-5:batch": { - "input_cost_per_token": 7.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, + "bedrock/claude_platform/claude-opus-5": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, + "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3.75e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_on_by_default": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, - "supports_prompt_caching": false, + "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": false + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "prompt_cache_min_tokens": 512, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" }, - "openrouter/mistralai/mistral-medium-3.1:batch": { - "cache_read_input_token_cost": 2e-08, - "input_cost_per_token": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 104857, - "max_tokens": 104857, + "bedrock/claude_platform/claude-opus-5-5": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_1hr": 8e-06, + "cache_creation_input_token_cost_batches": 2.5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "input_cost_per_token": 4e-06, + "input_cost_per_token_batches": 2e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 2e-05, + "output_cost_per_token_batches": 1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": false, + "supports_reasoning": true, "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": false + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "prompt_cache_min_tokens": 512, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" }, - "openrouter/mistralai/mistral-small-2603:batch": { - "cache_read_input_token_cost": 7.5e-09, - "input_cost_per_token": 7.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, + "bedrock/claude_platform/claude-sonnet-4-5": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "cache_creation_input_token_cost_batches": 1.875e-06, + "cache_read_input_token_cost_batches": 1.5e-07, + "deprecation_date": "2026-11-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "bedrock/claude_platform/claude-sonnet-5-5", + "input_cost_per_token_batches": 1.5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 64000, "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_batches": 7.5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, - "supports_pdf_input": false, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_native_structured_output": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": false + "prompt_cache_min_tokens": 1024, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" }, - "openrouter/moonshotai/kimi-k3:batch": { - "cache_read_input_token_cost": 2.28e-07, - "input_cost_per_token": 2.28e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 16384, - "max_tokens": 16384, + "bedrock/claude_platform/claude-sonnet-4-6": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_creation_input_token_cost_batches": 1.875e-06, + "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_batches": 1.5e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_batches": 1.5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.14e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_batches": 7.5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, - "supports_pdf_input": false, + "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": false + "supports_output_config": true, + "prompt_cache_min_tokens": 1024, + "provider_specific_entry": { + "us": 1.1 + }, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" }, - "openrouter/morph/morph-v3-fast": { - "input_cost_per_token": 8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 81920, - "max_output_tokens": 38000, - "max_tokens": 38000, + "bedrock/claude_platform/claude-sonnet-5": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_creation_input_token_cost_batches": 1.25e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/morph/morph-v3-large": { - "input_cost_per_token": 9e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.9e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/nex-agi/nex-n2.5-mini:free": { - "deprecation_date": "2026-09-25", - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/nex-agi/nex-n2.5-pro:free": { - "deprecation_date": "2026-09-25", - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/nousresearch/hermes-3-llama-3.1-405b": { - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/nousresearch/hermes-3-llama-3.1-70b": { - "input_cost_per_token": 7e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 7e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/nousresearch/hermes-4-405b": { - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, - "mode": "chat", - "output_cost_per_token": 3e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-3.5-turbo-0613": { - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 4095, - "max_output_tokens": 3685, - "max_tokens": 3685, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-3.5-turbo:batch": { - "input_cost_per_token": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 7.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": true - }, - "openrouter/openai/gpt-4-turbo:batch": { - "input_cost_per_token": 5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-4.1-mini:batch": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 8e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_on_by_default": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": false, + "supports_thinking_cache_preservation": true, + "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "prompt_cache_min_tokens": 1024, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" }, - "openrouter/openai/gpt-4.1-nano:batch": { - "cache_read_input_token_cost": 1.25e-08, - "input_cost_per_token": 5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, + "bedrock/claude_platform/claude-sonnet-5-5": { + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_creation_input_token_cost_batches": 1.25e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": false, + "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing", "supports_web_search": true }, - "openrouter/openai/gpt-4.1:batch": { - "cache_read_input_token_cost": 2.5e-07, + "gpt-6.1-terra": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_12hr": 2.5e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 2.5e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 2.5e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_above_12hr_batches": 1.25e-06, + "cache_creation_input_token_cost_above_12hr_flex": 1.25e-06, + "cache_creation_input_token_cost_above_12hr_priority": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_batches": 1.25e-06, + "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 5e-06, + "cache_creation_input_token_cost_batches": 6.25e-07, + "cache_creation_input_token_cost_flex": 6.25e-07, + "cache_creation_input_token_cost_priority": 2.5e-06, + "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_above_272k_tokens": 1e-07, + "cache_read_input_token_cost_above_272k_tokens_batches": 5e-08, + "cache_read_input_token_cost_above_272k_tokens_flex": 5e-08, + "cache_read_input_token_cost_above_272k_tokens_priority": 2e-07, + "cache_read_input_token_cost_batches": 2.5e-08, + "cache_read_input_token_cost_flex": 2.5e-08, + "cache_read_input_token_cost_priority": 1e-07, "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, + "input_cost_per_token_above_272k_tokens": 2e-06, + "input_cost_per_token_above_272k_tokens_batches": 1e-06, + "input_cost_per_token_above_272k_tokens_flex": 1e-06, + "input_cost_per_token_above_272k_tokens_priority": 4e-06, + "input_cost_per_token_batches": 5e-07, + "input_cost_per_token_flex": 5e-07, + "input_cost_per_token_priority": 2e-06, + "litellm_provider": "openai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 4e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_272k_tokens": 7.5e-06, + "output_cost_per_token_above_272k_tokens_batches": 3.75e-06, + "output_cost_per_token_above_272k_tokens_flex": 3.75e-06, + "output_cost_per_token_above_272k_tokens_priority": 1.5e-05, + "output_cost_per_token_batches": 2.5e-06, + "output_cost_per_token_flex": 2.5e-06, + "output_cost_per_token_priority": 1e-05, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard", + "pro" + ], + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, - "supports_reasoning": false, + "supports_reasoning": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true }, - "openrouter/openai/gpt-4o-mini:batch": { - "cache_read_input_token_cost": 3.75e-08, - "input_cost_per_token": 7.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "gpt-terra-latest": { + "alias_of": "gpt-6.1-terra" + }, + "chatgpt/gpt-6.1-terra": { + "litellm_provider": "chatgpt", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "responses", + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_xhigh_reasoning_effort": true }, - "openrouter/openai/gpt-4o:batch": { - "cache_read_input_token_cost": 6.25e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "global.openai.gpt-6.1-terra": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, + "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_above_272k_tokens": 1e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_272k_tokens": 2e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 922000, + "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token_above_272k_tokens": 7.5e-06, + "source": "https://developers.openai.com/api/docs/models/gpt-6.1-terra", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_bedrock_converse_tool_result_images": false, + "supports_bedrock_runtime_chat_completions_response_format": true, "supports_function_calling": true, - "supports_pdf_input": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, + "supports_reasoning": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_xhigh_reasoning_effort": true }, - "openrouter/openai/gpt-5-image": { - "cache_read_input_token_cost": 1.25e-06, - "input_cost_per_token": 1e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": true + "bedrock/gpt-terra-latest": { + "alias_of": "global.openai.gpt-6.1-terra" }, - "openrouter/openai/gpt-5-image-mini": { - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, + "us.openai.gpt-6.1-terra": { + "cache_creation_input_token_cost": 1.375e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.75e-06, + "cache_read_input_token_cost": 5.5e-08, + "cache_read_input_token_cost_above_272k_tokens": 1.1e-07, + "input_cost_per_token": 1.1e-06, + "input_cost_per_token_above_272k_tokens": 2.2e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": true, + "output_cost_per_token": 5.5e-06, + "output_cost_per_token_above_272k_tokens": 8.25e-06, + "source": "https://developers.openai.com/api/docs/models/gpt-6.1-terra", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_bedrock_converse_tool_result_images": false, + "supports_bedrock_runtime_chat_completions_response_format": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": false, + "supports_sampling_params": false, + "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_xhigh_reasoning_effort": true }, - "openrouter/openai/gpt-5-mini:batch": { - "cache_read_input_token_cost": 1.25e-08, - "input_cost_per_token": 1.25e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, + "baseten/decision-models/baseten-elephant-9b-latest": { + "input_cost_per_token": 3.5e-08, + "litellm_provider": "baseten", + "max_input_tokens": 16384, + "mode": "decisions", + "output_cost_per_token": 0.0, + "source": "https://inference.baseten.co/v1/models", + "supports_vision": true + }, + "baseten/decision-models/baseten-mammoth-27b-latest": { + "input_cost_per_token": 1e-07, + "litellm_provider": "baseten", + "max_input_tokens": 16384, + "mode": "decisions", + "output_cost_per_token": 0.0, + "source": "https://inference.baseten.co/v1/models", + "supports_vision": true + }, + "github_copilot/gpt-6.1-terra": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, + "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_above_272k_tokens": 1e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_272k_tokens": 2e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "mode": "responses", + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_272k_tokens": 7.5e-06, + "source": "https://github.blog/changelog/2026-10-26-gpt-6-1-terra-in-github-copilot", + "supported_endpoints": [ + "/v1/responses" + ], "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_vision": true }, - "openrouter/openai/gpt-5-nano:batch": { - "cache_read_input_token_cost": 2.5e-09, - "input_cost_per_token": 2.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "github_copilot/gpt-terra-latest": { + "alias_of": "github_copilot/gpt-6.1-terra" + }, + "refuseless/glm-5.3-abliterated": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "refuseless", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 2e-06, + "source": "https://refuseless.com/pricing", "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_vision": false, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ] }, - "openrouter/openai/gpt-5-pro:batch": { - "input_cost_per_token": 7.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "refuseless/glm-5.3-flash-abliterated": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 1.2e-07, + "litellm_provider": "refuseless", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 6e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 5e-07, + "source": "https://refuseless.com/pricing", "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_vision": false, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ] }, - "openrouter/openai/gpt-5:batch": { - "cache_read_input_token_cost": 6.25e-08, - "input_cost_per_token": 6.25e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "refuseless/deepseek-v4.1-flash-abliterated": { + "cache_read_input_token_cost": 3.5e-08, + "input_cost_per_token": 1.4e-07, + "litellm_provider": "refuseless", + "max_input_tokens": 1048576, + "max_output_tokens": 130000, "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 5e-07, + "source": "https://refuseless.com/pricing", "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_vision": false, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ] }, - "openrouter/openai/gpt-5.1:batch": { - "cache_read_input_token_cost": 6.25e-08, - "input_cost_per_token": 6.25e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "refuseless/deepseek-v4.1-flash-fast": { + "cache_read_input_token_cost": 3e-09, + "input_cost_per_token": 5e-08, + "litellm_provider": "refuseless", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 1.5e-07, + "source": "https://refuseless.com/pricing", "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_vision": false, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ] }, - "openrouter/openai/gpt-5.2-pro:batch": { - "input_cost_per_token": 1.05e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "refuseless/minimax-m3.1-flash": { + "cache_read_input_token_cost": 2e-09, + "input_cost_per_token": 5e-08, + "litellm_provider": "refuseless", + "max_input_tokens": 1048576, + "max_output_tokens": 512000, "mode": "chat", - "output_cost_per_token": 8.4e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "output_cost_per_token": 2.5e-07, + "source": "https://refuseless.com/pricing", "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_vision": false, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ] }, - "openrouter/openai/gpt-5.2:batch": { - "cache_read_input_token_cost": 8.75e-08, - "input_cost_per_token": 8.75e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, + "fireworks_ai/accounts/fireworks/models/rune": { + "cache_read_input_token_cost": 8.4e-09, + "input_cost_per_token": 4.2e-08, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 262144, + "mode": "decisions", + "output_cost_per_token": 0.0, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested" + }, + "bedrock_mantle/openai.gpt-6.1-terra": { + "cache_creation_input_token_cost": 1.375e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.75e-06, + "cache_read_input_token_cost": 5.5e-08, + "cache_read_input_token_cost_above_272k_tokens": 1.1e-07, + "input_cost_per_token": 1.1e-06, + "input_cost_per_token_above_272k_tokens": 2.2e-06, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 7e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, + "mode": "responses", + "output_cost_per_token": 5.5e-06, + "output_cost_per_token_above_272k_tokens": 8.25e-06, + "search_context_cost_per_query": {"search_context_size_high":0.012,"search_context_size_low":0.012,"search_context_size_medium":0.012}, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-terra.html", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, - "supports_pdf_input": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": true, + "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true, + "use_openai_responses_path": true }, - "openrouter/openai/gpt-5.4-image-2": { - "cache_read_input_token_cost": 2e-06, - "input_cost_per_token": 8e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "bedrock_mantle/gpt-terra-latest": { + "alias_of": "bedrock_mantle/openai.gpt-6.1-terra" + }, + "clf_ai_gateway/glm-5.3": { + "metadata": { + "comment": "Billed price checked 2026-10-29, which the gateway shows as 60% off a list price 2.5x higher. Update the rows when the discount ends." + }, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 5.6e-07, + "output_cost_per_token": 1.76e-06, + "cache_read_input_token_cost": 1.04e-07, + "litellm_provider": "clf_ai_gateway", "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, "supports_reasoning": true, + "reasoning_effort_levels": [ + "low", + "medium", + "high", + "max" + ], "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": true + "supports_system_messages": true, + "supports_prompt_caching": true, + "source": "https://clfaigateway.dev/models" }, - "openrouter/openai/gpt-5.4-mini:batch": { - "cache_read_input_token_cost": 3.75e-08, - "input_cost_per_token": 3.75e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "clf_ai_gateway/glm-5.3-flash": { + "metadata": { + "comment": "Billed price checked 2026-10-29, which the gateway shows as 60% off a list price 2.5x higher. Update the rows when the discount ends." + }, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 2e-07, + "cache_read_input_token_cost": 1.2e-08, + "litellm_provider": "clf_ai_gateway", "mode": "chat", - "output_cost_per_token": 2.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, "supports_reasoning": true, + "reasoning_effort_levels": [ + "low", + "medium", + "high", + "xhigh", + "max" + ], "supports_response_schema": true, - "supports_tool_choice": true, + "supports_system_messages": true, + "supports_prompt_caching": true, "supports_vision": true, - "supports_web_search": true + "source": "https://clfaigateway.dev/models" }, - "openrouter/openai/gpt-5.4-nano:batch": { - "cache_read_input_token_cost": 1e-08, - "input_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "clf_ai_gateway/glm-5.2": { + "metadata": { + "comment": "Billed price checked 2026-10-29, which the gateway shows as 60% off a list price 2.5x higher. Update the rows when the discount ends." + }, + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "input_cost_per_token": 5.6e-07, + "output_cost_per_token": 1.76e-06, + "cache_read_input_token_cost": 1.04e-07, + "litellm_provider": "clf_ai_gateway", "mode": "chat", - "output_cost_per_token": 6.25e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, "supports_reasoning": true, + "reasoning_effort_levels": [ + "low", + "medium", + "high", + "xhigh", + "max" + ], "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_system_messages": true, + "supports_prompt_caching": true, + "source": "https://clfaigateway.dev/models" }, - "openrouter/openai/gpt-5.4-pro:batch": { - "input_cost_per_token": 1.5e-05, - "input_cost_per_token_above_272k_tokens": 3e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "clf_ai_gateway/glm-4.7-flash": { + "metadata": { + "comment": "Billed price checked 2026-10-29, which the gateway shows as 60% off a list price 2.5x higher. Update the rows when the discount ends." + }, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 2.4e-08, + "output_cost_per_token": 1.6e-07, + "litellm_provider": "clf_ai_gateway", "mode": "chat", - "output_cost_per_token": 9e-05, - "output_cost_per_token_above_272k_tokens": 0.000135, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, "supports_reasoning": true, + "reasoning_effort_levels": [ + "low", + "medium", + "high" + ], "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_system_messages": true, + "source": "https://clfaigateway.dev/models" }, - "openrouter/openai/gpt-5.4:batch": { - "cache_read_input_token_cost": 1.25e-07, - "cache_read_input_token_cost_above_272k_tokens": 2.5e-07, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_272k_tokens": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "clf_ai_gateway/deepseek-v4-pro": { + "metadata": { + "comment": "Billed price checked 2026-10-29, which the gateway shows as 60% off a list price 2.5x higher. Update the rows when the discount ends." + }, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 5.28e-07, + "output_cost_per_token": 1.584e-06, + "cache_read_input_token_cost": 1.7e-08, + "litellm_provider": "clf_ai_gateway", "mode": "chat", - "output_cost_per_token": 7.5e-06, - "output_cost_per_token_above_272k_tokens": 1.125e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, "supports_reasoning": true, + "reasoning_effort_levels": [ + "low", + "medium", + "high", + "xhigh", + "max" + ], "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_system_messages": true, + "supports_prompt_caching": true, + "source": "https://clfaigateway.dev/models" }, - "openrouter/openai/gpt-5.5-pro:batch": { - "input_cost_per_token": 1.5e-05, - "input_cost_per_token_above_272k_tokens": 3e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "clf_ai_gateway/deepseek-v4-flash": { + "metadata": { + "comment": "Billed price checked 2026-10-29, which the gateway shows as 60% off a list price 2.5x higher. Update the rows when the discount ends." + }, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 1.76e-07, + "output_cost_per_token": 5.28e-07, + "cache_read_input_token_cost": 5e-09, + "litellm_provider": "clf_ai_gateway", "mode": "chat", - "output_cost_per_token": 9e-05, - "output_cost_per_token_above_272k_tokens": 0.000135, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, "supports_reasoning": true, + "reasoning_effort_levels": [ + "low", + "medium", + "high", + "xhigh", + "max" + ], "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_system_messages": true, + "supports_prompt_caching": true, + "source": "https://clfaigateway.dev/models" }, - "openrouter/openai/gpt-5.5:batch": { - "cache_read_input_token_cost": 2.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 5e-07, - "input_cost_per_token": 2.5e-06, - "input_cost_per_token_above_272k_tokens": 5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "clf_ai_gateway/deepseek-v4.1-flash": { + "metadata": { + "comment": "Billed price checked 2026-10-29, which the gateway shows as 60% off a list price 2.5x higher. Update the rows when the discount ends." + }, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 4.8e-07, + "cache_read_input_token_cost": 2e-09, + "litellm_provider": "clf_ai_gateway", "mode": "chat", - "output_cost_per_token": 1.5e-05, - "output_cost_per_token_above_272k_tokens": 2.25e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, "supports_reasoning": true, + "reasoning_effort_levels": [ + "none", + "low", + "medium", + "high", + "xhigh", + "max" + ], "supports_response_schema": true, - "supports_tool_choice": true, + "supports_system_messages": true, + "supports_prompt_caching": true, "supports_vision": true, - "supports_web_search": true + "source": "https://clfaigateway.dev/models" }, - "openrouter/openai/gpt-5.6-luna-pro:batch": { - "cache_read_input_token_cost": 1e-08, - "cache_read_input_token_cost_above_272k_tokens": 2e-08, - "input_cost_per_token": 1e-07, - "input_cost_per_token_above_272k_tokens": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "clf_ai_gateway/kimi-k2.6": { + "metadata": { + "comment": "Billed price checked 2026-10-29, which the gateway shows as 60% off a list price 2.5x higher. Update the rows when the discount ends." + }, + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "input_cost_per_token": 3.8e-07, + "output_cost_per_token": 1.6e-06, + "cache_read_input_token_cost": 6.4e-08, + "litellm_provider": "clf_ai_gateway", "mode": "chat", - "output_cost_per_token": 6e-07, - "output_cost_per_token_above_272k_tokens": 9e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, "supports_reasoning": true, + "reasoning_effort_levels": [ + "none", + "low", + "medium", + "high" + ], "supports_response_schema": true, - "supports_tool_choice": true, + "supports_system_messages": true, + "supports_prompt_caching": true, "supports_vision": true, - "supports_web_search": true + "source": "https://clfaigateway.dev/models" }, - "openrouter/openai/gpt-5.6-luna:batch": { - "cache_read_input_token_cost": 1e-08, - "cache_read_input_token_cost_above_272k_tokens": 2e-08, - "input_cost_per_token": 1e-07, - "input_cost_per_token_above_272k_tokens": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "clf_ai_gateway/kimi-k2.7-code": { + "metadata": { + "comment": "Billed price checked 2026-10-29, which the gateway shows as 60% off a list price 2.5x higher. Update the rows when the discount ends." + }, + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "input_cost_per_token": 3.8e-07, + "output_cost_per_token": 1.6e-06, + "cache_read_input_token_cost": 7.6e-08, + "litellm_provider": "clf_ai_gateway", "mode": "chat", - "output_cost_per_token": 6e-07, - "output_cost_per_token_above_272k_tokens": 9e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, "supports_reasoning": true, + "reasoning_effort_levels": [ + "low", + "medium", + "high" + ], "supports_response_schema": true, - "supports_tool_choice": true, + "supports_system_messages": true, + "supports_prompt_caching": true, "supports_vision": true, - "supports_web_search": true + "source": "https://clfaigateway.dev/models" }, - "openrouter/openai/gpt-5.6-sol-pro:batch": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_272k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "clf_ai_gateway/qwen3.8-27b": { + "metadata": { + "comment": "Billed price checked 2026-10-29, which the gateway shows as 60% off a list price 2.5x higher. Update the rows when the discount ends." + }, + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "input_cost_per_token": 1.8e-07, + "output_cost_per_token": 1.28e-06, + "cache_read_input_token_cost": 2e-08, + "litellm_provider": "clf_ai_gateway", "mode": "chat", - "output_cost_per_token": 5e-06, - "output_cost_per_token_above_272k_tokens": 7.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, "supports_reasoning": true, + "reasoning_effort_levels": [ + "low", + "medium", + "xhigh" + ], "supports_response_schema": true, - "supports_tool_choice": true, + "supports_system_messages": true, + "supports_prompt_caching": true, "supports_vision": true, - "supports_web_search": true + "source": "https://clfaigateway.dev/models" }, - "openrouter/openai/gpt-5.6-sol:batch": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_272k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, + "kyma/claude-fable-5": { + "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, + "input_cost_per_token": 1.35e-05, + "output_cost_per_token": 6.75e-05, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 5e-06, - "output_cost_per_token_above_272k_tokens": 7.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_vision": true, + "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_pdf_input": true, + "supports_adaptive_thinking": true, + "thinking_always_on": true }, - "openrouter/openai/gpt-5.6-terra-pro:batch": { - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_272k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, + "kyma/claude-fable-5.1": { + "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, + "input_cost_per_token": 1.35e-05, + "output_cost_per_token": 6.75e-05, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 6e-06, - "output_cost_per_token_above_272k_tokens": 9e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, "supports_pdf_input": true, + "supports_adaptive_thinking": true, + "thinking_always_on": true + }, + "kyma/claude-haiku-4-5": { + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "input_cost_per_token": 1.35e-06, + "cache_read_input_token_cost": 1.35e-07, + "output_cost_per_token": 6.75e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_pdf_input": false, + "prompt_cache_min_tokens": 4096 }, - "openrouter/openai/gpt-5.6-terra:batch": { - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_272k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, + "kyma/claude-haiku-5.5": { + "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, + "input_cost_per_token": 1.35e-07, + "cache_read_input_token_cost": 1.35e-08, + "output_cost_per_token": 6.75e-07, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 6e-06, - "output_cost_per_token_above_272k_tokens": 9e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": true, + "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_pdf_input": true, + "supports_adaptive_thinking": true, + "thinking_always_on": false, + "prompt_cache_min_tokens": 512 }, - "openrouter/openai/gpt-6-astra-pro:batch": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05, - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "input_cost_per_token": 5e-06, - "input_cost_per_token_above_272k_tokens": 1e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, + "kyma/claude-opus-4-7": { + "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, + "input_cost_per_token": 6.75e-06, + "cache_read_input_token_cost": 6.75e-07, + "output_cost_per_token": 3.375e-05, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 2.5e-05, - "output_cost_per_token_above_272k_tokens": 3.75e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": true, + "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_pdf_input": false, + "supports_adaptive_thinking": true, + "prompt_cache_min_tokens": 2048 }, - "openrouter/openai/gpt-6-astra:batch": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05, - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "input_cost_per_token": 5e-06, - "input_cost_per_token_above_272k_tokens": 1e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, + "kyma/claude-opus-5": { + "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, + "input_cost_per_token": 6.75e-06, + "cache_read_input_token_cost": 6.75e-07, + "output_cost_per_token": 3.375e-05, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 2.5e-05, - "output_cost_per_token_above_272k_tokens": 3.75e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": true, + "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_pdf_input": true, + "supports_adaptive_thinking": true, + "prompt_cache_min_tokens": 512 }, - "openrouter/openai/gpt-6-luna": { - "cache_creation_input_token_cost": 1.25e-07, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, - "cache_read_input_token_cost": 1e-08, - "cache_read_input_token_cost_above_272k_tokens": 2e-08, - "input_cost_per_token": 1e-07, - "input_cost_per_token_above_272k_tokens": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, + "kyma/claude-opus-5.5": { + "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, + "input_cost_per_token": 5.4e-06, + "cache_read_input_token_cost": 2.7e-07, + "output_cost_per_token": 2.7e-05, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 5e-07, - "output_cost_per_token_above_272k_tokens": 7.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": true, + "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_pdf_input": true, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512 }, - "openrouter/openai/gpt-6-luna-pro": { - "cache_creation_input_token_cost": 1.25e-07, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, - "cache_read_input_token_cost": 1e-08, - "cache_read_input_token_cost_above_272k_tokens": 2e-08, - "input_cost_per_token": 1e-07, - "input_cost_per_token_above_272k_tokens": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, + "kyma/claude-sonnet-4-6": { + "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, + "input_cost_per_token": 4.05e-06, + "cache_read_input_token_cost": 4.05e-07, + "output_cost_per_token": 2.025e-05, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 5e-07, - "output_cost_per_token_above_272k_tokens": 7.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": true, + "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_pdf_input": false, + "supports_adaptive_thinking": true, + "prompt_cache_min_tokens": 1024 }, - "openrouter/openai/gpt-6-sol": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_272k_tokens": 4e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, + "kyma/claude-sonnet-5": { + "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, + "input_cost_per_token": 2.7e-06, + "cache_read_input_token_cost": 2.7e-07, + "output_cost_per_token": 1.35e-05, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": true, + "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_pdf_input": true, + "supports_adaptive_thinking": true, + "prompt_cache_min_tokens": 1024 }, - "openrouter/openai/gpt-6-sol-pro": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_272k_tokens": 4e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, + "kyma/claude-sonnet-5.5": { + "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, + "input_cost_per_token": 2.7e-06, + "cache_read_input_token_cost": 1.35e-07, + "output_cost_per_token": 1.35e-05, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": true, + "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_pdf_input": true, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512 }, - "openrouter/openai/o3-mini:batch": { - "cache_read_input_token_cost": 2.75e-07, - "input_cost_per_token": 5.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "kyma/deepseek-r1": { + "max_input_tokens": 64000, + "max_output_tokens": 32768, + "input_cost_per_token": 7.425e-07, + "output_cost_per_token": 2.957e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 2.2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_vision": false, + "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, + "supports_pdf_input": false + }, + "kyma/deepseek-v3": { + "max_input_tokens": 160000, + "max_output_tokens": 8192, + "input_cost_per_token": 5.18e-07, + "output_cost_per_token": 7.571e-07, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, "supports_vision": false, - "supports_web_search": true + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false }, - "openrouter/openai/o3:batch": { - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "kyma/deepseek-v4-flash": { + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "input_cost_per_token": 1.23e-07, + "cache_read_input_token_cost": 2.43e-08, + "output_cost_per_token": 2.458e-07, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 4e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": true, + "supports_vision": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, + "supports_pdf_input": false + }, + "kyma/deepseek-v4-flash-vision-exp": { + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "input_cost_per_token": 3.892e-07, + "output_cost_per_token": 1.168e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, "supports_vision": true, - "supports_web_search": true + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false }, - "openrouter/openai/o4-mini:batch": { - "cache_read_input_token_cost": 1.375e-07, - "input_cost_per_token": 5.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "kyma/deepseek-v4.1-flash": { + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 2.7e-07, + "output_cost_per_token": 8.1e-07, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 2.2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": true, + "supports_vision": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/gemini-3-flash": { + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "input_cost_per_token": 6.75e-07, + "cache_read_input_token_cost": 6.75e-08, + "output_cost_per_token": 4.05e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, + "supports_pdf_input": false + }, + "kyma/gemini-3.1-pro": { + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "input_cost_per_token": 2.7e-06, + "cache_read_input_token_cost": 2.7e-07, + "output_cost_per_token": 1.62e-05, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, "supports_vision": true, - "supports_web_search": true + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true }, - "openrouter/perceptron/perceptron-mk1": { - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, + "kyma/gemini-3.5-flash": { + "max_input_tokens": 1048576, "max_output_tokens": 8192, - "max_tokens": 8192, + "input_cost_per_token": 2.025e-06, + "cache_read_input_token_cost": 2.025e-07, + "output_cost_per_token": 1.215e-05, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": false + "supports_pdf_input": false }, - "openrouter/perplexity/sonar": { - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 127072, - "max_output_tokens": 114364, - "max_tokens": 114364, + "kyma/gemini-3.5-flash-lite": { + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "input_cost_per_token": 4.05e-07, + "cache_read_input_token_cost": 4.05e-08, + "output_cost_per_token": 3.375e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 1e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, + "supports_function_calling": true, "supports_vision": true, - "supports_web_search": true + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false }, - "openrouter/perplexity/sonar-deep-research": { - "input_cost_per_token": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 115200, - "max_tokens": 115200, + "kyma/gemini-3.6-flash": { + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "input_cost_per_token": 1.013e-06, + "cache_read_input_token_cost": 1.0125e-07, + "output_cost_per_token": 5.063e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 8e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": true + "supports_pdf_input": false }, - "openrouter/perplexity/sonar-pro": { - "input_cost_per_token": 3e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 8000, - "max_tokens": 8000, + "kyma/gemini-3.7-flash": { + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "input_cost_per_token": 2.026e-06, + "cache_read_input_token_cost": 1.0125e-07, + "output_cost_per_token": 1.0126e-05, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, + "supports_function_calling": true, "supports_vision": true, - "supports_web_search": true + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true }, - "openrouter/perplexity/sonar-pro-search": { - "input_cost_per_token": 3e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 8000, - "max_tokens": 8000, + "kyma/gemini-3.8-flash": { + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "input_cost_per_token": 2.026e-06, + "output_cost_per_token": 1.0126e-05, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": false, + "supports_pdf_input": true + }, + "kyma/gemini-4-argon": { + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "input_cost_per_token": 5.4e-06, + "cache_read_input_token_cost": 2.7e-07, + "output_cost_per_token": 2.7e-05, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, "supports_vision": true, - "supports_web_search": true + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true }, - "openrouter/perplexity/sonar-reasoning-pro": { - "input_cost_per_token": 2e-06, - "litellm_provider": "openrouter", + "kyma/gemma-4-31b": { "max_input_tokens": 128000, - "max_output_tokens": 115200, - "max_tokens": 115200, + "max_output_tokens": 8192, + "input_cost_per_token": 1.642e-07, + "cache_read_input_token_cost": 1.642e-07, + "output_cost_per_token": 4.689e-07, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 8e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": false, + "supports_function_calling": true, "supports_vision": true, - "supports_web_search": true + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false }, - "openrouter/qwen/qwen3.8-27b:free": { - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, + "kyma/glm-4.5-air": { + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "input_cost_per_token": 1.797e-07, + "cache_read_input_token_cost": 3.375e-08, + "output_cost_per_token": 1.175e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, + "supports_vision": false, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "supports_pdf_input": false }, - "openrouter/rekaai/reka-edge": { - "input_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 16384, - "max_output_tokens": 14745, - "max_tokens": 14745, + "kyma/glm-4.7-flash": { + "max_input_tokens": 203000, + "max_output_tokens": 65536, + "input_cost_per_token": 8.1e-08, + "cache_read_input_token_cost": 1.35e-08, + "output_cost_per_token": 5.4e-07, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 1e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "supports_pdf_input": false }, - "openrouter/rekaai/reka-flash-3": { - "input_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 58982, - "max_tokens": 58982, + "kyma/glm-5.1": { + "max_input_tokens": 203000, + "max_output_tokens": 65536, + "input_cost_per_token": 1.89e-06, + "cache_read_input_token_cost": 2.7675e-07, + "output_cost_per_token": 5.94e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, + "supports_function_calling": true, + "supports_vision": false, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": false, + "supports_pdf_input": false + }, + "kyma/glm-5.2": { + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "input_cost_per_token": 9.029e-07, + "cache_read_input_token_cost": 2.9835e-07, + "output_cost_per_token": 3.083e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, "supports_vision": false, - "supports_web_search": false + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false }, - "openrouter/relace/relace-apply-3": { - "input_cost_per_token": 8.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 256000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "kyma/glm-5.3": { + "max_input_tokens": 1310720, + "max_output_tokens": 131072, + "input_cost_per_token": 1.178e-06, + "output_cost_per_token": 3.702e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 1.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, + "supports_function_calling": true, "supports_vision": false, - "supports_web_search": false + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false }, - "openrouter/relace/relace-search": { - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 256000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "kyma/glm-5.3-flash": { + "max_input_tokens": 1310720, + "max_output_tokens": 65536, + "input_cost_per_token": 1.72e-07, + "output_cost_per_token": 5.733e-07, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 3e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_pdf_input": false }, - "openrouter/sakana/fugu-max": { - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, + "kyma/gpt-5.6-luna": { + "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, + "input_cost_per_token": 2.944e-07, + "cache_read_input_token_cost": 2.7e-08, + "output_cost_per_token": 1.767e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 6e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": true, + "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_pdf_input": true }, - "openrouter/sakana/fugu-ultra": { - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "input_cost_per_token": 5e-06, - "input_cost_per_token_above_272k_tokens": 1e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, + "kyma/gpt-5.6-luna-pro": { + "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, + "input_cost_per_token": 2.703e-07, + "cache_read_input_token_cost": 2.7e-08, + "output_cost_per_token": 1.621e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 3e-05, - "output_cost_per_token_above_272k_tokens": 4.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": false, + "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_pdf_input": true }, - "openrouter/sakana/fugu-ultra-v2": { - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "input_cost_per_token": 5e-06, - "input_cost_per_token_above_272k_tokens": 1e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, + "kyma/gpt-5.6-sol": { + "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, + "input_cost_per_token": 5.4e-06, + "cache_read_input_token_cost": 6.75e-07, + "output_cost_per_token": 2.7e-05, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 3e-05, - "output_cost_per_token_above_272k_tokens": 4.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": true, + "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_pdf_input": true }, - "openrouter/sakana/sakana-namazu": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 9.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, + "kyma/gpt-5.6-sol-pro": { + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "input_cost_per_token": 5.4e-06, + "cache_read_input_token_cost": 6.75e-07, + "output_cost_per_token": 2.7e-05, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 4e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": true, + "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_pdf_input": true }, - "openrouter/sao10k/l3-lunaris-8b": { - "input_cost_per_token": 4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 8192, - "max_output_tokens": 7372, - "max_tokens": 7372, + "kyma/gpt-5.6-terra": { + "max_input_tokens": 1050000, + "max_output_tokens": 8192, + "input_cost_per_token": 2.7e-06, + "cache_read_input_token_cost": 2.7e-07, + "output_cost_per_token": 1.62e-05, + "input_cost_per_token_above_272k_tokens": 5.4e-06, + "output_cost_per_token_above_272k_tokens": 2.43e-05, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 5e-08, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false + "supports_pdf_input": false }, - "openrouter/sao10k/l3.1-euryale-70b": { - "input_cost_per_token": 8.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, + "kyma/gpt-5.6-terra-pro": { + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "input_cost_per_token": 2.7e-06, + "cache_read_input_token_cost": 2.7e-07, + "output_cost_per_token": 1.62e-05, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 8.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_pdf_input": true }, - "openrouter/sao10k/l3.3-euryale-70b": { - "input_cost_per_token": 6.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, + "kyma/gpt-6-astra": { + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "input_cost_per_token": 1.35e-05, + "cache_read_input_token_cost": 1.35e-06, + "output_cost_per_token": 6.75e-05, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 7.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false + "supports_pdf_input": false }, - "openrouter/stealth/space-bunny-alpha": { - "deprecation_date": "2098-12-31", - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, + "kyma/gpt-6-luna": { + "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, + "input_cost_per_token": 1.639e-07, + "cache_read_input_token_cost": 1.35e-08, + "output_cost_per_token": 8.195e-07, + "input_cost_per_token_above_272k_tokens": 2.7e-07, + "output_cost_per_token_above_272k_tokens": 1.0125e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true + "supports_response_schema": true, + "supports_pdf_input": true }, - "openrouter/stepfun/step-3.5-flash": { - "input_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, + "kyma/gpt-6.1-sol": { + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "input_cost_per_token": 2.7e-06, + "cache_read_input_token_cost": 1.35e-07, + "output_cost_per_token": 1.35e-05, + "input_cost_per_token_above_272k_tokens": 5.4e-06, + "output_cost_per_token_above_272k_tokens": 2.025e-05, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, + "supports_vision": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_response_schema": true, + "supports_pdf_input": true }, - "openrouter/stepfun/step-3.7-flash": { - "cache_read_input_token_cost": 4e-08, - "input_cost_per_token": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 230400, - "max_tokens": 230400, + "kyma/gpt-oss-120b": { + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "input_cost_per_token": 4.73e-08, + "output_cost_per_token": 2.303e-07, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 1.15e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": false, + "supports_vision": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "supports_pdf_input": false }, - "openrouter/tencent/hunyuan-a13b-instruct": { - "input_cost_per_token": 1.4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, + "kyma/grok-4.20": { + "max_input_tokens": 2000000, + "max_output_tokens": 8192, + "input_cost_per_token": 1.763e-06, + "output_cost_per_token": 3.528e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 5.7e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, + "supports_function_calling": true, + "supports_vision": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false + "supports_pdf_input": true }, - "openrouter/tencent/hy-mt2-1.8b": { - "input_cost_per_token": 4.4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, + "kyma/grok-4.20-multi-agent": { + "max_input_tokens": 2000000, + "max_output_tokens": 8192, + "input_cost_per_token": 1.767e-06, + "output_cost_per_token": 3.534e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 1.77e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": false, - "supports_pdf_input": false, + "supports_vision": true, "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true }, - "openrouter/tencent/hy-mt2-30b-a3b": { - "input_cost_per_token": 7.4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, + "kyma/grok-4.3": { + "max_input_tokens": 1000000, + "max_output_tokens": 32768, + "input_cost_per_token": 1.92e-06, + "cache_read_input_token_cost": 2.7e-07, + "output_cost_per_token": 3.838e-06, + "input_cost_per_token_above_200k_tokens": 3.375e-06, + "output_cost_per_token_above_200k_tokens": 6.75e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 2.95e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false + "supports_pdf_input": false }, - "openrouter/tencent/hy-mt2-7b": { - "input_cost_per_token": 7.4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, + "kyma/grok-4.5": { + "max_input_tokens": 500000, + "max_output_tokens": 8192, + "input_cost_per_token": 2.73e-06, + "output_cost_per_token": 8.189e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 2.95e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, + "supports_function_calling": true, + "supports_vision": true, "supports_prompt_caching": false, - "supports_reasoning": false, + "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false + "supports_pdf_input": true }, - "openrouter/tencent/hy3": { - "cache_read_input_token_cost": 3.3e-08, - "input_cost_per_token": 1.32e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 128000, - "max_tokens": 128000, + "kyma/grok-4.6": { + "max_input_tokens": 500000, + "max_output_tokens": 8192, + "input_cost_per_token": 2.758e-06, + "output_cost_per_token": 8.274e-06, + "litellm_provider": "kyma", "mode": "chat", - "off_peak_pricing": {"hours_utc":"16:00-00:00","input_cost_per_token":8.25e-8,"output_cost_per_token":3.3e-7,"cache_read_input_token_cost":2.0625e-8}, - "output_cost_per_token": 5.28e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, + "supports_vision": true, + "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_pdf_input": true }, - "openrouter/tencent/hy3-preview": { - "cache_read_input_token_cost": 6e-08, - "input_cost_per_token": 1.8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, + "kyma/grok-4.7": { + "max_input_tokens": 500000, + "max_output_tokens": 450000, + "input_cost_per_token": 2.16e-06, + "cache_read_input_token_cost": 5.4e-07, + "output_cost_per_token": 6.48e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": false, + "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_response_schema": true, + "supports_pdf_input": true }, - "openrouter/tencent/hy4-preview": { - "cache_read_input_token_cost": 4.2e-08, - "input_cost_per_token": 8.34e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 64000, - "max_tokens": 64000, + "kyma/grok-build": { + "max_input_tokens": 256000, + "max_output_tokens": 32768, + "input_cost_per_token": 1.389e-06, + "cache_read_input_token_cost": 2.7e-07, + "output_cost_per_token": 2.777e-06, + "input_cost_per_token_above_200k_tokens": 2.7e-06, + "output_cost_per_token_above_200k_tokens": 5.4e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 2.501e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": false, + "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_pdf_input": false }, - "openrouter/thedrummer/cydonia-24b-v4.1": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, + "kyma/hy3": { + "max_input_tokens": 262144, + "max_output_tokens": 8192, + "input_cost_per_token": 1.594e-07, + "output_cost_per_token": 6.576e-07, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, + "supports_function_calling": true, + "supports_vision": false, + "supports_prompt_caching": false, + "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": false, + "supports_pdf_input": false + }, + "kyma/hy4-preview": { + "max_input_tokens": 1048576, + "max_output_tokens": 64000, + "input_cost_per_token": 1.1259e-06, + "output_cost_per_token": 3.3764e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, "supports_vision": false, - "supports_web_search": false + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false }, - "openrouter/thedrummer/skyfall-36b-v2": { - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 5.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 29491, - "max_tokens": 29491, + "kyma/kimi-k2.6": { + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "input_cost_per_token": 5.909e-07, + "output_cost_per_token": 2.758e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 8e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": false, + "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false + "supports_pdf_input": false }, - "openrouter/thedrummer/unslopnemo-12b": { - "input_cost_per_token": 4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1024000, - "max_output_tokens": 819200, - "max_tokens": 819200, + "kyma/kimi-k2.7-code": { + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "input_cost_per_token": 1.009e-06, + "output_cost_per_token": 4.774e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 4e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, + "supports_function_calling": true, + "supports_vision": true, "supports_prompt_caching": false, - "supports_reasoning": false, + "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false + "supports_pdf_input": false }, - "openrouter/thinkingmachines/inkling": { - "cache_read_input_token_cost": 1.7e-07, - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 524288, - "max_output_tokens": 471859, - "max_tokens": 471859, + "kyma/kimi-k3": { + "max_input_tokens": 1048576, + "max_output_tokens": 32768, + "input_cost_per_token": 3.052e-06, + "cache_read_input_token_cost": 4.05e-07, + "output_cost_per_token": 1.5258e-05, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 4.05e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, "supports_function_calling": true, - "supports_pdf_input": false, + "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "supports_response_schema": true, + "supports_pdf_input": false }, - "openrouter/thinkingmachines/inkling-small": { - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 4.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 524288, - "max_output_tokens": 262144, - "max_tokens": 262144, + "kyma/kimi-k3.1-pro": { + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "input_cost_per_token": 2.7e-06, + "cache_read_input_token_cost": 2.7e-07, + "output_cost_per_token": 1.35e-05, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, "supports_function_calling": true, - "supports_pdf_input": false, + "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "supports_response_schema": true, + "supports_pdf_input": false }, - "openrouter/thinkingmachines/inkling-small:free": { - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", + "kyma/llama-3.3-70b": { + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "input_cost_per_token": 1.35e-07, + "output_cost_per_token": 4.32e-07, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/llama-4-maverick": { "max_input_tokens": 1048576, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16384, + "input_cost_per_token": 3.344e-07, + "output_cost_per_token": 1.337e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": false, "supports_vision": true, - "supports_web_search": false + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_pdf_input": false }, - "openrouter/thinkingmachines/inkling:free": { - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 262144, - "max_tokens": 262144, + "kyma/mimo-v2.5": { + "max_input_tokens": 1050000, + "max_output_tokens": 16384, + "input_cost_per_token": 1.859e-07, + "output_cost_per_token": 3.718e-07, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, "supports_function_calling": true, - "supports_pdf_input": false, + "supports_vision": true, "supports_prompt_caching": false, "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": false, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/mimo-v2.6-flash": { + "max_input_tokens": 1050000, + "max_output_tokens": 131072, + "input_cost_per_token": 1.89e-07, + "output_cost_per_token": 3.78e-07, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, "supports_vision": true, - "supports_web_search": false + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false }, - "openrouter/unbiased/pareto": { - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, + "kyma/mimo-v2.6-pro": { + "max_input_tokens": 1050000, "max_output_tokens": 131072, - "max_tokens": 131072, + "input_cost_per_token": 5.805e-07, + "output_cost_per_token": 1.1745e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 7.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": false + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false }, - "openrouter/upstage/solar-pro-3": { - "cache_read_input_token_cost": 1.5e-08, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, + "kyma/minimax-m2.5": { + "max_input_tokens": 196608, + "max_output_tokens": 32768, + "input_cost_per_token": 4.188e-07, + "output_cost_per_token": 1.675e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": false, + "supports_vision": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, + "supports_pdf_input": false + }, + "kyma/minimax-m2.7": { + "max_input_tokens": 204800, + "max_output_tokens": 32768, + "input_cost_per_token": 4.05e-07, + "output_cost_per_token": 1.62e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, "supports_vision": false, - "supports_web_search": false + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false }, - "openrouter/upstage/solar-pro4": { - "cache_read_input_token_cost": 1.8e-08, - "input_cost_per_token": 9e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 524288, - "max_output_tokens": 131072, - "max_tokens": 131072, + "kyma/minimax-m3": { + "max_input_tokens": 1048576, + "max_output_tokens": 32768, + "input_cost_per_token": 3.956e-07, + "cache_read_input_token_cost": 7.56e-08, + "output_cost_per_token": 1.582e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 3.6e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": false, + "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_pdf_input": false }, - "openrouter/upstage/solar-mini4": { - "cache_read_input_token_cost": 5e-09, - "input_cost_per_token": 5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 524288, - "max_output_tokens": 131072, - "max_tokens": 131072, + "kyma/minimax-m3.1-flash": { + "max_input_tokens": 1048576, + "max_output_tokens": 524288, + "input_cost_per_token": 2.025e-07, + "cache_read_input_token_cost": 2.025e-08, + "output_cost_per_token": 8.1e-07, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": false, + "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_pdf_input": false }, - "openrouter/writer/palmyra-x5": { - "input_cost_per_token": 6e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1040000, + "kyma/muse-glimmer-30b": { + "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, + "input_cost_per_token": 4.554e-07, + "output_cost_per_token": 1.821e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 6e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, + "supports_function_calling": true, + "supports_vision": true, "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false }, - "openrouter/x-ai/grok-4.3:batch": { - "cache_read_input_token_cost": 1.6e-07, - "cache_read_input_token_cost_above_200k_tokens": 3.2e-07, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_200k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 900000, - "max_tokens": 900000, + "kyma/muse-spark-1.1": { + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "input_cost_per_token": 1.542e-06, + "output_cost_per_token": 5.243e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 2e-06, - "output_cost_per_token_above_200k_tokens": 4e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_vision": true, + "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_pdf_input": true }, - "openrouter/z-ai/glm-5.3-flash:batch": { - "cache_read_input_token_cost": 1.2e-08, - "input_cost_per_token": 6e-08, - "litellm_provider": "openrouter", + "kyma/muse-spark-1.2": { "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 8192, + "input_cost_per_token": 1.773e-06, + "output_cost_per_token": 6.025e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, + "supports_vision": true, + "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "supports_pdf_input": true }, - "openrouter/z-ai/glm-5.3:batch": { - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 4.5e-07, - "litellm_provider": "openrouter", + "kyma/muse-spark-1.3": { "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 8192, + "input_cost_per_token": 1.688e-06, + "output_cost_per_token": 5.738e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, + "supports_vision": true, + "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_pdf_input": true }, - "openrouter/prism-ml/ternary-bonsai-2-27b": { - "cache_read_input_token_cost": 3.75e-08, - "input_cost_per_token": 7.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, + "kyma/muse-spark-open": { + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "input_cost_per_token": 1.688e-06, + "output_cost_per_token": 5.738e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": false, + "supports_vision": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, + "supports_pdf_input": false + }, + "kyma/muse-wonder": { + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "input_cost_per_token": 5.4e-06, + "output_cost_per_token": 2.7e-05, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, "supports_vision": true, - "supports_web_search": false + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true }, - "openrouter/z-ai/glm-5.3-prime": { - "cache_read_input_token_cost": 5.6e-07, - "input_cost_per_token": 2.8e-06, - "litellm_provider": "openrouter", + "kyma/nemotron-3-ultra-550b": { "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 32768, + "input_cost_per_token": 6.75e-07, + "cache_read_input_token_cost": 1.35e-07, + "output_cost_per_token": 3.375e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 8.8e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": false, + "supports_vision": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "supports_pdf_input": false }, - "openrouter/z-ai/glm-5.3-flashx": { - "cache_read_input_token_cost": 9e-08, - "deprecation_date": "2098-12-31", - "input_cost_per_token": 3.7e-07, - "litellm_provider": "openrouter", + "kyma/nemotron-3.5-super-vl": { "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 235929, + "input_cost_per_token": 8.1e-08, + "cache_read_input_token_cost": 1.35e-08, + "output_cost_per_token": 4.725e-07, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 1.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": false, + "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "supports_pdf_input": false }, - "openrouter/x-ai/grok-4.7": { - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_200k_tokens": 1e-06, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_200k_tokens": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 500000, - "max_output_tokens": 450000, - "max_tokens": 450000, + "kyma/qwen-3-32b": { + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "input_cost_per_token": 1.08e-07, + "output_cost_per_token": 3.78e-07, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 6e-06, - "output_cost_per_token_above_200k_tokens": 1.2e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": true, + "supports_vision": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_pdf_input": false }, - "moonshotai.kimi-k3": { - "cache_creation_input_token_cost": 4.125e-06, - "cache_read_input_token_cost": 3.3e-07, - "input_cost_per_token": 3.3e-06, - "litellm_provider": "bedrock_converse", + "kyma/qwen-3-coder": { + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "input_cost_per_token": 3.546e-07, + "cache_read_input_token_cost": 1.35e-07, + "output_cost_per_token": 1.612e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/qwen-3.6-plus": { "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 65536, + "input_cost_per_token": 4.388e-07, + "output_cost_per_token": 2.633e-06, + "input_cost_per_token_above_256k_tokens": 1.755e-06, + "output_cost_per_token_above_256k_tokens": 5.265e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 1.65e-05, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", - "supports_audio_input": false, "supports_function_calling": true, + "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_pdf_input": false }, - "global.moonshotai.kimi-k3": { - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "litellm_provider": "bedrock_converse", + "kyma/qwen-3.7-max": { "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 32768, + "input_cost_per_token": 2.071e-06, + "cache_read_input_token_cost": 1.6875e-07, + "output_cost_per_token": 6.207e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://aws.amazon.com/bedrock/pricing/", - "supports_audio_input": false, "supports_function_calling": true, + "supports_vision": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_pdf_input": false }, - "us.moonshotai.kimi-k3": { - "cache_creation_input_token_cost": 4.125e-06, - "cache_read_input_token_cost": 3.3e-07, - "input_cost_per_token": 3.3e-06, - "litellm_provider": "bedrock_converse", + "kyma/qwen-3.7-plus": { "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 32768, + "input_cost_per_token": 4.325e-07, + "cache_read_input_token_cost": 8.64e-08, + "output_cost_per_token": 1.731e-06, + "input_cost_per_token_above_256k_tokens": 1.296e-06, + "output_cost_per_token_above_256k_tokens": 5.184e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 1.65e-05, - "source": "https://aws.amazon.com/bedrock/pricing/", - "supports_audio_input": false, "supports_function_calling": true, + "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_pdf_input": false }, - "openrouter/xiaomi/mimo-v2.6-flash": { - "cache_read_input_token_cost": 2.8e-09, - "input_cost_per_token": 1.4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, + "kyma/qwen-3.8-max": { + "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, + "input_cost_per_token": 2.228e-06, + "cache_read_input_token_cost": 2.781e-07, + "output_cost_per_token": 6.684e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 2.8e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, "supports_function_calling": true, - "supports_pdf_input": false, + "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "supports_pdf_input": false }, - "openrouter/xiaomi/mimo-v2.6-pro": { - "cache_read_input_token_cost": 3.6e-09, - "input_cost_per_token": 4.35e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, + "kyma/qwen3.7-flash": { + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "input_cost_per_token": 4.35e-08, + "cache_read_input_token_cost": 8.1e-09, + "output_cost_per_token": 1.886e-07, + "input_cost_per_token_above_32k_tokens": 1.35e-07, + "output_cost_per_token_above_32k_tokens": 5.4e-07, + "input_cost_per_token_above_256k_tokens": 2.7e-07, + "output_cost_per_token_above_256k_tokens": 1.08e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 8.7e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, "supports_function_calling": true, - "supports_pdf_input": false, + "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, + "supports_pdf_input": false + }, + "kyma/qwen3.8-27b": { + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "input_cost_per_token": 3.826e-07, + "output_cost_per_token": 2.732e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, "supports_vision": true, - "supports_web_search": false + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false }, - "openrouter/xiaomi/mimo-v2.6-pro-ultraspeed": { - "cache_read_input_token_cost": 3.6e-08, - "input_cost_per_token": 4.35e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, + "kyma/qwen3.8-flash": { + "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, + "input_cost_per_token": 2.045e-07, + "output_cost_per_token": 6.41e-07, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 8.7e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, "supports_function_calling": true, - "supports_pdf_input": false, + "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, + "supports_pdf_input": false + }, + "kyma/sonar": { + "max_input_tokens": 127072, + "max_output_tokens": 4096, + "input_cost_per_token": 1.35e-06, + "output_cost_per_token": 1.35e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": false, "supports_vision": true, - "supports_web_search": false + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_pdf_input": false }, - "xiaomi_mimo/mimo-v2.6-pro": { - "cache_read_input_token_cost": 3.6e-09, - "input_cost_per_token": 4.35e-07, - "litellm_provider": "xiaomi_mimo", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, + "kyma/sonar-pro": { + "max_input_tokens": 200000, + "max_output_tokens": 8000, + "input_cost_per_token": 4.05e-06, + "output_cost_per_token": 2.025e-05, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": false, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_pdf_input": false + }, + "kyma/step-3.7-flash": { + "max_input_tokens": 256000, + "max_output_tokens": 8192, + "input_cost_per_token": 2.229e-07, + "cache_read_input_token_cost": 5.4e-08, + "output_cost_per_token": 1.282e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 8.7e-07, - "source": "https://platform.xiaomimimo.com/static/docs/price/pay-as-you-go.md", - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supports_audio_input": true, "supports_function_calling": true, + "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true + "supports_pdf_input": false }, - "xiaomi_mimo/mimo-v2.6-flash": { - "cache_read_input_token_cost": 2.8e-09, - "input_cost_per_token": 1.4e-07, - "litellm_provider": "xiaomi_mimo", + "kyma/step-5-preview": { "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 64000, + "input_cost_per_token": 1.35e-06, + "cache_read_input_token_cost": 1.35e-07, + "output_cost_per_token": 3.645e-06, + "litellm_provider": "kyma", "mode": "chat", - "output_cost_per_token": 2.8e-07, - "source": "https://platform.xiaomimimo.com/static/docs/price/pay-as-you-go.md", - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supports_audio_input": true, "supports_function_calling": true, + "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true + "supports_pdf_input": false }, - "xai/grok-4.20-0309": { - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_batches": 1.6e-07, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_batches": 1e-06, - "litellm_provider": "xai", + "databricks/databricks-claude-haiku-5-5": { + "cache_creation_input_token_cost": 1.2502e-07, + "cache_creation_input_token_cost_above_100k_tokens": 6.2503e-07, + "cache_creation_input_token_cost_above_1hr": 1.9999e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.00002e-06, + "cache_read_input_token_cost": 1.001e-08, + "cache_read_input_token_cost_above_100k_tokens": 4.998e-08, + "input_cost_per_token": 1.0003e-07, + "input_cost_per_token_above_100k_tokens": 5.0001e-07, + "input_dbu_cost_per_token": 1.429e-06, + "litellm_provider": "databricks", "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, "mode": "chat", - "output_cost_per_token": 2.5e-06, - "output_cost_per_token_batches": 2e-06, - "source": "https://api.x.ai/v1/language-models", + "output_cost_per_token": 5.0001e-07, + "output_cost_per_token_above_100k_tokens": 2.49998e-06, + "output_dbu_cost_per_token": 7.143e-06, + "prompt_cache_min_tokens": 512.0, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_adaptive_thinking": true, + "thinking_on_by_default": true, + "supports_anthropic_thinking_payload": true, + "supports_assistant_prefill": false, "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_prompt_caching": true, "supports_reasoning": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "input_cost_per_token_above_200k_tokens_batches": 2e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "output_cost_per_token_above_200k_tokens_batches": 4e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, - "input_cost_per_image_token": 1.25e-06, - "supports_prompt_caching": true, - "supports_response_schema": true + "thinking_always_on": false }, - "xai/grok-4.20-beta": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", + "databricks/claude-haiku-latest": { + "alias_of": "databricks/databricks-claude-haiku-5-5" + }, + "databricks/databricks-claude-sonnet-5-5": { + "cache_creation_input_token_cost": 2.49998e-06, + "cache_creation_input_token_cost_above_1hr": 4.00001e-06, + "cache_read_input_token_cost": 1.0003e-07, + "input_cost_per_token": 1.99997e-06, + "input_dbu_cost_per_token": 2.8571e-05, + "litellm_provider": "databricks", "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://api.x.ai/v1/language-models", + "output_cost_per_token": 9.99999e-06, + "output_dbu_cost_per_token": 0.00014286, + "prompt_cache_min_tokens": 512.0, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_adaptive_thinking": true, + "supports_anthropic_thinking_payload": true, + "supports_assistant_prefill": false, "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_prompt_caching": true, "supports_reasoning": true, + "supports_sampling_params": false, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_image_token": 1.25e-06, - "supports_prompt_caching": true, - "supports_response_schema": true + "supports_vision": false, + "thinking_always_on": true }, - "xai/grok-4.20-beta-0309": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", + "databricks/claude-sonnet-latest": { + "alias_of": "databricks/databricks-claude-sonnet-5-5" + }, + "databricks/databricks-deepseek-v4-1-flash": { + "cache_creation_input_token_cost": 3.0002e-07, + "cache_read_input_token_cost": 3.003e-08, + "deprecation_date": "2026-11-19", + "deprecation_source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", + "input_cost_per_token": 3.0002e-07, + "input_dbu_cost_per_token": 4.286e-06, + "litellm_provider": "databricks", "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 384000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields. The docs list only databricks-deepseek-v4-1-flash (retiring 2026-11-19) and databricks-deepseek-v4-1-flash-1017, so the pricing page's 'DeepSeek V4.1 Flash (0910)' row prices the unsuffixed endpoint." + }, "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://api.x.ai/v1/language-models", + "output_cost_per_token": 1.20001e-06, + "output_dbu_cost_per_token": 1.7143e-05, + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_image_token": 1.25e-06, - "supports_prompt_caching": true, - "supports_response_schema": true + "input_cost_per_token_priority": 5.25e-07, + "output_cost_per_token_priority": 2.1e-06, + "cache_read_input_token_cost_priority": 5.25e-08, + "cache_creation_input_token_cost_priority": 5.25e-07, + "successor_model": "databricks/databricks-deepseek-v4-1-flash-1017" }, - "xai/grok-4.20-beta-latest": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", + "databricks/databricks-deepseek-v4-1-flash-1017": { + "cache_creation_input_token_cost": 3.0002e-07, + "cache_read_input_token_cost": 7e-09, + "input_cost_per_token": 3.0002e-07, + "input_dbu_cost_per_token": 4.286e-06, + "litellm_provider": "databricks", "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 384000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://api.x.ai/v1/language-models", + "output_cost_per_token": 1.20001e-06, + "output_dbu_cost_per_token": 1.7143e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_image_token": 1.25e-06, - "supports_prompt_caching": true, - "supports_response_schema": true + "supports_vision": true }, - "xai/grok-4.20-beta-latest-non-reasoning": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "max_tokens": 1000000, + "databricks/databricks-gemini-2-5-flash-lite": { + "cache_creation_input_token_cost": 1.2502e-07, + "cache_read_input_audio_token_cost": 3.752e-08, + "cache_read_input_token_cost": 1.253e-08, + "input_cost_per_audio_token": 3.7499e-07, + "input_cost_per_image_token": 1.2502e-07, + "input_cost_per_token": 1.2502e-07, + "input_dbu_cost_per_token": 1.786e-06, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://api.x.ai/v1/language-models", + "output_cost_per_token": 5.0001e-07, + "output_dbu_cost_per_token": 7.143e-06, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, "supports_function_calling": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_image_token": 1.25e-06, - "supports_response_schema": true + "supports_video_input": true, + "supports_vision": true }, - "xai/grok-4.20-beta-latest-reasoning": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "max_tokens": 1000000, + "databricks/databricks-gemini-3-1-flash-lite-image": { + "cache_creation_input_token_cost": 3.1248e-07, + "cache_read_input_token_cost": 3.1248e-07, + "input_cost_per_image_token": 3.1248e-07, + "input_cost_per_token": 3.1248e-07, + "input_dbu_cost_per_token": 4.464e-06, + "litellm_provider": "databricks", + "max_input_tokens": 65536, + "max_output_tokens": 4096, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://api.x.ai/v1/language-models", + "output_cost_per_image_token": 3.749998e-05, + "output_cost_per_token": 1.87502e-06, + "output_dbu_cost_per_token": 2.6786e-05, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_vision": true + }, + "databricks/databricks-gemini-4-argon": { + "cache_creation_input_token_cost": 2.49998e-06, + "cache_read_input_token_cost": 1.2502e-07, + "input_cost_per_token": 2.49998e-06, + "input_dbu_cost_per_token": 3.5714e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 1.249997e-05, + "output_dbu_cost_per_token": 0.00017857, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, + "supports_video_input": true, "supports_vision": true, - "supports_web_search": true, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_image_token": 1.25e-06, + "input_cost_per_token_priority": 4.50002e-06, + "output_cost_per_token_priority": 2.250003e-05, + "cache_read_input_token_cost_priority": 2.2498e-07, + "cache_creation_input_token_cost_priority": 4.50002e-06 + }, + "databricks/databricks-gpt-5-4-pro": { + "cache_creation_input_token_cost": 2.999997e-05, + "cache_read_input_token_cost": 2.999997e-05, + "input_cost_per_token": 2.999997e-05, + "input_cost_per_token_above_272k_tokens": 6e-05, + "input_dbu_cost_per_token": 0.00042857, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "responses", + "output_cost_per_token": 0.0001800001, + "output_cost_per_token_above_272k_tokens": 0.00027, + "output_dbu_cost_per_token": 0.0025714, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, "supports_prompt_caching": true, - "supports_response_schema": true + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true }, - "xai/grok-4.20-beta-non-reasoning": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "max_tokens": 1000000, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://api.x.ai/v1/language-models", + "databricks/databricks-gpt-6-1-sol": { + "cache_creation_input_token_cost": 2.49998e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5.00003e-06, + "cache_read_input_token_cost": 1.0003e-07, + "cache_read_input_token_cost_above_272k_tokens": 1.9999e-07, + "input_cost_per_token": 1.99997e-06, + "input_cost_per_token_above_272k_tokens": 4.00001e-06, + "input_dbu_cost_per_token": 2.8571e-05, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "responses", + "output_cost_per_token": 9.99999e-06, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "output_dbu_cost_per_token": 0.00014286, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_image_token": 1.25e-06, - "supports_response_schema": true + "input_cost_per_token_priority": 4.00001e-06, + "output_cost_per_token_priority": 1.99997e-05, + "cache_read_input_token_cost_priority": 1.9999e-07, + "cache_creation_input_token_cost_priority": 5.00003e-06, + "input_cost_per_token_above_272k_tokens_priority": 8.00002e-06, + "output_cost_per_token_above_272k_tokens_priority": 2.99999e-05, + "cache_read_input_token_cost_above_272k_tokens_priority": 3.9998e-07, + "cache_creation_input_token_cost_above_272k_tokens_priority": 9.99999e-06 }, - "xai/grok-4.20-beta-reasoning": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "max_tokens": 1000000, + "databricks/gpt-sol-latest": { + "alias_of": "databricks/databricks-gpt-6-1-sol" + }, + "databricks/databricks-gpt-6-1-terra": { + "cache_creation_input_token_cost": 1.24999e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.49998e-06, + "cache_read_input_token_cost": 4.998e-08, + "cache_read_input_token_cost_above_272k_tokens": 1.0003e-07, + "input_cost_per_token": 1.00002e-06, + "input_cost_per_token_above_272k_tokens": 1.99997e-06, + "input_dbu_cost_per_token": 1.4286e-05, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://api.x.ai/v1/language-models", + "output_cost_per_token": 5.00003e-06, + "output_cost_per_token_above_272k_tokens": 7.50001e-06, + "output_dbu_cost_per_token": 7.1429e-05, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_image_token": 1.25e-06, - "supports_prompt_caching": true, - "supports_response_schema": true + "input_cost_per_token_priority": 1.99997e-06, + "output_cost_per_token_priority": 9.99999e-06, + "cache_read_input_token_cost_priority": 1.0003e-07, + "cache_creation_input_token_cost_priority": 2.49998e-06, + "input_cost_per_token_above_272k_tokens_priority": 4.00001e-06, + "output_cost_per_token_above_272k_tokens_priority": 1.500002e-05, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.9999e-07, + "cache_creation_input_token_cost_above_272k_tokens_priority": 5.00003e-06 }, - "xai/grok-4.20-experimental-beta-0304": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "max_tokens": 1000000, + "databricks/gpt-terra-latest": { + "alias_of": "databricks/databricks-gpt-6-1-terra" + }, + "databricks/databricks-gpt-6-astra": { + "cache_creation_input_token_cost": 1.249997e-05, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, + "cache_read_input_token_cost": 1.00002e-06, + "cache_read_input_token_cost_above_272k_tokens": 1.99997e-06, + "input_cost_per_token": 9.99999e-06, + "input_cost_per_token_above_272k_tokens": 2e-05, + "input_dbu_cost_per_token": 0.00014286, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://api.x.ai/v1/language-models", + "output_cost_per_token": 5.000002e-05, + "output_cost_per_token_above_272k_tokens": 7.50001e-05, + "output_dbu_cost_per_token": 0.00071429, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_image_token": 1.25e-06, - "supports_prompt_caching": true, - "supports_response_schema": true + "input_cost_per_token_priority": 1.999998e-05, + "output_cost_per_token_priority": 9.99999e-05, + "cache_read_input_token_cost_priority": 1.99997e-06, + "cache_creation_input_token_cost_priority": 2.500001e-05, + "input_cost_per_token_above_272k_tokens_priority": 4.000003e-05, + "output_cost_per_token_above_272k_tokens_priority": 0.0001500002, + "cache_read_input_token_cost_above_272k_tokens_priority": 4.00001e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 5.000002e-05 }, - "xai/grok-4.20-experimental-beta-0304-non-reasoning": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "max_tokens": 1000000, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://api.x.ai/v1/language-models", + "databricks/gpt-astra-latest": { + "alias_of": "databricks/databricks-gpt-6-astra" + }, + "databricks/databricks-gpt-6-luna": { + "cache_creation_input_token_cost": 1.2502e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.4997e-07, + "cache_read_input_token_cost": 1.001e-08, + "cache_read_input_token_cost_above_272k_tokens": 2.002e-08, + "input_cost_per_token": 1.0003e-07, + "input_cost_per_token_above_272k_tokens": 1.9999e-07, + "input_dbu_cost_per_token": 1.429e-06, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "responses", + "output_cost_per_token": 5.0001e-07, + "output_cost_per_token_above_272k_tokens": 7.497e-07, + "output_dbu_cost_per_token": 7.143e-06, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_image_token": 1.25e-06, - "supports_response_schema": true + "input_cost_per_token_priority": 1.9999e-07, + "output_cost_per_token_priority": 1.0003e-06, + "cache_read_input_token_cost_priority": 2.002e-08, + "cache_creation_input_token_cost_priority": 2.4997e-07, + "input_cost_per_token_above_272k_tokens_priority": 3.9998e-07, + "output_cost_per_token_above_272k_tokens_priority": 1.5001e-06, + "cache_read_input_token_cost_above_272k_tokens_priority": 3.997e-08, + "cache_creation_input_token_cost_above_272k_tokens_priority": 5.0001e-07 }, - "xai/grok-4.20-experimental-beta-0304-reasoning": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "max_tokens": 1000000, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://api.x.ai/v1/language-models", + "databricks/gpt-luna-latest": { + "alias_of": "databricks/databricks-gpt-6-luna" + }, + "databricks/databricks-gpt-6-sol": { + "cache_creation_input_token_cost": 2.49998e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5.00003e-06, + "cache_read_input_token_cost": 1.9999e-07, + "cache_read_input_token_cost_above_272k_tokens": 3.9998e-07, + "input_cost_per_token": 1.99997e-06, + "input_cost_per_token_above_272k_tokens": 4.00001e-06, + "input_dbu_cost_per_token": 2.8571e-05, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "responses", + "output_cost_per_token": 9.99999e-06, + "output_cost_per_token_above_272k_tokens": 1.50003e-05, + "output_dbu_cost_per_token": 0.00014286, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_image_token": 1.25e-06, - "supports_prompt_caching": true, - "supports_response_schema": true + "input_cost_per_token_priority": 4.00001e-06, + "output_cost_per_token_priority": 1.99997e-05, + "cache_read_input_token_cost_priority": 3.9998e-07, + "cache_creation_input_token_cost_priority": 5.00003e-06, + "input_cost_per_token_above_272k_tokens_priority": 8.00002e-06, + "output_cost_per_token_above_272k_tokens_priority": 2.99999e-05, + "cache_read_input_token_cost_above_272k_tokens_priority": 8.0003e-07, + "cache_creation_input_token_cost_above_272k_tokens_priority": 9.99999e-06 }, - "xai/grok-4.20-experimental-beta-latest": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "max_tokens": 1000000, + "databricks/databricks-gpt-image-1": { + "cache_creation_input_token_cost": 5.00003e-06, + "cache_read_input_token_cost": 1.24999e-06, + "input_cost_per_image_token": 9.99999e-06, + "input_cost_per_token": 5.00003e-06, + "input_dbu_cost_per_token": 7.1429e-05, + "litellm_provider": "databricks", + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "image_generation", + "output_cost_per_image_token": 4.000003e-05, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" + }, + "databricks/databricks-gpt-image-1-5": { + "cache_creation_input_token_cost": 5.00003e-06, + "cache_read_input_token_cost": 1.24999e-06, + "input_cost_per_image_token": 8.00002e-06, + "input_cost_per_token": 5.00003e-06, + "input_dbu_cost_per_token": 7.1429e-05, + "litellm_provider": "databricks", + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "image_generation", + "output_cost_per_image_token": 3.200001e-05, + "output_cost_per_token": 9.99999e-06, + "output_dbu_cost_per_token": 0.00014286, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_pdf_input": true, + "supports_vision": true + }, + "databricks/databricks-gpt-image-1-mini": { + "cache_creation_input_token_cost": 1.99997e-06, + "cache_read_input_token_cost": 1.9999e-07, + "input_cost_per_image_token": 2.49998e-06, + "input_cost_per_token": 1.99997e-06, + "input_dbu_cost_per_token": 2.8571e-05, + "litellm_provider": "databricks", + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "image_generation", + "output_cost_per_image_token": 8.00002e-06, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" + }, + "databricks/databricks-gpt-image-2": { + "cache_creation_input_token_cost": 5.00003e-06, + "cache_read_input_token_cost": 1.24999e-06, + "input_cost_per_image_token": 8.00002e-06, + "input_cost_per_token": 5.00003e-06, + "input_dbu_cost_per_token": 7.1429e-05, + "litellm_provider": "databricks", + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "image_generation", + "output_cost_per_image_token": 2.999997e-05, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_pdf_input": true, + "supports_vision": true + }, + "databricks/databricks-grok-4-7": { + "cache_creation_input_token_cost": 2.49998e-06, + "cache_read_input_token_cost": 6.2503e-07, + "input_cost_per_token": 2.49998e-06, + "input_dbu_cost_per_token": 3.5714e-05, + "litellm_provider": "databricks", + "max_input_tokens": 500000, + "max_output_tokens": 500000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://api.x.ai/v1/language-models", + "output_cost_per_token": 7.50001e-06, + "output_dbu_cost_per_token": 0.00010714, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_image_token": 1.25e-06, - "supports_prompt_caching": true, - "supports_response_schema": true + "supports_vision": true }, - "xai/grok-4.20-experimental-beta-non-reasoning-latest": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "max_tokens": 1000000, + "databricks/grok-latest": { + "alias_of": "databricks/databricks-grok-4-7" + }, + "databricks/databricks-kimi-k2-7": { + "cache_creation_input_token_cost": 9.4997e-07, + "cache_read_input_token_cost": 1.8998e-07, + "deprecation_date": "2026-10-30", + "deprecation_source": "https://docs.databricks.com/aws/en/machine-learning/retired-models-policy", + "input_cost_per_token": 9.4997e-07, + "input_dbu_cost_per_token": 1.3571e-05, + "litellm_provider": "databricks", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://api.x.ai/v1/language-models", + "output_cost_per_token": 4.00001e-06, + "output_dbu_cost_per_token": 5.7143e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "successor_model": "databricks/databricks-kimi-k3", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_image_token": 1.25e-06, - "supports_response_schema": true + "supports_vision": true }, - "xai/grok-4.20-experimental-beta-reasoning-latest": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "max_tokens": 1000000, + "fireworks_ai/accounts/fireworks/routers/spot-deepseek-v4-flash": { + "cache_read_input_token_cost": 2.1e-08, + "deprecation_date": "2026-08-14", + "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md", + "input_cost_per_token": 1.05e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://api.x.ai/v1/language-models", + "output_cost_per_token": 2.1e-07, + "source": "https://api.fireworks.ai/v1/serverless/models", + "successor_model": "fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_image_token": 1.25e-06, - "supports_prompt_caching": true, - "supports_response_schema": true + "supports_vision": false }, - "xai/grok-4.20-multi-agent-beta-latest": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "max_tokens": 1000000, - "mode": "responses", - "output_cost_per_token": 2.5e-06, - "source": "https://api.x.ai/v1/language-models", - "supports_function_calling": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": true, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_image_token": 1.25e-06, - "supports_response_schema": true, - "supported_endpoints": [ - "/v1/responses" - ] - }, - "xai/grok-4.20-multi-agent-experimental-beta-0304": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "max_tokens": 1000000, - "mode": "responses", - "output_cost_per_token": 2.5e-06, - "source": "https://api.x.ai/v1/language-models", - "supports_function_calling": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": true, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_image_token": 1.25e-06, - "supports_response_schema": true, - "supported_endpoints": [ - "/v1/responses" - ] - }, - "xai/grok-4.20-multi-agent-experimental-beta-latest": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "max_tokens": 1000000, - "mode": "responses", - "output_cost_per_token": 2.5e-06, - "source": "https://api.x.ai/v1/language-models", - "supports_function_calling": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": true, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_image_token": 1.25e-06, - "supports_response_schema": true, - "supported_endpoints": [ - "/v1/responses" - ] - }, - "xai/grok-4.20-non-reasoning-gv2": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "max_tokens": 1000000, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://api.x.ai/v1/language-models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_image_token": 1.25e-06, - "supports_response_schema": true - }, - "xai/grok-4.20-reasoning-gv2": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "xai", - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "max_tokens": 1000000, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://api.x.ai/v1/language-models", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_image_token": 1.25e-06, - "supports_prompt_caching": true, - "supports_response_schema": true - }, - "openrouter/nex-agi/nex-n2.5-mini": { - "cache_read_input_token_cost": 2.5e-09, - "input_cost_per_token": 2.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "output_cost_per_token": 1e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/nex-agi/nex-n2.5-pro": { - "cache_read_input_token_cost": 1.5e-08, - "input_cost_per_token": 7.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "output_cost_per_token": 2.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "baseten/deepseek-ai/DeepSeek-V4.1-Flash": { - "cache_read_input_token_cost": 7e-09, - "input_cost_per_token": 3e-07, - "litellm_provider": "baseten", + "fireworks_ai/accounts/fireworks/routers/kimi-k3-spot": { + "cache_read_input_token_cost": 2.1e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://inference.baseten.co/v1/models", + "output_cost_per_token": 1.05e-05, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, - "baseten/moonshotai/Kimi-K2.6": { - "cache_read_input_token_cost": 1.6e-07, - "input_cost_per_token": 9.5e-07, - "litellm_provider": "baseten", - "max_input_tokens": 262000, - "max_output_tokens": 262000, - "max_tokens": 262000, + "fireworks_ai/accounts/fireworks/routers/glm-5p3-spot": { + "cache_read_input_token_cost": 1.82e-07, + "input_cost_per_token": 9.8e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 4e-06, - "source": "https://inference.baseten.co/v1/models", + "output_cost_per_token": 3.08e-06, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": false }, - "baseten/moonshotai/Kimi-K2.7-Code": { - "cache_read_input_token_cost": 1.6e-07, - "input_cost_per_token": 9.5e-07, - "litellm_provider": "baseten", - "max_input_tokens": 262000, - "max_output_tokens": 262000, - "max_tokens": 262000, + "fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-spot": { + "cache_read_input_token_cost": 4.2e-09, + "input_cost_per_token": 2.1e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, "mode": "chat", - "output_cost_per_token": 4e-06, - "source": "https://inference.baseten.co/v1/models", + "output_cost_per_token": 8.4e-07, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, - "baseten/moonshotai/Kimi-K3": { - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "litellm_provider": "baseten", + "fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-1017-ultrafast": { + "cache_read_input_token_cost": 4.8e-08, + "input_cost_per_token": 2.4e-06, + "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 393216, "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://inference.baseten.co/v1/models", + "output_cost_per_token": 9.6e-06, + "source": "https://docs.fireworks.ai/serverless/pricing.md", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, - "baseten/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": { - "cache_read_input_token_cost": 1.2e-07, - "input_cost_per_token": 6e-07, - "litellm_provider": "baseten", - "max_input_tokens": 202800, - "max_output_tokens": 202800, - "max_tokens": 202800, + "fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-1017-spot": { + "cache_read_input_token_cost": 4.2e-09, + "input_cost_per_token": 2.1e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, "mode": "chat", - "output_cost_per_token": 2.4e-06, - "source": "https://inference.baseten.co/v1/models", + "output_cost_per_token": 8.4e-07, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true }, - "baseten/thinkingmachines/inkling": { - "cache_read_input_token_cost": 1.7e-07, - "input_cost_per_token": 1e-06, - "litellm_provider": "baseten", - "max_input_tokens": 1048576, - "max_output_tokens": 32768, - "max_tokens": 32768, + "bigmodel/glm-5.3": { + "input_cost_per_token": 1.1428571428571428e-06, + "output_cost_per_token": 4e-06, + "cache_read_input_token_cost": 2.857142857142857e-07, + "litellm_provider": "bigmodel", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 4.05e-06, - "source": "https://inference.baseten.co/v1/models", + "source": "https://docs.bigmodel.cn/cn/guide/start/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "thinking_always_on": true, + "metadata": { + "comment": "Official API list price checked 2026-10-27: input 8, output 28, cached input 2 CNY per million tokens; converted at 7.0 CNY/USD. Cache storage is temporarily free and is not encoded." + }, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_native_streaming": true }, - "baseten/thinkingmachines/inkling-small": { - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 5e-07, - "litellm_provider": "baseten", - "max_input_tokens": 1048576, - "max_output_tokens": 32768, - "max_tokens": 32768, + "bigmodel/glm-5.3-flash": { + "input_cost_per_token": 1.142857142857143e-07, + "output_cost_per_token": 4e-07, + "cache_read_input_token_cost": 3.2857142857142855e-08, + "litellm_provider": "bigmodel", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://inference.baseten.co/v1/models", + "source": "https://docs.bigmodel.cn/cn/guide/start/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "thinking_always_on": true, + "supports_vision": true, + "supports_video_input": true, + "metadata": { + "comment": "Official API list price checked 2026-10-27: input 0.8, output 2.8, cached input 0.23 CNY per million tokens; converted at 7.0 CNY/USD. Cache storage is temporarily free and is not encoded." + }, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_native_streaming": true }, - "baseten/zai-org/GLM-5.2": { - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 1.4e-06, - "litellm_provider": "baseten", - "max_input_tokens": 1048576, - "max_output_tokens": 262144, - "max_tokens": 262144, + "bigmodel/glm-5.3-flashx": { + "input_cost_per_token": 2.857142857142857e-07, + "output_cost_per_token": 1e-06, + "cache_read_input_token_cost": 8.142857142857142e-08, + "litellm_provider": "bigmodel", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 4.4e-06, - "source": "https://inference.baseten.co/v1/models", + "source": "https://docs.bigmodel.cn/cn/guide/start/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "thinking_always_on": true, + "supports_vision": true, + "supports_video_input": true, + "metadata": { + "comment": "Official API list price checked 2026-10-27: input 2, output 7, cached input 0.57 CNY per million tokens; converted at 7.0 CNY/USD. Cache storage is temporarily free and is not encoded." + }, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_native_streaming": true }, - "baseten/zai-org/GLM-5.3-Flash": { + "fireworks_ai/accounts/fireworks/models/ultramarine-1-flash-us": { "cache_read_input_token_cost": 3e-08, + "cache_read_input_token_cost_priority": 3.75e-08, "input_cost_per_token": 1.5e-07, - "litellm_provider": "baseten", + "input_cost_per_token_priority": 1.875e-07, + "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 5e-07, - "source": "https://inference.baseten.co/v1/models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, + "output_cost_per_token_priority": 6.25e-07, + "source": "https://docs.fireworks.ai/serverless/pricing.md", + "supports_function_calling": false, "supports_response_schema": true, - "supports_tool_choice": true, + "supports_tool_choice": false, "supports_vision": true }, - "baseten/deepseek-ai/DeepSeek-V4-Flash-0731": { - "cache_read_input_token_cost": 2.8e-08, - "input_cost_per_token": 1.3e-07, + "baseten/decision-models/baseten-joey-2b-latest": { + "input_cost_per_token": 1e-08, "litellm_provider": "baseten", - "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, - "mode": "chat", - "output_cost_per_token": 2.6e-07, + "max_input_tokens": 16384, + "mode": "decisions", + "output_cost_per_token": 0.0, "source": "https://inference.baseten.co/v1/models", + "supports_vision": true + }, + "gpt-6-rosalind": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_creation_input_token_cost_above_12hr": 3.75e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 7.5e-05, + "cache_creation_input_token_cost_above_272k_tokens": 3.75e-05, + "cache_read_input_token_cost": 1.5e-06, + "cache_read_input_token_cost_above_272k_tokens": 3e-06, + "input_cost_per_token": 1.5e-05, + "input_cost_per_token_above_272k_tokens": 3e-05, + "litellm_provider": "openai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "output_cost_per_token_above_272k_tokens": 0.0001125, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, + "source": "https://developers.openai.com/api/docs/pricing", + "supports_computer_use": true, "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": false + "supports_tool_search": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true }, - "baseten/deepseek-ai/DeepSeek-V4-Pro": { - "cache_read_input_token_cost": 1.45e-07, - "input_cost_per_token": 1.74e-06, - "litellm_provider": "baseten", - "max_input_tokens": 1048576, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 3.48e-06, - "source": "https://inference.baseten.co/v1/models", + "chatgpt/gpt-6-rosalind": { + "litellm_provider": "chatgpt", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "responses", + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/responses" + ], "supports_function_calling": true, - "supports_prompt_caching": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true, + "supports_xhigh_reasoning_effort": true }, - "baseten/deepseek-ai/DeepSeek-V4-Pro-0813": { - "cache_read_input_token_cost": 1.32e-07, - "input_cost_per_token": 1.32e-06, - "litellm_provider": "baseten", - "max_input_tokens": 1048576, - "max_output_tokens": 262144, - "max_tokens": 262144, + "gpt-6-cyber": { + "cache_creation_input_token_cost": 2.5e-05, + "cache_creation_input_token_cost_above_12hr": 5e-05, + "cache_read_input_token_cost": 2e-06, + "cache_read_input_token_cost_above_272k_tokens": 4e-06, + "input_cost_per_token": 2e-05, + "input_cost_per_token_above_272k_tokens": 4e-05, + "litellm_provider": "openai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3.96e-06, - "source": "https://inference.baseten.co/v1/models", + "output_cost_per_token": 0.0001, + "output_cost_per_token_above_272k_tokens": 0.00015, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, "supports_function_calling": true, + "supports_native_streaming": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false + "supports_tool_search": true, + "supports_vision": true, + "supports_web_search": true }, - "baseten/zai-org/GLM-5.2-Fast": { - "cache_read_input_token_cost": 2.1e-07, - "input_cost_per_token": 2.1e-06, - "litellm_provider": "baseten", - "max_input_tokens": 1048576, - "max_output_tokens": 262144, - "max_tokens": 262144, + "gpt-6-astra-law": { + "cache_read_input_token_cost": 1e-06, + "input_cost_per_token": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 6.6e-06, - "source": "https://inference.baseten.co/v1/models", + "output_cost_per_token": 5e-05, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard", + "pro" + ], + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_tool_search": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true }, - "xai/grok-code-fast": { - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_image_token": 1e-06, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_200k_tokens": 2e-06, - "litellm_provider": "xai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 2e-06, - "output_cost_per_token_above_200k_tokens": 4e-06, - "source": "https://api.x.ai/v1/language-models", + "chatgpt/gpt-6-astra-law": { + "litellm_provider": "chatgpt", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "responses", + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], "supports_function_calling": true, - "supports_prompt_caching": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_xhigh_reasoning_effort": true }, - "xai/grok-code-fast-1": { - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_image_token": 1e-06, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_200k_tokens": 2e-06, - "litellm_provider": "xai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "nebius/deepseek-ai/DeepSeek-V4.1-Flash-1017": { + "max_input_tokens": 1048576, + "input_cost_per_token": 3e-07, + "cache_read_input_token_cost": 6e-09, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 2e-06, - "output_cost_per_token_above_200k_tokens": 4e-06, - "source": "https://api.x.ai/v1/language-models", + "supports_vision": true, + "supports_reasoning": true, "supports_function_calling": true, - "supports_prompt_caching": true, + "source": "https://tokenfactory.nebius.com/api/public/models_info" + }, + "nebius/meta-models/muse-spark-open": { + "max_input_tokens": 1048576, + "input_cost_per_token": 1.25e-06, + "cache_read_input_token_cost": 1.5e-07, + "output_cost_per_token": 4.25e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_vision": true, + "supports_video_input": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_function_calling": true, + "source": "https://tokenfactory.nebius.com/api/public/models_info" }, - "xai/grok-code-fast-1-0825": { - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_image_token": 1e-06, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_200k_tokens": 2e-06, - "litellm_provider": "xai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "nebius/MiniMaxAI/MiniMax-M3.1-Flash": { + "max_input_tokens": 1048576, + "input_cost_per_token": 1.5e-07, + "cache_read_input_token_cost": 1.5e-08, + "output_cost_per_token": 6e-07, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 2e-06, - "output_cost_per_token_above_200k_tokens": 4e-06, - "source": "https://api.x.ai/v1/language-models", - "supports_function_calling": true, - "supports_prompt_caching": true, + "supports_vision": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_function_calling": true, + "source": "https://tokenfactory.nebius.com/api/public/models_info" }, - "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro": { - "cache_read_input_token_cost": 6e-07, - "cache_read_input_token_cost_priority": 6e-07, - "deprecation_date": "2026-08-27", - "input_cost_per_token": 1.2e-06, - "input_cost_per_token_priority": 1.2e-06, - "litellm_provider": "fireworks_ai", + "nebius/nvidia/Nemotron-3.5-Super-VL": { "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, + "input_cost_per_token": 3e-07, + "cache_read_input_token_cost": 6e-08, + "output_cost_per_token": 9e-07, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 1.2e-06, - "output_cost_per_token_priority": 1.2e-06, - "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_vision": true, + "supports_video_input": true, + "supports_reasoning": true, "supports_function_calling": true, + "source": "https://tokenfactory.nebius.com/api/public/models_info" + }, + "empiriolabs/aplomb-1": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1000000, + "input_cost_per_token": 2e-08, + "output_cost_per_token": 0.0, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages", + "/v1/decisions" + ], + "supports_vision": true, + "supports_audio_input": true, + "source": "https://empiriolabs.ai/models/aplomb-1" + }, + "empiriolabs/deepseek-v4-1-flash-1017": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 8e-07, + "supports_system_messages": true, + "supports_vision": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false + "source": "https://empiriolabs.ai/models/deepseek-v4-1-flash-1017", + "cache_read_input_token_cost": 2e-08, + "supports_prompt_caching": true, + "supports_function_calling": true }, - "fireworks_ai/accounts/fireworks/models/minimax-m2p7": { - "cache_read_input_token_cost_priority": 6e-07, - "deprecation_date": "2026-08-27", - "input_cost_per_token_priority": 1.2e-06, - "litellm_provider": "fireworks_ai", - "max_input_tokens": 196608, - "max_output_tokens": 196608, - "max_tokens": 196608, + "empiriolabs/deepseek-v4-flash-0731": { + "litellm_provider": "empiriolabs", "mode": "chat", - "output_cost_per_token_priority": 1.2e-06, - "source": "https://api.fireworks.ai/v1/serverless/models", - "supports_function_calling": true, + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "input_cost_per_token": 4.24e-07, + "output_cost_per_token": 1.272e-06, + "supports_system_messages": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true + "source": "https://empiriolabs.ai/models/deepseek-v4-flash-0731", + "supports_function_calling": true }, - "fireworks_ai/accounts/fireworks/models/ember-1": { - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "litellm_provider": "fireworks_ai", - "max_input_tokens": 1048576, + "empiriolabs/deepseek-v4-flash-0731:variant1": { + "litellm_provider": "empiriolabs", "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://api.fireworks.ai/v1/serverless/models", - "supports_function_calling": true, + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "input_cost_per_token": 4.4e-07, + "output_cost_per_token": 1.32e-06, + "supports_system_messages": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true + "source": "https://empiriolabs.ai/models/deepseek-v4-flash-0731", + "supports_function_calling": true }, - "openrouter/anthropic/claude-opus-5.5:batch": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_1hr": 4e-06, - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/deepseek-v4-pro": { + "litellm_provider": "empiriolabs", "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "input_cost_per_token": 1.65e-06, + "output_cost_per_token": 3.3e-06, + "supports_system_messages": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "source": "https://empiriolabs.ai/models/deepseek-v4-pro", + "supports_function_calling": true }, - "openrouter/cohere/command-a-plus": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 192000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "empiriolabs/deepseek-v4-pro-0813": { + "litellm_provider": "empiriolabs", "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "input_cost_per_token": 1.32e-06, + "output_cost_per_token": 3.96e-06, + "supports_system_messages": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": false + "source": "https://empiriolabs.ai/models/deepseek-v4-pro-0813", + "supports_function_calling": true }, - "openrouter/deepseek/deepseek-v4.1-flash:batch": { - "cache_read_input_token_cost": 3.36e-09, - "input_cost_per_token": 1.12e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, + "empiriolabs/deepseek-v4-pro:variant1": { + "litellm_provider": "empiriolabs", "mode": "chat", - "output_cost_per_token": 3.36e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "input_cost_per_token": 2.4e-06, + "output_cost_per_token": 4.8e-06, + "supports_system_messages": true, "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.02, + "search_context_size_medium": 0.02, + "search_context_size_high": 0.02 + }, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "source": "https://empiriolabs.ai/models/deepseek-v4-pro", + "supports_function_calling": true }, - "openrouter/openai/gpt-6-luna-pro:batch": { - "cache_creation_input_token_cost": 6.25e-08, - "cache_creation_input_token_cost_above_272k_tokens": 1.25e-07, - "cache_read_input_token_cost": 5e-09, - "cache_read_input_token_cost_above_272k_tokens": 1e-08, - "input_cost_per_token": 5e-08, - "input_cost_per_token_above_272k_tokens": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/deepseek-v4-pro:variant2": { + "litellm_provider": "empiriolabs", "mode": "chat", - "output_cost_per_token": 2.5e-07, - "output_cost_per_token_above_272k_tokens": 3.75e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "input_cost_per_token": 1.65e-06, + "output_cost_per_token": 3.301e-06, + "cache_read_input_token_cost": 1.38e-07, + "supports_system_messages": true, "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 + }, + "supports_prompt_caching": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "source": "https://empiriolabs.ai/models/deepseek-v4-pro", + "supports_function_calling": true }, - "openrouter/openai/gpt-6-luna:batch": { - "cache_creation_input_token_cost": 6.25e-08, - "cache_creation_input_token_cost_above_272k_tokens": 1.25e-07, - "cache_read_input_token_cost": 5e-09, - "cache_read_input_token_cost_above_272k_tokens": 1e-08, - "input_cost_per_token": 5e-08, - "input_cost_per_token_above_272k_tokens": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/deepseek-v4-pro:variant3": { + "litellm_provider": "empiriolabs", "mode": "chat", - "output_cost_per_token": 2.5e-07, - "output_cost_per_token_above_272k_tokens": 3.75e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "input_cost_per_token": 2.4e-06, + "output_cost_per_token": 4.8e-06, + "supports_system_messages": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "source": "https://empiriolabs.ai/models/deepseek-v4-pro", + "supports_function_calling": true }, - "openrouter/openai/gpt-6-sol-pro:batch": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_272k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/fugu-max": { + "litellm_provider": "empiriolabs", "mode": "chat", - "output_cost_per_token": 5e-06, - "output_cost_per_token_above_272k_tokens": 7.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 2.5e-07, + "supports_system_messages": true, + "supports_vision": true, "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.007, + "search_context_size_medium": 0.007, + "search_context_size_high": 0.007 + }, + "supports_prompt_caching": true, + "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "source": "https://empiriolabs.ai/models/fugu-max" }, - "openrouter/openai/gpt-6-sol:batch": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_272k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/fugu-ultra-v1-0": { + "litellm_provider": "empiriolabs", "mode": "chat", - "output_cost_per_token": 5e-06, - "output_cost_per_token_above_272k_tokens": 7.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "input_cost_per_token": 7.5e-06, + "output_cost_per_token": 4.5e-05, + "input_cost_per_token_above_272k_tokens": 1.5e-05, + "output_cost_per_token_above_272k_tokens": 6.75e-05, + "cache_read_input_token_cost_above_272k_tokens": 3e-06, + "cache_read_input_token_cost": 1.5e-06, + "supports_system_messages": true, + "supports_vision": true, "supports_reasoning": true, + "supports_web_search": true, + "supports_prompt_caching": true, + "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "source": "https://empiriolabs.ai/models/fugu-ultra-v1-0" }, - "openrouter/openai/gpt-6.1-sol": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/fugu-ultra-v1-1": { + "litellm_provider": "empiriolabs", "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 3e-05, + "input_cost_per_token_above_272k_tokens": 1e-05, + "output_cost_per_token_above_272k_tokens": 4.5e-05, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "cache_read_input_token_cost": 5e-07, + "supports_system_messages": true, + "supports_vision": true, "supports_reasoning": true, + "supports_web_search": true, + "supports_prompt_caching": true, + "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "source": "https://empiriolabs.ai/models/fugu-ultra-v1-1" }, - "openrouter/openai/gpt-6.1-sol-pro": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/fugu-ultra-v2-0": { + "litellm_provider": "empiriolabs", "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 3e-05, + "input_cost_per_token_above_272k_tokens": 1e-05, + "output_cost_per_token_above_272k_tokens": 4.5e-05, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "cache_read_input_token_cost": 5e-07, + "supports_system_messages": true, + "supports_vision": true, "supports_reasoning": true, + "supports_web_search": true, + "supports_prompt_caching": true, + "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "source": "https://empiriolabs.ai/models/fugu-ultra-v2-0" }, - "openrouter/openai/gpt-6.1-sol-pro:batch": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, - "cache_read_input_token_cost": 5e-08, - "cache_read_input_token_cost_above_272k_tokens": 1e-07, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_272k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/gemma-4-26b-a4b": { + "litellm_provider": "empiriolabs", "mode": "chat", - "output_cost_per_token": 5e-06, - "output_cost_per_token_above_272k_tokens": 7.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 2.9e-07, + "cache_read_input_token_cost": 2.5e-08, + "supports_system_messages": true, + "supports_vision": true, "supports_reasoning": true, + "supports_prompt_caching": true, + "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "source": "https://empiriolabs.ai/models/gemma-4-26b-a4b" }, - "openrouter/openai/gpt-6.1-sol:batch": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, - "cache_read_input_token_cost": 5e-08, - "cache_read_input_token_cost_above_272k_tokens": 1e-07, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_272k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/glm-4-6v-flashx": { + "litellm_provider": "empiriolabs", "mode": "chat", - "output_cost_per_token": 5e-06, - "output_cost_per_token_above_272k_tokens": 7.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "input_cost_per_token": 4e-08, + "output_cost_per_token": 4e-07, + "cache_read_input_token_cost": 3.6e-08, + "supports_system_messages": true, + "supports_vision": true, "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.033, + "search_context_size_medium": 0.033, + "search_context_size_high": 0.033 + }, + "supports_prompt_caching": true, + "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "source": "https://empiriolabs.ai/models/glm-4-6v-flashx" }, - "openrouter/openai/gpt-oss-20b:batch": { - "input_cost_per_token": 2.4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, + "empiriolabs/glm-4-7-flashx": { + "litellm_provider": "empiriolabs", "mode": "chat", - "output_cost_per_token": 1.12e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, + "max_input_tokens": 202752, + "max_output_tokens": 131072, + "input_cost_per_token": 7e-08, + "output_cost_per_token": 4e-07, + "cache_read_input_token_cost": 6.3e-08, + "supports_system_messages": true, "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.033, + "search_context_size_medium": 0.033, + "search_context_size_high": 0.033 + }, + "supports_prompt_caching": true, + "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false + "source": "https://empiriolabs.ai/models/glm-4-7-flashx" }, - "openrouter/qwen/qwen3.8-omni-flash": { - "cache_read_input_token_cost": 1.6e-08, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, + "empiriolabs/glm-5-1": { + "litellm_provider": "empiriolabs", "mode": "chat", - "output_cost_per_token": 4.7e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, + "max_input_tokens": 202745, + "max_output_tokens": 128000, + "input_cost_per_token": 8.25e-07, + "output_cost_per_token": 3.301e-06, + "input_cost_per_token_above_32k_tokens": 1.1e-06, + "output_cost_per_token_above_32k_tokens": 3.851e-06, + "cache_read_input_token_cost_above_32k_tokens": 2.2e-07, + "cache_read_input_token_cost": 1.65e-07, + "supports_system_messages": true, "supports_reasoning": true, + "supports_prompt_caching": true, + "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "source": "https://empiriolabs.ai/models/glm-5-1" }, - "openrouter/perceptron/perceptron-mk1.5": { - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 36864, - "max_output_tokens": 8192, - "max_tokens": 8192, + "empiriolabs/glm-5-2": { + "litellm_provider": "empiriolabs", "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "supports_system_messages": true, "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.033, + "search_context_size_medium": 0.033, + "search_context_size_high": 0.033 + }, + "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true + "source": "https://empiriolabs.ai/models/glm-5-2" }, - "vertex_ai/gemini-2.0-flash": { - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 1e-06, - "input_cost_per_audio_token_batches": 5e-07, - "input_cost_per_character": 3.75e-08, - "input_cost_per_token": 1.5e-07, - "input_cost_per_token_batches": 7.5e-08, - "litellm_provider": "vertex_ai", + "empiriolabs/glm-5-2:variant1": { + "litellm_provider": "empiriolabs", "mode": "chat", - "output_cost_per_token": 6e-07, - "output_cost_per_token_batches": 3e-07, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 1.1e-06, + "output_cost_per_token": 3.851e-06, + "cache_read_input_token_cost": 2.75e-07, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.013, + "search_context_size_medium": 0.013, + "search_context_size_high": 0.013 + }, + "supports_prompt_caching": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/glm-5-2", + "supports_function_calling": true }, - "vertex_ai/gemini-2.0-flash-lite": { - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7.5e-08, - "input_cost_per_audio_token_batches": 3.75e-08, - "input_cost_per_character": 1.875e-08, - "input_cost_per_token": 7.5e-08, - "input_cost_per_token_batches": 3.75e-08, - "litellm_provider": "vertex_ai", + "empiriolabs/glm-5-2:variant2": { + "litellm_provider": "empiriolabs", "mode": "chat", - "output_cost_per_token": 3e-07, - "output_cost_per_token_batches": 1.5e-07, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" - }, - "vertex_ai/zai-org/glm-5.2-maas": { - "cache_read_input_token_cost": 1.4e-07, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, "input_cost_per_token": 1.4e-06, - "litellm_provider": "vertex_ai-zai_models", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", "output_cost_per_token": 4.4e-06, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", - "supported_regions": ["global"], - "supports_function_calling": true, - "supports_prompt_caching": true, + "supports_system_messages": true, "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.013, + "search_context_size_medium": 0.013, + "search_context_size_high": 0.013 + }, "supports_response_schema": true, - "supports_tool_choice": true + "source": "https://empiriolabs.ai/models/glm-5-2", + "supports_function_calling": true }, - "vertex_ai/meta/llama-3.3-70b-instruct-maas": { - "deprecation_date": "2026-10-21", - "input_cost_per_token": 7.2e-07, - "input_cost_per_token_batches": 3.6e-07, - "litellm_provider": "vertex_ai-llama_models", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "empiriolabs/glm-5-3": { + "litellm_provider": "empiriolabs", "mode": "chat", - "output_cost_per_token": 7.2e-07, - "output_cost_per_token_batches": 3.6e-07, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "text", - "code" - ], + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.033, + "search_context_size_medium": 0.033, + "search_context_size_high": 0.033 + }, "supports_function_calling": true, - "supports_tool_choice": true + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/glm-5-3" }, - "vertex_ai/veo-3.0-generate-001": { - "deprecation_date": "2026-06-30", - "litellm_provider": "vertex_ai-video-models", - "max_input_tokens": 1024, - "max_tokens": 1024, - "mode": "video_generation", - "output_cost_per_second": 0.4, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#veo", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "video" - ] - }, - "vertex_ai/veo-3.0-fast-generate-001": { - "deprecation_date": "2026-06-30", - "litellm_provider": "vertex_ai-video-models", - "max_input_tokens": 1024, - "max_tokens": 1024, - "mode": "video_generation", - "output_cost_per_second": 0.1, - "output_cost_per_second_1080p": 0.12, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#veo", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "video" - ] - }, - "vertex_ai/veo-2.0-generate-001": { - "litellm_provider": "vertex_ai-video-models", - "max_input_tokens": 1024, - "max_tokens": 1024, - "mode": "video_generation", - "output_cost_per_second": 0.5, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#veo", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "video" - ] - }, - "vertex_ai/virtual-try-on-001": { - "deprecation_date": "2027-03-15", - "litellm_provider": "vertex_ai", - "mode": "image_generation", - "output_cost_per_image": 0.06, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", - "supported_modalities": [ - "image" - ], - "supported_output_modalities": [ - "image" - ] - }, - "vertex_ai/gemini-2.5-flash-tts": { - "input_cost_per_token": 5e-07, - "input_cost_per_token_batches": 2.5e-07, - "litellm_provider": "vertex_ai", - "mode": "audio_speech", - "output_cost_per_audio_token": 1e-05, - "output_cost_per_token": 1e-05, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" - }, - "vertex_ai/gemini-2.5-pro-tts": { - "input_cost_per_token": 1e-06, - "input_cost_per_token_batches": 5e-07, - "litellm_provider": "vertex_ai", - "mode": "audio_speech", - "output_cost_per_audio_token": 2e-05, - "output_cost_per_token": 2e-05, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" - }, - "anthropic.claude-mythos-5-1": { - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/glm-5-3-flash": { + "litellm_provider": "empiriolabs", "mode": "chat", - "supports_adaptive_thinking": true, - "thinking_always_on": true, - "supports_mid_conversation_system": true, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 7.5e-08, + "output_cost_per_token": 2.5e-07, + "supports_system_messages": true, + "supports_vision": true, "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.033, + "search_context_size_medium": 0.033, + "search_context_size_high": 0.033 + }, + "supports_function_calling": true, "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, - "supports_max_reasoning_effort": true, - "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh", - "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512, - "cache_creation_input_token_cost_above_1hr": 2e-05, - "cache_creation_input_token_cost": 1.25e-05, - "cache_read_input_token_cost": 2.5e-07, - "output_cost_per_token": 5e-05, - "input_cost_per_token": 1e-05, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://empiriolabs.ai/models/glm-5-3-flash" }, - "global.anthropic.claude-mythos-5-1": { - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/kimi-k2-6": { + "litellm_provider": "empiriolabs", "mode": "chat", - "supports_adaptive_thinking": true, - "thinking_always_on": true, - "supports_mid_conversation_system": true, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "max_input_tokens": 262144, + "max_output_tokens": 16000, + "input_cost_per_token": 8.939e-07, + "output_cost_per_token": 3.7131e-06, + "cache_read_input_token_cost": 1.788e-07, + "supports_system_messages": true, + "supports_vision": true, "supports_reasoning": true, + "supports_prompt_caching": true, "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, - "supports_max_reasoning_effort": true, - "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh", - "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512, - "cache_read_input_token_cost": 2.5e-07, - "cache_creation_input_token_cost": 1.25e-05, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 5e-05, - "cache_creation_input_token_cost_above_1hr": 2e-05, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://empiriolabs.ai/models/kimi-k2-6", + "supports_function_calling": true }, - "us.anthropic.claude-mythos-5-1": { - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/kimi-k2-7-code": { + "litellm_provider": "empiriolabs", "mode": "chat", - "supports_adaptive_thinking": true, - "thinking_always_on": true, - "supports_mid_conversation_system": true, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "input_cost_per_token": 9.5e-07, + "output_cost_per_token": 4e-06, + "supports_system_messages": true, + "supports_vision": true, "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.015, + "search_context_size_medium": 0.015, + "search_context_size_high": 0.015 + }, "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, - "supports_max_reasoning_effort": true, - "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh", - "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512, - "input_cost_per_token": 1.1e-05, - "output_cost_per_token": 5.5e-05, - "cache_read_input_token_cost": 2.75e-07, - "cache_creation_input_token_cost": 1.375e-05, - "cache_creation_input_token_cost_above_1hr": 2.2e-05, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://empiriolabs.ai/models/kimi-k2-7-code", + "supports_function_calling": true }, - "us.anthropic.claude-mythos-5": { - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/kimi-k2-7-code-highspeed": { + "litellm_provider": "empiriolabs", "mode": "chat", - "supports_adaptive_thinking": true, - "thinking_always_on": true, - "supports_mid_conversation_system": true, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "input_cost_per_token": 1.9e-06, + "output_cost_per_token": 8e-06, + "supports_system_messages": true, + "supports_vision": true, "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.015, + "search_context_size_medium": 0.015, + "search_context_size_high": 0.015 + }, "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, - "supports_max_reasoning_effort": true, - "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh", - "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512, - "cache_creation_input_token_cost": 1.375e-05, - "input_cost_per_token": 1.1e-05, - "cache_read_input_token_cost": 1.1e-06, - "output_cost_per_token": 5.5e-05, - "cache_creation_input_token_cost_above_1hr": 2.2e-05, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://empiriolabs.ai/models/kimi-k2-7-code-highspeed", + "supports_function_calling": true }, - "apac.anthropic.claude-fable-5": { - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/kimi-k2-7-code:variant1": { + "litellm_provider": "empiriolabs", "mode": "chat", - "supports_adaptive_thinking": true, - "thinking_always_on": true, - "supports_mid_conversation_system": true, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "input_cost_per_token": 8.939e-07, + "output_cost_per_token": 3.7131e-06, + "cache_read_input_token_cost": 1.788e-07, + "supports_system_messages": true, + "supports_vision": true, "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.013, + "search_context_size_medium": 0.013, + "search_context_size_high": 0.013 + }, + "supports_prompt_caching": true, "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, - "supports_max_reasoning_effort": true, - "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh", - "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512, - "output_cost_per_token": 5.5e-05, - "cache_creation_input_token_cost": 1.375e-05, - "cache_read_input_token_cost": 1.1e-06, - "input_cost_per_token": 1.1e-05, - "cache_creation_input_token_cost_above_1hr": 2.2e-05, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://empiriolabs.ai/models/kimi-k2-7-code", + "supports_function_calling": true }, - "au.anthropic.claude-fable-5": { - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/kimi-k3": { + "litellm_provider": "empiriolabs", "mode": "chat", - "supports_adaptive_thinking": true, - "thinking_always_on": true, - "supports_mid_conversation_system": true, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "supports_system_messages": true, + "supports_vision": true, "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.015, + "search_context_size_medium": 0.015, + "search_context_size_high": 0.015 + }, "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, - "supports_max_reasoning_effort": true, - "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh", - "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512, - "output_cost_per_token": 5.5e-05, - "cache_creation_input_token_cost": 1.375e-05, - "cache_read_input_token_cost": 1.1e-06, - "input_cost_per_token": 1.1e-05, - "cache_creation_input_token_cost_above_1hr": 2.2e-05, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://empiriolabs.ai/models/kimi-k3", + "supports_function_calling": true }, - "apac.anthropic.claude-opus-4-7": { - "bedrock_converse_supports_strict_tools": false, - "supports_adaptive_thinking": true, - "litellm_provider": "bedrock_converse", - "supports_tool_search": true, - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/kimi-k3-1-pro": { + "litellm_provider": "empiriolabs", "mode": "chat", - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1.8e-06, + "supports_system_messages": true, + "supports_vision": true, "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.015, + "search_context_size_medium": 0.015, + "search_context_size_high": 0.015 + }, + "supports_prompt_caching": true, "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": false, - "supports_max_reasoning_effort": true, - "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh", - "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 2048, - "output_cost_per_token": 2.75e-05, - "cache_creation_input_token_cost": 6.875e-06, - "input_cost_per_token": 5.5e-06, - "cache_creation_input_token_cost_above_1hr": 1.1e-05, - "cache_read_input_token_cost": 5.5e-07, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "supports_function_calling": true, + "source": "https://empiriolabs.ai/models/kimi-k3-1-pro" }, - "apac.anthropic.claude-opus-4-8": { - "bedrock_converse_supports_strict_tools": false, - "supports_adaptive_thinking": true, - "supports_mid_conversation_system": true, - "litellm_provider": "bedrock_converse", - "supports_tool_search": true, - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/mimo-v2-6-flash": { + "litellm_provider": "empiriolabs", "mode": "chat", - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 2.8e-07, + "supports_system_messages": true, + "supports_vision": true, "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.015, + "search_context_size_medium": 0.015, + "search_context_size_high": 0.015 + }, "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": false, - "supports_max_reasoning_effort": true, - "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh", - "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024, - "input_cost_per_token": 5.5e-06, - "cache_creation_input_token_cost_above_1hr": 1.1e-05, - "output_cost_per_token": 2.75e-05, - "cache_read_input_token_cost": 5.5e-07, - "cache_creation_input_token_cost": 6.875e-06, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "supports_audio_input": true, + "source": "https://empiriolabs.ai/models/mimo-v2-6-flash", + "supports_function_calling": true }, - "apac.anthropic.claude-opus-5": { - "bedrock_converse_supports_strict_tools": false, - "supports_adaptive_thinking": true, - "supports_mid_conversation_system": true, - "litellm_provider": "bedrock_converse", - "supports_tool_search": true, - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/mimo-v2-6-pro": { + "litellm_provider": "empiriolabs", "mode": "chat", - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 4.35e-07, + "output_cost_per_token": 8.7e-07, + "supports_system_messages": true, + "supports_vision": true, "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.015, + "search_context_size_medium": 0.015, + "search_context_size_high": 0.015 + }, "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": false, - "supports_max_reasoning_effort": true, - "supports_output_config": true, - "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512, - "cache_creation_input_token_cost_above_1hr": 1.1e-05, - "cache_creation_input_token_cost": 6.875e-06, - "input_cost_per_token": 5.5e-06, - "cache_read_input_token_cost": 5.5e-07, - "output_cost_per_token": 2.75e-05, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "supports_audio_input": true, + "source": "https://empiriolabs.ai/models/mimo-v2-6-pro", + "supports_function_calling": true }, - "apac.anthropic.claude-opus-5-5": { - "bedrock_converse_supports_strict_tools": false, - "supports_adaptive_thinking": true, - "supports_mid_conversation_system": true, - "litellm_provider": "bedrock_converse", - "supports_tool_search": true, - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/mimo-v2-6-pro-ultraspeed": { + "litellm_provider": "empiriolabs", "mode": "chat", - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 4.35e-06, + "output_cost_per_token": 8.7e-06, + "supports_system_messages": true, + "supports_vision": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": false, - "supports_max_reasoning_effort": true, - "supports_output_config": true, - "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512, - "thinking_always_on": true, - "supports_forced_tool_use": false, - "cache_creation_input_token_cost_above_1hr": 8.8e-06, - "cache_creation_input_token_cost": 5.5e-06, - "input_cost_per_token": 4.4e-06, - "output_cost_per_token": 2.2e-05, - "cache_read_input_token_cost": 2.2e-07, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "supports_audio_input": true, + "source": "https://empiriolabs.ai/models/mimo-v2-6-pro-ultraspeed", + "supports_function_calling": true }, - "apac.anthropic.claude-sonnet-4-6": { - "supports_adaptive_thinking": true, - "supports_legacy_thinking": true, - "litellm_provider": "bedrock_converse", - "supports_tool_search": true, - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "empiriolabs/minimax-m2-7": { + "litellm_provider": "empiriolabs", "mode": "chat", - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "cache_read_input_token_cost": 3e-08, + "supports_system_messages": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_max_reasoning_effort": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_native_structured_output": true, - "supports_output_config": true, - "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024, - "output_cost_per_token": 1.65e-05, - "cache_creation_input_token_cost_above_1hr": 6.6e-06, - "cache_read_input_token_cost": 3.3e-07, - "cache_creation_input_token_cost": 4.125e-06, - "input_cost_per_token": 3.3e-06, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "supports_prompt_caching": true, + "supports_function_calling": true, + "source": "https://empiriolabs.ai/models/minimax-m2-7" }, - "apac.anthropic.claude-sonnet-5": { - "bedrock_converse_supports_strict_tools": false, - "litellm_provider": "bedrock_converse", - "supports_tool_search": true, - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/minimax-m2-7-highspeed": { + "litellm_provider": "empiriolabs", "mode": "chat", - "supports_adaptive_thinking": true, - "supports_mid_conversation_system": true, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 3e-08, + "supports_system_messages": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_function_calling": true, + "source": "https://empiriolabs.ai/models/minimax-m2-7-highspeed" + }, + "empiriolabs/minimax-m3": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1048576, + "max_output_tokens": 524288, + "input_cost_per_token": 2.25e-07, + "output_cost_per_token": 9e-07, + "input_cost_per_token_above_512k_tokens": 4.5e-07, + "output_cost_per_token_above_512k_tokens": 1.8e-06, + "cache_read_input_token_cost_above_512k_tokens": 9e-08, + "cache_read_input_token_cost": 4.5e-08, + "supports_system_messages": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": false, - "supports_max_reasoning_effort": true, - "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh", - "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024, - "cache_creation_input_token_cost_above_1hr": 4.4e-06, - "cache_creation_input_token_cost": 2.75e-06, - "input_cost_per_token": 2.2e-06, - "output_cost_per_token": 1.1e-05, - "cache_read_input_token_cost": 2.2e-07, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 + }, + "supports_prompt_caching": true, + "supports_function_calling": true, + "source": "https://empiriolabs.ai/models/minimax-m3" }, - "us.anthropic.claude-mythos-preview": { - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/minimax-m3-1-flash": { + "litellm_provider": "empiriolabs", "mode": "chat", - "thinking_always_on": true, - "supports_function_calling": true, + "max_input_tokens": 1048576, + "max_output_tokens": 524288, + "input_cost_per_token": 1.125e-07, + "output_cost_per_token": 4.5e-07, + "cache_read_input_token_cost": 1.125e-08, + "supports_system_messages": true, "supports_vision": true, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true, - "supports_output_config": true, - "cache_creation_input_token_cost_above_1hr": 5.5e-05, - "cache_read_input_token_cost": 2.75e-06, - "cache_creation_input_token_cost": 3.4375e-05, - "output_cost_per_token": 0.0001375, - "input_cost_per_token": 2.75e-05, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 + }, + "supports_prompt_caching": true, + "supports_function_calling": true, + "source": "https://empiriolabs.ai/models/minimax-m3-1-flash" }, - "apac.anthropic.claude-mythos-preview": { - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/minimax-m3:priority": { + "litellm_provider": "empiriolabs", "mode": "chat", - "thinking_always_on": true, - "supports_function_calling": true, + "max_input_tokens": 1048458, + "max_output_tokens": 524288, + "input_cost_per_token": 3.375e-07, + "output_cost_per_token": 1.35e-06, + "input_cost_per_token_above_512k_tokens": 6.75e-07, + "output_cost_per_token_above_512k_tokens": 2.7e-06, + "cache_read_input_token_cost_above_512k_tokens": 1.35e-07, + "cache_read_input_token_cost": 6.75e-08, + "supports_system_messages": true, "supports_vision": true, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true, - "supports_output_config": true, - "input_cost_per_token": 2.75e-05, - "cache_creation_input_token_cost": 3.4375e-05, - "output_cost_per_token": 0.0001375, - "cache_creation_input_token_cost_above_1hr": 5.5e-05, - "cache_read_input_token_cost": 2.75e-06, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 + }, + "supports_prompt_caching": true, + "supports_function_calling": true, + "source": "https://empiriolabs.ai/models/minimax-m3" }, - "au.anthropic.claude-mythos-preview": { - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/mistral-small-4": { + "litellm_provider": "empiriolabs", "mode": "chat", - "thinking_always_on": true, - "supports_function_calling": true, + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "supports_system_messages": true, + "supports_vision": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.084, + "search_context_size_medium": 0.084, + "search_context_size_high": 0.14 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/mistral-small-4", + "supports_function_calling": true + }, + "empiriolabs/muse-glimmer-30b": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 8e-07, + "cache_read_input_token_cost": 5e-08, + "supports_system_messages": true, "supports_vision": true, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true, - "supports_output_config": true, - "input_cost_per_token": 2.75e-05, - "cache_creation_input_token_cost": 3.4375e-05, - "output_cost_per_token": 0.0001375, - "cache_creation_input_token_cost_above_1hr": 5.5e-05, - "cache_read_input_token_cost": 2.75e-06, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "supports_prompt_caching": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/muse-glimmer-30b", + "supports_function_calling": true }, - "deepseek.r1-v1:0": { - "input_cost_per_token": 1.35e-06, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "empiriolabs/muse-spark-1-1": { + "litellm_provider": "empiriolabs", "mode": "chat", - "output_cost_per_token": 5.4e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", - "supports_function_calling": false, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 4.25e-06, + "cache_read_input_token_cost": 1e-06, + "supports_system_messages": true, + "supports_vision": true, "supports_reasoning": true, - "supports_tool_choice": false + "supports_web_search": true, + "supports_prompt_caching": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_audio_input": true, + "source": "https://empiriolabs.ai/models/muse-spark-1-1" }, - "mistral.pixtral-large-2502-v1:0": { - "input_cost_per_token": 2e-06, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "empiriolabs/muse-spark-1-2": { + "litellm_provider": "empiriolabs", "mode": "chat", - "output_cost_per_token": 6e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 4.25e-06, + "cache_read_input_token_cost": 1e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "supports_prompt_caching": true, "supports_function_calling": true, - "supports_tool_choice": false + "supports_response_schema": true, + "supports_audio_input": true, + "source": "https://empiriolabs.ai/models/muse-spark-1-2" }, - "azure_ai/MAI-Cyber-1-Flash": { - "cache_read_input_token_cost": 6e-08, - "input_cost_per_token": 6e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 256000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "empiriolabs/muse-spark-1-3": { + "litellm_provider": "empiriolabs", "mode": "chat", - "output_cost_per_token": 3.5e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 4.25e-06, + "cache_read_input_token_cost": 1e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "supports_prompt_caching": true, "supports_function_calling": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/muse-spark-1-3" + }, + "empiriolabs/nova-lite-1-0": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 317379, + "max_output_tokens": 10000, + "input_cost_per_token": 6.9e-08, + "output_cost_per_token": 2.8e-07, + "cache_read_input_token_cost": 3.86e-08, + "supports_system_messages": true, + "supports_vision": true, "supports_prompt_caching": true, + "source": "https://empiriolabs.ai/models/nova-lite-1-0", + "supports_function_calling": true + }, + "empiriolabs/nova-lite-2": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "input_cost_per_token": 3.8e-07, + "output_cost_per_token": 3.16e-06, + "cache_read_input_token_cost": 2.128e-07, + "supports_system_messages": true, + "supports_vision": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_prompt_caching": true, + "source": "https://empiriolabs.ai/models/nova-lite-2", + "supports_function_calling": true }, - "azure_ai/mistral-ocr-2505": { - "litellm_provider": "azure_ai", - "mode": "ocr", - "ocr_cost_per_page": 0.001, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/mistral-ai/" + "empiriolabs/nova-micro-1-0": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 133003, + "max_output_tokens": 10000, + "input_cost_per_token": 4e-08, + "output_cost_per_token": 1.6e-07, + "cache_read_input_token_cost": 2.24e-08, + "supports_system_messages": true, + "supports_prompt_caching": true, + "source": "https://empiriolabs.ai/models/nova-micro-1-0", + "supports_function_calling": true }, - "azure_ai/mistral-ocr-2512": { - "litellm_provider": "azure_ai", - "mode": "ocr", - "ocr_cost_per_page": 0.002, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/mistral-ai/" + "empiriolabs/nova-pro-1-0": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 317319, + "max_output_tokens": 10000, + "input_cost_per_token": 2.4e-06, + "output_cost_per_token": 9.6e-06, + "supports_system_messages": true, + "supports_vision": true, + "source": "https://empiriolabs.ai/models/nova-pro-1-0", + "supports_function_calling": true }, - "anthropic.claude-sonnet-5-5": { - "bedrock_converse_supports_strict_tools": false, - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_1hr": 4e-06, - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 2e-06, - "litellm_provider": "bedrock_converse", - "supports_tool_search": true, - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/perplexity-advanced-deep-research": { + "litellm_provider": "empiriolabs", "mode": "chat", - "output_cost_per_token": 1e-05, + "max_output_tokens": 16000, + "input_cost_per_token": 1.2e-05, + "output_cost_per_token": 6e-05, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_low": 0.012, + "search_context_size_medium": 0.012, + "search_context_size_high": 0.012 }, - "supports_adaptive_thinking": true, - "supports_mid_conversation_system": true, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "source": "https://empiriolabs.ai/models/perplexity-advanced-deep-research" + }, + "empiriolabs/perplexity-deep-research": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 919327, + "input_cost_per_token": 4.8e-06, + "output_cost_per_token": 1.9e-05, + "supports_system_messages": true, + "supports_vision": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, + "supports_web_search": true, + "source": "https://empiriolabs.ai/models/perplexity-deep-research" + }, + "empiriolabs/perplexity-pro-search": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_output_tokens": 32768, + "input_cost_per_token": 7.8e-06, + "output_cost_per_token": 3.9e-05, + "supports_system_messages": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": false, - "supports_max_reasoning_effort": true, - "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh", - "supports_parallel_tool_use_config": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, - "prompt_cache_min_tokens": 512, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "supports_reasoning": true, + "supports_web_search": true, + "source": "https://empiriolabs.ai/models/perplexity-pro-search" }, - "apac.anthropic.claude-sonnet-5-5": { - "bedrock_converse_supports_strict_tools": false, - "litellm_provider": "bedrock_converse", - "supports_tool_search": true, - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/perplexity-sonar": { + "litellm_provider": "empiriolabs", "mode": "chat", - "supports_adaptive_thinking": true, - "supports_mid_conversation_system": true, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "max_input_tokens": 919327, + "input_cost_per_token": 2.4e-06, + "output_cost_per_token": 2.4e-06, + "supports_system_messages": true, + "supports_vision": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, + "supports_web_search": true, + "source": "https://empiriolabs.ai/models/perplexity-sonar" + }, + "empiriolabs/perplexity-sonar-pro": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 919328, + "max_output_tokens": 32768, + "input_cost_per_token": 7.2e-06, + "output_cost_per_token": 3.6e-05, + "supports_system_messages": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": false, - "supports_max_reasoning_effort": true, - "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh", - "supports_parallel_tool_use_config": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, - "prompt_cache_min_tokens": 512, - "cache_creation_input_token_cost_above_1hr": 4.4e-06, - "cache_creation_input_token_cost": 2.75e-06, - "input_cost_per_token": 2.2e-06, - "output_cost_per_token": 1.1e-05, - "cache_read_input_token_cost": 2.2e-07, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "supports_reasoning": true, + "supports_web_search": true, + "source": "https://empiriolabs.ai/models/perplexity-sonar-pro" }, - "au.anthropic.claude-sonnet-5-5": { - "bedrock_converse_supports_strict_tools": false, - "cache_creation_input_token_cost": 2.75e-06, - "cache_creation_input_token_cost_above_1hr": 4.4e-06, - "cache_read_input_token_cost": 2.2e-07, - "input_cost_per_token": 2.2e-06, - "litellm_provider": "bedrock_converse", - "supports_tool_search": true, - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/perplexity-sonar-reasoning-pro": { + "litellm_provider": "empiriolabs", "mode": "chat", - "output_cost_per_token": 1.1e-05, + "max_input_tokens": 919330, + "max_output_tokens": 131072, + "input_cost_per_token": 4.8e-06, + "output_cost_per_token": 1.9e-05, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "source": "https://empiriolabs.ai/models/perplexity-sonar-reasoning-pro" + }, + "empiriolabs/qwen3-5-122b-a10b": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 258048, + "max_output_tokens": 64000, + "input_cost_per_token": 1.15e-07, + "output_cost_per_token": 9.17e-07, + "input_cost_per_token_above_128k_tokens": 2.87e-07, + "output_cost_per_token_above_128k_tokens": 2.294e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, "search_context_cost_per_query": { - "search_context_size_high": 0.01, "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 }, - "supports_adaptive_thinking": true, - "supports_mid_conversation_system": true, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": false, - "supports_max_reasoning_effort": true, - "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh", - "supports_parallel_tool_use_config": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, - "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://empiriolabs.ai/models/qwen3-5-122b-a10b", + "supports_function_calling": true }, - "azure_ai/claude-sonnet-5-5": { - "supports_mid_conversation_system": true, - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_1hr": 4e-06, - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 2e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/qwen3-5-27b": { + "litellm_provider": "empiriolabs", "mode": "chat", - "output_cost_per_token": 1e-05, + "max_input_tokens": 258048, + "max_output_tokens": 64000, + "input_cost_per_token": 8.6e-08, + "output_cost_per_token": 6.88e-07, + "input_cost_per_token_above_128k_tokens": 2.58e-07, + "output_cost_per_token_above_128k_tokens": 2.064e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, "search_context_cost_per_query": { - "search_context_size_high": 0.01, "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 }, - "supports_adaptive_thinking": true, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_max_reasoning_effort": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, - "prompt_cache_min_tokens": 512 + "source": "https://empiriolabs.ai/models/qwen3-5-27b", + "supports_function_calling": true }, - "bedrock/us-gov-east-1/anthropic.claude-sonnet-5-5": { - "bedrock_converse_supports_strict_tools": false, - "bedrock_output_config_effort_ceiling": "xhigh", - "cache_creation_input_token_cost": 3e-06, - "cache_creation_input_token_cost_above_1hr": 4.8e-06, - "cache_read_input_token_cost": 2.4e-07, - "input_cost_per_token": 2.4e-06, - "litellm_provider": "bedrock", - "supports_tool_search": true, - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/qwen3-5-35b-a3b": { + "litellm_provider": "empiriolabs", "mode": "chat", - "output_cost_per_token": 1.2e-05, - "supports_forced_tool_use": false, - "thinking_always_on": true, - "prompt_cache_min_tokens": 512, - "supports_adaptive_thinking": true, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_max_reasoning_effort": true, - "supports_mid_conversation_system": true, - "supports_native_structured_output": false, - "supports_output_config": true, - "supports_parallel_tool_use_config": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "max_input_tokens": 258048, + "max_output_tokens": 64000, + "input_cost_per_token": 5.7e-08, + "output_cost_per_token": 4.59e-07, + "input_cost_per_token_above_128k_tokens": 2.29e-07, + "output_cost_per_token_above_128k_tokens": 1.835e-06, + "supports_system_messages": true, + "supports_vision": true, "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 + }, "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, + "source": "https://empiriolabs.ai/models/qwen3-5-35b-a3b", + "supports_function_calling": true + }, + "empiriolabs/qwen3-5-397b-a17b": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 258048, + "max_output_tokens": 64000, + "input_cost_per_token": 1.72e-07, + "output_cost_per_token": 1.032e-06, + "input_cost_per_token_above_128k_tokens": 4.3e-07, + "output_cost_per_token_above_128k_tokens": 2.58e-06, + "supports_system_messages": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-5-397b-a17b", + "supports_function_calling": true }, - "bedrock/us-gov-west-1/anthropic.claude-sonnet-5-5": { - "bedrock_converse_supports_strict_tools": false, - "bedrock_output_config_effort_ceiling": "xhigh", - "cache_creation_input_token_cost": 3e-06, - "cache_creation_input_token_cost_above_1hr": 4.8e-06, - "cache_read_input_token_cost": 2.4e-07, - "input_cost_per_token": 2.4e-06, - "litellm_provider": "bedrock", - "supports_tool_search": true, - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/qwen3-5-4b": { + "litellm_provider": "empiriolabs", "mode": "chat", - "output_cost_per_token": 1.2e-05, - "supports_forced_tool_use": false, - "thinking_always_on": true, - "prompt_cache_min_tokens": 512, - "supports_adaptive_thinking": true, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_max_reasoning_effort": true, - "supports_mid_conversation_system": true, - "supports_native_structured_output": false, - "supports_output_config": true, - "supports_parallel_tool_use_config": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "input_cost_per_token": 4e-08, + "output_cost_per_token": 7e-08, + "cache_read_input_token_cost": 2e-08, + "supports_system_messages": true, + "supports_vision": true, "supports_reasoning": true, + "supports_prompt_caching": true, + "supports_function_calling": true, "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, + "source": "https://empiriolabs.ai/models/qwen3-5-4b" + }, + "empiriolabs/qwen3-5-9b": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 1.3e-07, + "cache_read_input_token_cost": 4.5e-08, + "supports_system_messages": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_reasoning": true, + "supports_prompt_caching": true, + "supports_function_calling": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-5-9b" }, - "eu.anthropic.claude-sonnet-5-5": { - "bedrock_converse_supports_strict_tools": false, - "cache_creation_input_token_cost": 2.75e-06, - "cache_creation_input_token_cost_above_1hr": 4.4e-06, - "cache_read_input_token_cost": 2.2e-07, - "input_cost_per_token": 2.2e-06, - "litellm_provider": "bedrock_converse", - "supports_tool_search": true, - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/qwen3-5-flash": { + "litellm_provider": "empiriolabs", "mode": "chat", - "output_cost_per_token": 1.1e-05, + "max_input_tokens": 995904, + "max_output_tokens": 32768, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 3.68e-07, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_low": 0.015, + "search_context_size_medium": 0.015, + "search_context_size_high": 0.015 }, - "supports_adaptive_thinking": true, - "supports_mid_conversation_system": true, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-5-flash", + "supports_function_calling": true + }, + "empiriolabs/qwen3-5-flash:variant1": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 995904, + "max_output_tokens": 65536, + "input_cost_per_token": 2.9e-08, + "output_cost_per_token": 2.87e-07, + "input_cost_per_token_above_128k_tokens": 1.15e-07, + "output_cost_per_token_above_128k_tokens": 1.147e-06, + "input_cost_per_token_above_256k_tokens": 1.72e-07, + "output_cost_per_token_above_256k_tokens": 1.72e-06, + "supports_system_messages": true, + "supports_vision": true, "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 + }, "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, + "source": "https://empiriolabs.ai/models/qwen3-5-flash", + "supports_function_calling": true + }, + "empiriolabs/qwen3-5-omni-flash": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 196608, + "max_output_tokens": 32768, + "input_cost_per_token": 8e-07, + "output_cost_per_token": 4.4e-06, + "supports_system_messages": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": false, - "supports_max_reasoning_effort": true, - "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh", - "supports_parallel_tool_use_config": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, - "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.015, + "search_context_size_medium": 0.015, + "search_context_size_high": 0.015 + }, + "supports_audio_input": true, + "source": "https://empiriolabs.ai/models/qwen3-5-omni-flash", + "supports_function_calling": true }, - "global.anthropic.claude-sonnet-5-5": { - "bedrock_converse_supports_strict_tools": false, - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_1hr": 4e-06, - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 2e-06, - "litellm_provider": "bedrock_converse", - "supports_tool_search": true, - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/qwen3-5-omni-plus": { + "litellm_provider": "empiriolabs", "mode": "chat", - "output_cost_per_token": 1e-05, + "max_input_tokens": 196608, + "max_output_tokens": 32768, + "input_cost_per_token": 2.8e-06, + "output_cost_per_token": 1.66e-05, + "supports_system_messages": true, + "supports_vision": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.015, + "search_context_size_medium": 0.015, + "search_context_size_high": 0.015 + }, + "supports_response_schema": true, + "supports_audio_input": true, + "source": "https://empiriolabs.ai/models/qwen3-5-omni-plus", + "supports_function_calling": true + }, + "empiriolabs/qwen3-5-plus": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 983616, + "max_output_tokens": 65536, + "input_cost_per_token": 3.6e-07, + "output_cost_per_token": 2.21e-06, + "input_cost_per_token_above_256k_tokens": 4.5e-07, + "output_cost_per_token_above_256k_tokens": 2.76e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.015, + "search_context_size_medium": 0.015, + "search_context_size_high": 0.015 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-5-plus", + "supports_function_calling": true + }, + "empiriolabs/qwen3-5-plus:variant1": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 983616, + "max_output_tokens": 65536, + "input_cost_per_token": 1.15e-07, + "output_cost_per_token": 6.88e-07, + "input_cost_per_token_above_128k_tokens": 2.87e-07, + "output_cost_per_token_above_128k_tokens": 1.72e-06, + "input_cost_per_token_above_256k_tokens": 5.73e-07, + "output_cost_per_token_above_256k_tokens": 3.44e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, "search_context_cost_per_query": { - "search_context_size_high": 0.01, "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 }, - "supports_adaptive_thinking": true, - "supports_mid_conversation_system": true, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-5-plus", + "supports_function_calling": true + }, + "empiriolabs/qwen3-6-27b": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 229376, + "max_output_tokens": 64000, + "input_cost_per_token": 4.12564e-07, + "output_cost_per_token": 2.475384e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-6-27b", + "supports_function_calling": true + }, + "empiriolabs/qwen3-6-35b-a3b": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "input_cost_per_token": 7e-08, + "output_cost_per_token": 4.2e-07, + "cache_read_input_token_cost": 3.5e-08, + "supports_system_messages": true, + "supports_reasoning": true, "supports_prompt_caching": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-6-35b-a3b", + "supports_function_calling": true + }, + "empiriolabs/qwen3-6-flash": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 983616, + "max_output_tokens": 65536, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 1.5e-06, + "input_cost_per_token_above_256k_tokens": 1e-06, + "output_cost_per_token_above_256k_tokens": 4e-06, + "supports_system_messages": true, + "supports_vision": true, "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.02, + "search_context_size_medium": 0.02, + "search_context_size_high": 0.02 + }, "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, + "source": "https://empiriolabs.ai/models/qwen3-6-flash", + "supports_function_calling": true + }, + "empiriolabs/qwen3-6-flash:variant1": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 983616, + "max_output_tokens": 65536, + "input_cost_per_token": 1.65e-07, + "output_cost_per_token": 9.9e-07, + "input_cost_per_token_above_256k_tokens": 6.6e-07, + "output_cost_per_token_above_256k_tokens": 3.961e-06, + "supports_system_messages": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": false, - "supports_max_reasoning_effort": true, - "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh", - "supports_parallel_tool_use_config": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, - "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-6-flash", + "supports_function_calling": true }, - "jp.anthropic.claude-sonnet-5-5": { - "bedrock_converse_supports_strict_tools": false, - "cache_creation_input_token_cost": 2.75e-06, - "cache_creation_input_token_cost_above_1hr": 4.4e-06, - "cache_read_input_token_cost": 2.2e-07, - "input_cost_per_token": 2.2e-06, - "litellm_provider": "bedrock_converse", - "supports_tool_search": true, - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "empiriolabs/qwen3-6-plus": { + "litellm_provider": "empiriolabs", "mode": "chat", - "output_cost_per_token": 1.1e-05, + "max_input_tokens": 983616, + "max_output_tokens": 65536, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 3e-06, + "input_cost_per_token_above_256k_tokens": 2e-06, + "output_cost_per_token_above_256k_tokens": 6e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.026, + "search_context_size_medium": 0.026, + "search_context_size_high": 0.026 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-6-plus", + "supports_function_calling": true + }, + "empiriolabs/qwen3-6-plus:variant1": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 983616, + "max_output_tokens": 65536, + "input_cost_per_token": 2.76e-07, + "output_cost_per_token": 1.651e-06, + "input_cost_per_token_above_256k_tokens": 1.101e-06, + "output_cost_per_token_above_256k_tokens": 6.602e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, "search_context_cost_per_query": { - "search_context_size_high": 0.01, "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 }, - "supports_adaptive_thinking": true, - "supports_mid_conversation_system": true, - "supports_assistant_prefill": false, - "supports_computer_use": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-6-plus", + "supports_function_calling": true + }, + "empiriolabs/qwen3-7-flash": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 983616, + "max_output_tokens": 65536, + "input_cost_per_token": 3e-08, + "output_cost_per_token": 1.3e-07, + "input_cost_per_token_above_32k_tokens": 1e-07, + "output_cost_per_token_above_32k_tokens": 4e-07, + "cache_read_input_token_cost_above_32k_tokens": 2e-08, + "input_cost_per_token_above_256k_tokens": 2e-07, + "output_cost_per_token_above_256k_tokens": 8e-07, + "cache_read_input_token_cost_above_256k_tokens": 4e-08, + "cache_read_input_token_cost": 6e-09, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.03, + "search_context_size_medium": 0.03, + "search_context_size_high": 0.03 + }, + "supports_prompt_caching": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-7-flash", + "supports_function_calling": true + }, + "empiriolabs/qwen3-7-flash:variant1": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 983616, + "max_output_tokens": 65536, + "input_cost_per_token": 2.8e-08, + "output_cost_per_token": 1.1e-07, + "input_cost_per_token_above_32k_tokens": 8.3e-08, + "output_cost_per_token_above_32k_tokens": 3.3e-07, + "cache_read_input_token_cost_above_32k_tokens": 1.7e-08, + "input_cost_per_token_above_256k_tokens": 1.65e-07, + "output_cost_per_token_above_256k_tokens": 6.6e-07, + "cache_read_input_token_cost_above_256k_tokens": 3.3e-08, + "cache_read_input_token_cost": 6e-09, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 + }, + "supports_prompt_caching": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-7-flash", + "supports_function_calling": true + }, + "empiriolabs/qwen3-7-max": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 983616, + "max_output_tokens": 65536, + "input_cost_per_token": 2.5e-06, + "output_cost_per_token": 7.5e-06, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.02, + "search_context_size_medium": 0.02, + "search_context_size_high": 0.02 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-7-max", + "supports_function_calling": true + }, + "empiriolabs/qwen3-7-max:variant1": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 983616, + "max_output_tokens": 65536, + "input_cost_per_token": 1.65e-06, + "output_cost_per_token": 4.951e-06, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-7-max", + "supports_function_calling": true + }, + "empiriolabs/qwen3-7-plus": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 983616, + "max_output_tokens": 65536, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 1.6e-06, + "input_cost_per_token_above_256k_tokens": 1.2e-06, + "output_cost_per_token_above_256k_tokens": 4.8e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.03, + "search_context_size_medium": 0.03, + "search_context_size_high": 0.03 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-7-plus", + "supports_function_calling": true + }, + "empiriolabs/qwen3-7-plus:variant1": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 983616, + "max_output_tokens": 65536, + "input_cost_per_token": 2.76e-07, + "output_cost_per_token": 1.101e-06, + "input_cost_per_token_above_256k_tokens": 8.26e-07, + "output_cost_per_token_above_256k_tokens": 3.301e-06, + "cache_read_input_token_cost_above_256k_tokens": 1.66e-07, + "cache_read_input_token_cost": 5.6e-08, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 + }, + "supports_prompt_caching": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-7-plus", + "supports_function_calling": true + }, + "empiriolabs/qwen3-8-27b": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "input_cost_per_token": 1.7e-07, + "output_cost_per_token": 5e-07, + "cache_read_input_token_cost": 8e-08, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_prompt_caching": true, "supports_function_calling": true, - "supports_pdf_input": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-8-27b" + }, + "empiriolabs/qwen3-8-flash": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 983616, + "max_output_tokens": 131072, + "input_cost_per_token": 1.6e-07, + "output_cost_per_token": 4.7e-07, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.02, + "search_context_size_medium": 0.02, + "search_context_size_high": 0.02 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-8-flash", + "supports_function_calling": true + }, + "empiriolabs/qwen3-8-max": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 983616, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.02, + "search_context_size_medium": 0.02, + "search_context_size_high": 0.02 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-8-max", + "supports_function_calling": true + }, + "empiriolabs/qwen3-8-max-0902": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 983616, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.02, + "search_context_size_medium": 0.02, + "search_context_size_high": 0.02 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-8-max-0902", + "supports_function_calling": true + }, + "empiriolabs/qwen3-8-max:variant1": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 983616, + "max_output_tokens": 131072, + "input_cost_per_token": 1.65e-06, + "output_cost_per_token": 4.951e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-8-max", + "supports_function_calling": true + }, + "empiriolabs/qwen3-8-omni-flash": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1006592, + "max_output_tokens": 131072, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 9.4e-07, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.02, + "search_context_size_medium": 0.02, + "search_context_size_high": 0.02 + }, + "supports_response_schema": true, + "supports_audio_input": true, + "source": "https://empiriolabs.ai/models/qwen3-8-omni-flash", + "supports_function_calling": true + }, + "empiriolabs/seed-2-0-code": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 229096, + "max_output_tokens": 128000, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 2.4e-06, + "input_cost_per_token_above_128k_tokens": 8e-07, + "output_cost_per_token_above_128k_tokens": 4.8e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "source": "https://empiriolabs.ai/models/seed-2-0-code", + "supports_function_calling": true + }, + "empiriolabs/seed-2-0-lite": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 229096, + "max_output_tokens": 128000, + "input_cost_per_token": 3.1e-07, + "output_cost_per_token": 2.5e-06, + "input_cost_per_token_above_128k_tokens": 6.2e-07, + "output_cost_per_token_above_128k_tokens": 5e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/seed-2-0-lite", + "supports_function_calling": true + }, + "empiriolabs/seed-2-0-mini": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 229156, + "max_output_tokens": 128000, + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 5e-07, + "input_cost_per_token_above_128k_tokens": 2.4e-07, + "output_cost_per_token_above_128k_tokens": 1e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/seed-2-0-mini", + "supports_function_calling": true + }, + "empiriolabs/seed-2-0-pro": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 229096, + "max_output_tokens": 128000, + "input_cost_per_token": 6.3e-07, + "output_cost_per_token": 3.79e-06, + "input_cost_per_token_above_128k_tokens": 1.26e-06, + "output_cost_per_token_above_128k_tokens": 7.58e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/seed-2-0-pro", + "supports_function_calling": true + }, + "empiriolabs/seed-2-1-turbo": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 229093, + "max_output_tokens": 65536, + "input_cost_per_token": 6.3e-07, + "output_cost_per_token": 3.13e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/seed-2-1-turbo", + "supports_function_calling": true + }, + "empiriolabs/skylark-embedding-vision": { + "litellm_provider": "empiriolabs", + "mode": "embedding", + "max_input_tokens": 8000, + "input_cost_per_token": 2.5e-07, + "supports_embedding_image_input": true, + "source": "https://empiriolabs.ai/models/skylark-embedding-vision" + }, + "empiriolabs/step-3-5-flash": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "cache_read_input_token_cost": 2e-08, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.013, + "search_context_size_medium": 0.013, + "search_context_size_high": 0.013 + }, "supports_prompt_caching": true, + "supports_function_calling": true, + "source": "https://empiriolabs.ai/models/step-3-5-flash" + }, + "empiriolabs/step-3-5-flash-2603": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "cache_read_input_token_cost": 2e-08, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.013, + "search_context_size_medium": 0.013, + "search_context_size_high": 0.013 + }, + "supports_prompt_caching": true, + "supports_function_calling": true, + "source": "https://empiriolabs.ai/models/step-3-5-flash-2603" + }, + "empiriolabs/step-3-7-flash": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 1.15e-06, + "cache_read_input_token_cost": 4e-08, + "supports_system_messages": true, + "supports_vision": true, "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.013, + "search_context_size_medium": 0.013, + "search_context_size_high": 0.013 + }, + "supports_prompt_caching": true, + "supports_function_calling": true, "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, + "source": "https://empiriolabs.ai/models/step-3-7-flash" + }, + "empiriolabs/step-5-preview": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1024000, + "max_output_tokens": 131072, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 2.7e-06, + "cache_read_input_token_cost": 1e-07, + "supports_system_messages": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": false, - "supports_max_reasoning_effort": true, - "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh", - "supports_parallel_tool_use_config": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, - "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "supports_reasoning": true, + "supports_prompt_caching": true, + "supports_function_calling": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/step-5-preview" + }, + "empiriolabs/stepaudio-2-5-chat": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 3.5e-06, + "cache_read_input_token_cost": 3e-07, + "supports_system_messages": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.013, + "search_context_size_medium": 0.013, + "search_context_size_high": 0.013 + }, + "supports_prompt_caching": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_audio_input": true, + "source": "https://empiriolabs.ai/models/stepaudio-2-5-chat" + }, + "empiriolabs/stepaudio-3-chat": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 3.5e-06, + "cache_read_input_token_cost": 3e-07, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_audio_input": true, + "source": "https://empiriolabs.ai/models/stepaudio-3-chat" + }, + "empiriolabs/text-embedding-v4": { + "litellm_provider": "empiriolabs", + "mode": "embedding", + "max_input_tokens": 8192, + "input_cost_per_token": 7e-08, + "source": "https://empiriolabs.ai/models/text-embedding-v4" + }, + "empiriolabs/tongyi-embedding-vision-flash": { + "litellm_provider": "empiriolabs", + "mode": "embedding", + "max_input_tokens": 1024, + "input_cost_per_token": 9e-08, + "supports_embedding_image_input": true, + "source": "https://empiriolabs.ai/models/tongyi-embedding-vision-flash" + }, + "empiriolabs/tongyi-embedding-vision-plus": { + "litellm_provider": "empiriolabs", + "mode": "embedding", + "max_input_tokens": 1024, + "input_cost_per_token": 9e-08, + "supports_embedding_image_input": true, + "source": "https://empiriolabs.ai/models/tongyi-embedding-vision-plus" + }, + "wally/glm-5.3-flash": { + "cache_read_input_token_cost": 7.6e-08, + "input_cost_per_token": 2.72e-07, + "litellm_provider": "wally", + "max_input_tokens": 1048567, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6.5e-07, + "reasoning_effort_levels": [ + "minimal", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "source": "https://www.runwally.com/pricing", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "wally/deepseek-v4.1-flash": { + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "wally", + "max_input_tokens": 1048569, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "reasoning_effort_levels": [ + "none", + "low", + "medium", + "high", + "max" + ], + "source": "https://www.runwally.com/pricing", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "wally/kimi-k3": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "wally", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "reasoning_effort_levels": [ + "none", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "source": "https://www.runwally.com/pricing", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "wally/deepseek-v4.1-flash-fast": { + "cache_read_input_token_cost": 1.4e-08, + "input_cost_per_token": 6e-07, + "litellm_provider": "wally", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "reasoning_effort_levels": [ + "none", + "low", + "medium", + "high", + "max" + ], + "source": "https://www.runwally.com/pricing", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "wally/glm-5.3-fast": { + "cache_read_input_token_cost": 3.9e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "wally", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "reasoning_effort_levels": [ + "low", + "medium", + "high", + "max" + ], + "source": "https://www.runwally.com/pricing", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "wally/deepseek-v4-pro-fast": { + "cache_read_input_token_cost": 1.6e-07, + "input_cost_per_token": 1.91e-06, + "litellm_provider": "wally", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3.83e-06, + "reasoning_effort_levels": [ + "none", + "minimal", + "low", + "medium", + "high", + "max" + ], + "source": "https://www.runwally.com/pricing", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "wally/deepseek-v4-flash-0731": { + "cache_read_input_token_cost": 1.4e-08, + "input_cost_per_token": 4.4e-07, + "litellm_provider": "wally", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.32e-06, + "reasoning_effort_levels": [ + "none", + "minimal", + "low", + "medium", + "high", + "max" + ], + "source": "https://www.runwally.com/pricing", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "wally/minimax-m3": { + "cache_read_input_token_cost": 6.6e-08, + "input_cost_per_token": 3.3e-07, + "litellm_provider": "wally", + "max_input_tokens": 524287, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.32e-06, + "reasoning_effort_levels": [ + "none", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "source": "https://www.runwally.com/pricing", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "wally/deepseek-v4.1-flash-1017": { + "cache_read_input_token_cost": 8e-09, + "input_cost_per_token": 3.75e-07, + "litellm_provider": "wally", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "reasoning_effort_levels": [ + "none", + "minimal", + "low", + "medium", + "high", + "max" + ], + "source": "https://inference.runanywhere.ai/v1/models", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "wally/deepseek-v4.1-flash-f2": { + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "wally", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "reasoning_effort_levels": [ + "none", + "minimal", + "low", + "medium", + "high", + "max" + ], + "source": "https://inference.runanywhere.ai/v1/models", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "together_ai/moonshotai/Kimi-K3.1-Pro": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://api.together.ai/v1/models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock/us-gov-east-1/anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 3.6e-06, + "input_cost_per_token_batches": 1.8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.8e-05, + "output_cost_per_token_batches": 9e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-gov-east-1/index.json", + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock/us-gov-east-1/anthropic.claude-3-7-sonnet-20250219-v1:0": { + "cache_creation_input_token_cost": 4.5e-06, + "cache_read_input_token_cost": 3.6e-07, + "input_cost_per_token": 3.6e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.8e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-gov-east-1/index.json", + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock/us-gov-west-1/anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 3.6e-06, + "input_cost_per_token_batches": 1.8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.8e-05, + "output_cost_per_token_batches": 9e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-gov-west-1/index.json", + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock/us-gov-west-1/anthropic.claude-3-7-sonnet-20250219-v1:0": { + "cache_creation_input_token_cost": 4.5e-06, + "cache_read_input_token_cost": 3.6e-07, + "input_cost_per_token": 3.6e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.8e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-gov-west-1/index.json", + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock_mantle/us-gov-east-1/nvidia.nemotron-nano-12b-v2": { + "input_cost_per_token": 2.4e-07, + "input_cost_per_token_batches": 1.2e-07, + "input_cost_per_token_flex": 1.2e-07, + "input_cost_per_token_priority": 4.2e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "output_cost_per_token_batches": 3.6e-07, + "output_cost_per_token_flex": 3.6e-07, + "output_cost_per_token_priority": 1.26e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_audio_input": false, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_vision": true + }, + "bedrock_mantle/us-gov-east-1/nvidia.nemotron-nano-3-30b": { + "input_cost_per_token": 7.2e-08, + "input_cost_per_token_batches": 3.6e-08, + "input_cost_per_token_flex": 3.6e-08, + "input_cost_per_token_priority": 1.32e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 262144, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.88e-07, + "output_cost_per_token_batches": 1.44e-07, + "output_cost_per_token_flex": 1.44e-07, + "output_cost_per_token_priority": 5.04e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_audio_input": false, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "bedrock_mantle/us-gov-east-1/nvidia.nemotron-nano-9b-v2": { + "input_cost_per_token": 7.2e-08, + "input_cost_per_token_batches": 3.6e-08, + "input_cost_per_token_flex": 3.6e-08, + "input_cost_per_token_priority": 1.32e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.76e-07, + "output_cost_per_token_batches": 1.44e-07, + "output_cost_per_token_flex": 1.44e-07, + "output_cost_per_token_priority": 4.8e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_audio_input": false, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_vision": false + }, + "bedrock_mantle/us-gov-east-1/nvidia.nemotron-super-3-120b": { + "input_cost_per_token": 1.8e-07, + "input_cost_per_token_batches": 9e-08, + "input_cost_per_token_flex": 9e-08, + "input_cost_per_token_priority": 3.15e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 256000, + "max_output_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 7.8e-07, + "output_cost_per_token_batches": 3.9e-07, + "output_cost_per_token_flex": 3.9e-07, + "output_cost_per_token_priority": 1.365e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_audio_input": false, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "bedrock_mantle/us-gov-west-1/nvidia.nemotron-nano-12b-v2": { + "input_cost_per_token": 2.4e-07, + "input_cost_per_token_batches": 1.2e-07, + "input_cost_per_token_flex": 1.2e-07, + "input_cost_per_token_priority": 4.2e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "output_cost_per_token_batches": 3.6e-07, + "output_cost_per_token_flex": 3.6e-07, + "output_cost_per_token_priority": 1.26e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_audio_input": false, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_vision": true + }, + "bedrock_mantle/us-gov-west-1/nvidia.nemotron-nano-3-30b": { + "input_cost_per_token": 7.2e-08, + "input_cost_per_token_batches": 3.6e-08, + "input_cost_per_token_flex": 3.6e-08, + "input_cost_per_token_priority": 1.32e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 262144, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.88e-07, + "output_cost_per_token_batches": 1.44e-07, + "output_cost_per_token_flex": 1.44e-07, + "output_cost_per_token_priority": 5.04e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_audio_input": false, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "bedrock_mantle/us-gov-west-1/nvidia.nemotron-nano-9b-v2": { + "input_cost_per_token": 7.2e-08, + "input_cost_per_token_batches": 3.6e-08, + "input_cost_per_token_flex": 3.6e-08, + "input_cost_per_token_priority": 1.32e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.76e-07, + "output_cost_per_token_batches": 1.44e-07, + "output_cost_per_token_flex": 1.44e-07, + "output_cost_per_token_priority": 4.8e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_audio_input": false, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_vision": false + }, + "bedrock_mantle/us-gov-west-1/nvidia.nemotron-super-3-120b": { + "input_cost_per_token": 1.8e-07, + "input_cost_per_token_batches": 9e-08, + "input_cost_per_token_flex": 9e-08, + "input_cost_per_token_priority": 3.15e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 256000, + "max_output_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 7.8e-07, + "output_cost_per_token_batches": 3.9e-07, + "output_cost_per_token_flex": 3.9e-07, + "output_cost_per_token_priority": 1.365e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_audio_input": false, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "gmi/MiniMaxAI/MiniMax-M2": { + "input_cost_per_token": 3e-07, + "litellm_provider": "gmi", + "max_input_tokens": 196608, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/MiniMaxAI/MiniMax-M2.5": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "gmi", + "max_input_tokens": 196608, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/MiniMaxAI/MiniMax-M2.7": { + "cache_read_input_token_cost": 4.2e-08, + "input_cost_per_token": 2.1e-07, + "litellm_provider": "gmi", + "max_input_tokens": 196608, + "mode": "chat", + "output_cost_per_token": 8.4e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/MiniMaxAI/MiniMax-M3": { + "cache_read_input_token_cost": 4.8e-08, + "input_cost_per_token": 2.4e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 9.6e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/MiniMaxAI/MiniMax-M3.1-Flash": { + "cache_read_input_token_cost": 1.125e-08, + "input_cost_per_token": 1.125e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 4.5e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3-235B-A22B-FP8": { + "input_cost_per_token": 1.7e-07, + "litellm_provider": "gmi", + "max_input_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.09e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3-235B-A22B-Instruct-2507-FP8": { + "cache_read_input_token_cost": 1.75e-08, + "input_cost_per_token": 8.75e-08, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3.5e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3-235B-A22B-Thinking-2507-FP8": { + "input_cost_per_token": 3.5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262141, + "mode": "chat", + "output_cost_per_token": 4.2e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3-30B-A3B": { + "input_cost_per_token": 8e-08, + "litellm_provider": "gmi", + "max_input_tokens": 40946, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3-32B-FP8": { + "input_cost_per_token": 1e-07, + "litellm_provider": "gmi", + "max_input_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { + "cache_read_input_token_cost": 1.8e-07, + "input_cost_per_token": 9e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262128, + "mode": "chat", + "output_cost_per_token": 4.5e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3-Next-80B-A3B-Instruct": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3-Next-80B-A3B-Thinking": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3.5-122B-A10B": { + "input_cost_per_token": 4e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3.2e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3.5-27B": { + "input_cost_per_token": 3e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3.5-35B-A3B": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3.5-397B-A17B": { + "input_cost_per_token": 6e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3.6e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3.6-35B-A3B": { + "input_cost_per_token": 2.48e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.485e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3.6-Plus": { + "input_cost_per_token": 5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3.6-Plus-2026-04-02": { + "input_cost_per_token": 5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3.7-Max": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3.8-27B": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 4.5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1048575, + "mode": "chat", + "output_cost_per_token": 3.2e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3.8-Flash": { + "cache_read_input_token_cost": 1.6e-08, + "input_cost_per_token": 1.6e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1048575, + "mode": "chat", + "output_cost_per_token": 4.7e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3.8-Max": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3.8-Max-0902": { + "cache_read_input_token_cost": 2.06e-07, + "input_cost_per_token": 1.65e-06, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4.951e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/XiaomiMiMo/MiMo-V2.5": { + "cache_read_input_token_cost": 2.38e-09, + "input_cost_per_token": 1.19e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1050000, + "mode": "chat", + "output_cost_per_token": 2.38e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/XiaomiMiMo/MiMo-V2.5-Pro": { + "cache_read_input_token_cost": 2.52e-09, + "input_cost_per_token": 3.045e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1050000, + "mode": "chat", + "output_cost_per_token": 6.09e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/XiaomiMiMo/MiMo-V2.6-Flash": { + "cache_read_input_token_cost": 2.24e-09, + "input_cost_per_token": 1.12e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1050000, + "mode": "chat", + "output_cost_per_token": 2.24e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/XiaomiMiMo/MiMo-V2.6-Pro": { + "cache_read_input_token_cost": 2.88e-09, + "input_cost_per_token": 3.48e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1050000, + "mode": "chat", + "output_cost_per_token": 6.96e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-Prover-V2-671B": { + "input_cost_per_token": 5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.18e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-R1": { + "input_cost_per_token": 5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.18e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-R1-0528": { + "cache_read_input_token_cost": 2.3e-07, + "input_cost_per_token": 5.7e-07, + "litellm_provider": "gmi", + "max_input_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.29e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 7.5e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-R1-Distill-Llama-8B": { + "input_cost_per_token": 1.4e-07, + "litellm_provider": "gmi", + "max_input_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3.9e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": { + "input_cost_per_token": 2e-07, + "litellm_provider": "gmi", + "max_input_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": { + "input_cost_per_token": 5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": { + "input_cost_per_token": 1e-07, + "litellm_provider": "gmi", + "max_input_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-V3.1": { + "input_cost_per_token": 2.7e-07, + "litellm_provider": "gmi", + "max_input_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 1e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-V3.1-Terminus": { + "input_cost_per_token": 2.7e-07, + "litellm_provider": "gmi", + "max_input_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-V3.2-Exp": { + "input_cost_per_token": 2.7e-07, + "litellm_provider": "gmi", + "max_input_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 4.1e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-V3.2-Speciale": { + "input_cost_per_token": 2.8e-07, + "litellm_provider": "gmi", + "max_input_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 4e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-V4-Flash": { + "cache_read_input_token_cost": 1.82e-08, + "input_cost_per_token": 9.1e-08, + "litellm_provider": "gmi", + "max_input_tokens": 1048575, + "mode": "chat", + "output_cost_per_token": 1.82e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-V4-Flash-0731": { + "cache_read_input_token_cost": 9.1e-09, + "input_cost_per_token": 2.86e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 8.58e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-V4-Pro-0813": { + "cache_read_input_token_cost": 3.52e-08, + "input_cost_per_token": 1.056e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1048575, + "mode": "chat", + "output_cost_per_token": 3.168e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-V4.1-Flash": { + "cache_read_input_token_cost": 3.6e-09, + "input_cost_per_token": 1.8e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1048575, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/deepseek-v4-flash-vision-exp": { + "cache_read_input_token_cost": 1.4e-08, + "input_cost_per_token": 4.4e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1048575, + "mode": "chat", + "output_cost_per_token": 1.32e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/deepseek-v4.1-flash-1017": { + "cache_read_input_token_cost": 3.6e-09, + "input_cost_per_token": 1.8e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1048575, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/gmicloud/Ripple-65B-Preview": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/google/gemini-3.1-flash-lite-preview": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/google/gemini-3.1-pro-preview": { + "input_cost_per_token": 2e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/google/gemini-3.5-flash": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 9e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/google/gemini-3.5-flash-lite": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/google/gemini-3.6-flash": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/google/gemini-3.7-flash": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 3.75e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/google/gemini-3.8-flash": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 3.75e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/google/gemini-4-argon": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/google/gemma-4-26b-a4b-it": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "gmi", + "max_input_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/google/gemma-4-31b-it": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 1.4e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/meta-llama/Llama-3.3-70B-Instruct": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 7.5e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 8e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/meta-llama/Llama-4-Scout-17B-16E-Instruct": { + "input_cost_per_token": 8e-08, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/moonshotai/Kimi-K2-Instruct-0905": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 5.7e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2.29e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/moonshotai/Kimi-K2.5": { + "input_cost_per_token": 6e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/moonshotai/Kimi-K2.6": { + "cache_read_input_token_cost": 1.44e-07, + "input_cost_per_token": 8.55e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3.6e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/moonshotai/kimi-k2.7-code": { + "cache_read_input_token_cost": 1.9e-07, + "input_cost_per_token": 9.5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/moonshotai/kimi-k2.7-code-highspeed": { + "cache_read_input_token_cost": 3.8e-07, + "input_cost_per_token": 1.9e-06, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 8e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/moonshotai/kimi-k3": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/moonshotai/kimi-k3.1-pro": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "gmi", + "max_input_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/nvidia/nemotron-3-ultra-550b-a55b": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 8e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2.6e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/openai/gpt-5.4": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "gmi", + "max_input_tokens": 409600, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/openai/gpt-5.4-mini": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 409600, + "mode": "chat", + "output_cost_per_token": 4.5e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/openai/gpt-5.4-nano": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "gmi", + "max_input_tokens": 409600, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/openai/gpt-5.4-pro": { + "input_cost_per_token": 3e-05, + "litellm_provider": "gmi", + "max_input_tokens": 409600, + "mode": "chat", + "output_cost_per_token": 0.00018, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/openai/gpt-5.5": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1050000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/openai/gpt-5.6-luna": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1050000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/openai/gpt-5.6-sol": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1050000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/openai/gpt-5.6-terra": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1050000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/openai/gpt-6-astra": { + "cache_read_input_token_cost": 1e-06, + "input_cost_per_token": 1e-05, + "litellm_provider": "gmi", + "max_input_tokens": 1050000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/openai/gpt-6-luna": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1050000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/openai/gpt-6-sol": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1050000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/openai/gpt-6.1-sol": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1050000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/openai/gpt-oss-120b": { + "input_cost_per_token": 5e-08, + "litellm_provider": "gmi", + "max_input_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/openai/gpt-oss-20b": { + "input_cost_per_token": 4e-08, + "litellm_provider": "gmi", + "max_input_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/stepfun-ai/Step-3.7-Flash": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "gmi", + "max_input_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.15e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/stepfun-ai/Step-5-Preview": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 2.7e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/tencent/HunyuanOCR": { + "input_cost_per_token": 5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/tencent/Hy3": { + "cache_read_input_token_cost": 3.5e-08, + "input_cost_per_token": 1.4e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 5.8e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/tencent/hy3-preview": { + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 1.8e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/tencent/hy4": { + "cache_read_input_token_cost": 2.1e-08, + "input_cost_per_token": 4.17e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.2505e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/tencent/hy4-preview": { + "cache_read_input_token_cost": 4.2e-08, + "input_cost_per_token": 8.34e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2.501e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/x-ai/grok-4.5": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "gmi", + "max_input_tokens": 2000000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/xai/grok4.6": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "gmi", + "max_input_tokens": 2000000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/zai-org/GLM-4.5-Air-FP8": { + "input_cost_per_token": 2e-07, + "litellm_provider": "gmi", + "max_input_tokens": 131076, + "mode": "chat", + "output_cost_per_token": 1.1e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/zai-org/GLM-4.5-FP8": { + "input_cost_per_token": 6e-07, + "litellm_provider": "gmi", + "max_input_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.2e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/zai-org/GLM-4.6": { + "input_cost_per_token": 6e-07, + "litellm_provider": "gmi", + "max_input_tokens": 204800, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/zai-org/GLM-4.7-Flash": { + "input_cost_per_token": 7e-08, + "litellm_provider": "gmi", + "max_input_tokens": 202752, + "mode": "chat", + "output_cost_per_token": 4e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/zai-org/GLM-5-FP8": { + "cache_read_input_token_cost": 1.2e-07, + "input_cost_per_token": 6e-07, + "litellm_provider": "gmi", + "max_input_tokens": 202752, + "mode": "chat", + "output_cost_per_token": 1.92e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/zai-org/GLM-5.1-FP8": { + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "gmi", + "max_input_tokens": 202752, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/zai-org/GLM-5.2-FP8": { + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/zai-org/GLM-5.3": { + "cache_read_input_token_cost": 1.3e-07, + "input_cost_per_token": 7e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 2.2e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/zai-org/GLM-5.3-Flash": { + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 7.5e-08, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "fireworks_ai/accounts/fireworks/models/kimi-k3p1-pro": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_priority": 3e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_priority": 3e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_priority": 1.5e-05, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "baseten/moonshotai/Kimi-K3.1-Pro": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1000000, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-image-2.6-sunburst": { + "cache_read_input_image_token_cost": 2e-06, + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_image_token": 8e-06, + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_image_token": 3e-05, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_pdf_input": true, + "supports_vision": true + }, + "gpt-image-2.6-flare": { + "cache_read_input_image_token_cost": 2e-06, + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_image_token": 8e-06, + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_image_token": 3e-05, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_pdf_input": true, + "supports_vision": true + }, + "bedrock/us-gov-east-1/moonshotai.kimi-k3": { + "cache_creation_input_token_cost": 4.95e-06, + "cache_creation_input_token_cost_flex": 2.475e-06, + "cache_creation_input_token_cost_priority": 8.6625e-06, + "cache_read_input_token_cost": 3.96e-07, + "cache_read_input_token_cost_flex": 1.98e-07, + "cache_read_input_token_cost_priority": 6.93e-07, + "input_cost_per_token": 3.96e-06, + "input_cost_per_token_batches": 1.98e-06, + "input_cost_per_token_flex": 1.98e-06, + "input_cost_per_token_priority": 6.93e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 868928, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.98e-05, + "output_cost_per_token_batches": 9.9e-06, + "output_cost_per_token_flex": 9.9e-06, + "output_cost_per_token_priority": 3.465e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_prompt_cache_breakpoint": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_regex_lookaround": false, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "token_count_framing": 64.0, + "token_count_tokenizer": "kimi_k3" + }, + "bedrock/us-gov-west-1/moonshotai.kimi-k3": { + "cache_creation_input_token_cost": 4.95e-06, + "cache_creation_input_token_cost_flex": 2.475e-06, + "cache_creation_input_token_cost_priority": 8.6625e-06, + "cache_read_input_token_cost": 3.96e-07, + "cache_read_input_token_cost_flex": 1.98e-07, + "cache_read_input_token_cost_priority": 6.93e-07, + "input_cost_per_token": 3.96e-06, + "input_cost_per_token_batches": 1.98e-06, + "input_cost_per_token_flex": 1.98e-06, + "input_cost_per_token_priority": 6.93e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 868928, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.98e-05, + "output_cost_per_token_batches": 9.9e-06, + "output_cost_per_token_flex": 9.9e-06, + "output_cost_per_token_priority": 3.465e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_prompt_cache_breakpoint": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_regex_lookaround": false, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "token_count_framing": 64.0, + "token_count_tokenizer": "kimi_k3" + }, + "bedrock/us-gov-east-1/anthropic.claude-3-haiku-20240307-v1:0": { + "deprecation_date": "2026-09-10", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-3-haiku.md", + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 195904, + "max_output_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-gov-east-1/index.json", + "successor_model": "bedrock/us-gov-east-1/anthropic.claude-haiku-4-5-20251001-v1:0", + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock_mantle/us-gov-east-1/xai.grok-4.7": { + "cache_read_input_token_cost": 6.6e-07, + "cache_read_input_token_cost_flex": 3.3e-07, + "cache_read_input_token_cost_priority": 1.155e-06, + "input_cost_per_token": 2.64e-06, + "input_cost_per_token_batches": 1.32e-06, + "input_cost_per_token_flex": 1.32e-06, + "input_cost_per_token_priority": 4.62e-06, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 524288, + "max_output_tokens": 524288, + "mode": "chat", + "output_cost_per_token": 7.92e-06, + "output_cost_per_token_batches": 3.96e-06, + "output_cost_per_token_flex": 3.96e-06, + "output_cost_per_token_priority": 1.386e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "use_openai_responses_path": true + }, + "bedrock/us-gov-west-1/anthropic.claude-3-haiku-20240307-v1:0": { + "deprecation_date": "2026-09-10", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-3-haiku.md", + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 195904, + "max_output_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-gov-west-1/index.json", + "successor_model": "bedrock/us-gov-west-1/anthropic.claude-haiku-4-5-20251001-v1:0", + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock_mantle/us-gov-west-1/xai.grok-4.7": { + "cache_read_input_token_cost": 6.6e-07, + "cache_read_input_token_cost_flex": 3.3e-07, + "cache_read_input_token_cost_priority": 1.155e-06, + "input_cost_per_token": 2.64e-06, + "input_cost_per_token_batches": 1.32e-06, + "input_cost_per_token_flex": 1.32e-06, + "input_cost_per_token_priority": 4.62e-06, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 524288, + "max_output_tokens": 524288, + "mode": "chat", + "output_cost_per_token": 7.92e-06, + "output_cost_per_token_batches": 3.96e-06, + "output_cost_per_token_flex": 3.96e-06, + "output_cost_per_token_priority": 1.386e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "use_openai_responses_path": true + }, + "bedrock_mantle/xai.grok-4.7": { + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_flex": 2.75e-07, + "cache_read_input_token_cost_priority": 9.625e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, + "input_cost_per_token_flex": 1.1e-06, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 524288, + "max_output_tokens": 524288, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "output_cost_per_token_batches": 3.3e-06, + "output_cost_per_token_flex": 3.3e-06, + "output_cost_per_token_priority": 1.155e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "use_openai_responses_path": true + }, + "bedrock_mantle/grok-latest": { + "alias_of": "bedrock_mantle/xai.grok-4.7" + }, + "together_ai/ricursive-ai/Ripple-65B-Preview": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://api.together.ai/v1/models", + "supports_prompt_caching": true + }, + "vertex_ai/gemini-omni-1.2-flash": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "vertex_ai", + "max_input_tokens": 131072, + "max_output_tokens": 260640, + "mode": "chat", + "output_cost_per_reasoning_token": 9e-06, + "output_cost_per_token": 9e-06, + "output_cost_per_video_token": 1.2e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1beta/interactions" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text", + "video" + ], + "supports_audio_input": false, + "supports_audio_output": false, + "supports_computer_use": false, + "supports_function_calling": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_system_messages": false, + "supports_tool_choice": false, + "supports_url_context": false, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": false + }, + "gemini/gemini-omni-1.2-flash": { + "input_cost_per_image_token": 1.5e-06, + "input_cost_per_token": 1.5e-06, + "input_cost_per_video_token": 1.5e-06, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 9e-06, + "output_cost_per_token": 9e-06, + "output_cost_per_video_token": 1.2e-05, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1beta/interactions" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text", + "video", + "audio" + ], + "supports_audio_input": false, + "supports_audio_output": true, + "supports_reasoning": true, + "supports_system_messages": false, + "supports_video_input": true, + "supports_vision": true + }, + "databricks/databricks-kimi-k3-1-pro": { + "cache_creation_input_token_cost": 1.99997e-06, + "cache_read_input_token_cost": 1.9999e-07, + "input_cost_per_token": 1.99997e-06, + "input_dbu_cost_per_token": 2.8571e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "metadata": {"notes":"Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference."}, + "mode": "chat", + "output_cost_per_token": 9.99999e-06, + "output_dbu_cost_per_token": 0.000142857, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "token_count_framing": 100.0 + }, + "moonshotai.kimi-k3.1": { + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_flex": 2.75e-06, + "cache_creation_input_token_cost_priority": 9.625e-06, + "cache_read_input_token_cost": 2.2e-07, + "cache_read_input_token_cost_flex": 1.1e-07, + "cache_read_input_token_cost_priority": 3.85e-07, + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_flex": 2.2e-06, + "input_cost_per_token_priority": 7.7e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 868928, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_flex": 1.1e-05, + "output_cost_per_token_priority": 3.85e-05, + "reasoning_effort_levels": [ + "none", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k3-1-highspeed.md", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_none_reasoning_effort": true, + "supports_prompt_cache_breakpoint": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_regex_lookaround": false, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "us.moonshotai.kimi-k3.1": { + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_flex": 2.75e-06, + "cache_creation_input_token_cost_priority": 9.625e-06, + "cache_read_input_token_cost": 2.2e-07, + "cache_read_input_token_cost_flex": 1.1e-07, + "cache_read_input_token_cost_priority": 3.85e-07, + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_flex": 2.2e-06, + "input_cost_per_token_priority": 7.7e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 868928, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_flex": 1.1e-05, + "output_cost_per_token_priority": 3.85e-05, + "reasoning_effort_levels": [ + "none", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k3-1-highspeed.md", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_none_reasoning_effort": true, + "supports_prompt_cache_breakpoint": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_regex_lookaround": false, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "global.moonshotai.kimi-k3.1": { + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_flex": 2.5e-06, + "cache_creation_input_token_cost_priority": 8.75e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_flex": 1e-07, + "cache_read_input_token_cost_priority": 3.5e-07, + "input_cost_per_token": 4e-06, + "input_cost_per_token_flex": 2e-06, + "input_cost_per_token_priority": 7e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 868928, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-05, + "output_cost_per_token_flex": 1e-05, + "output_cost_per_token_priority": 3.5e-05, + "reasoning_effort_levels": [ + "none", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k3-1-highspeed.md", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_none_reasoning_effort": true, + "supports_prompt_cache_breakpoint": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_regex_lookaround": false, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "in.moonshotai.kimi-k3.1": { + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_flex": 2.75e-06, + "cache_creation_input_token_cost_priority": 9.625e-06, + "cache_read_input_token_cost": 2.2e-07, + "cache_read_input_token_cost_flex": 1.1e-07, + "cache_read_input_token_cost_priority": 3.85e-07, + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_flex": 2.2e-06, + "input_cost_per_token_priority": 7.7e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 868928, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_flex": 1.1e-05, + "output_cost_per_token_priority": 3.85e-05, + "reasoning_effort_levels": [ + "none", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k3-1-highspeed.md", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_none_reasoning_effort": true, + "supports_prompt_cache_breakpoint": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_regex_lookaround": false, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "wandb/deepseek-ai/DeepSeek-V4.1-Flash-1017": { + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "wandb", + "max_input_tokens": 1049000, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference", + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true + }, + "azure_ai/cohere-rerank-v5-pro": { + "deprecation_date": "2027-02-12", + "deprecation_source": "https://management.azure.com/subscriptions/{subscriptionId}/providers/Microsoft.CognitiveServices/locations/eastus/models?api-version=2024-10-01", + "input_cost_per_token": 5e-08, + "litellm_provider": "azure_ai", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure_ai/cohere-rerank-v5-fast": { + "deprecation_date": "2027-02-12", + "deprecation_source": "https://management.azure.com/subscriptions/{subscriptionId}/providers/Microsoft.CognitiveServices/locations/eastus/models?api-version=2024-10-01", + "input_cost_per_token": 2e-08, + "litellm_provider": "azure_ai", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-realtime-2.1": { + "cache_read_input_audio_token_cost": 4.4e-07, + "cache_read_input_image_token_cost": 5.5e-07, + "cache_read_input_token_cost": 4.4e-07, + "deprecation_date": "2027-06-25", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_audio_token": 3.52e-05, + "input_cost_per_image_token": 5.5e-06, + "input_cost_per_token": 4.4e-06, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "mode": "realtime", + "output_cost_per_audio_token": 7.04e-05, + "output_cost_per_token": 2.64e-05, + "provider_specific_entry": { + "realtime_ga_only": 1 + }, + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "azure/us/gpt-realtime-2.1-mini": { + "cache_read_input_audio_token_cost": 3.3e-07, + "cache_read_input_image_token_cost": 8.8e-08, + "cache_read_input_token_cost": 6.6e-08, + "deprecation_date": "2027-06-25", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_audio_token": 1.1e-05, + "input_cost_per_image_token": 8.8e-07, + "input_cost_per_token": 6.6e-07, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "mode": "realtime", + "output_cost_per_audio_token": 2.2e-05, + "output_cost_per_token": 2.64e-06, + "provider_specific_entry": { + "realtime_ga_only": 1 + }, + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "azure/us/gpt-realtime-1.5": { + "cache_read_input_audio_token_cost": 4.4e-07, + "cache_read_input_image_token_cost": 5.5e-07, + "cache_read_input_token_cost": 4.4e-07, + "deprecation_date": "2027-08-24", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_audio_token": 3.52e-05, + "input_cost_per_image_token": 5.5e-06, + "input_cost_per_token": 4.4e-06, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "mode": "realtime", + "output_cost_per_audio_token": 7.04e-05, + "output_cost_per_token": 1.76e-05, + "provider_specific_entry": { + "realtime_ga_only": 1 + }, + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "anthropic.claude-fable-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "anthropic.claude-mythos-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "eu.anthropic.claude-fable-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.1e-05, + "cache_creation_input_token_cost_above_1hr": 1.76e-05, + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 8.8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "eu.anthropic.claude-mythos-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.1e-05, + "cache_creation_input_token_cost_above_1hr": 1.76e-05, + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 8.8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "global.anthropic.claude-fable-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "global.anthropic.claude-mythos-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "us-gov.anthropic.claude-fable-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.2e-05, + "cache_creation_input_token_cost_above_1hr": 1.92e-05, + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 9.6e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.8e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "us-gov.anthropic.claude-mythos-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.2e-05, + "cache_creation_input_token_cost_above_1hr": 1.92e-05, + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 9.6e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.8e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "us.anthropic.claude-fable-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.1e-05, + "cache_creation_input_token_cost_above_1hr": 1.76e-05, + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 8.8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "us.anthropic.claude-mythos-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.1e-05, + "cache_creation_input_token_cost_above_1hr": 1.76e-05, + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 8.8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "claude-fable-5-2": { + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_creation_input_token_cost_batches": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "input_cost_per_token": 8e-06, + "input_cost_per_token_batches": 4e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "output_cost_per_token_batches": 2e-05, + "prompt_cache_min_tokens": 512.0, + "provider_specific_entry": {"us":1.1,"fast":2}, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://platform.claude.com/docs/en/about-claude/pricing", + "supports_adaptive_thinking": true, + "supports_anthropic_compaction": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_fast_mode": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_speed": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "bedrock/claude_platform/claude-fable-5-2": { + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_creation_input_token_cost_batches": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "input_cost_per_token": 8e-06, + "input_cost_per_token_batches": 4e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "output_cost_per_token_batches": 2e-05, + "prompt_cache_min_tokens": 512.0, + "provider_specific_entry": {"us":1.1}, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing", + "supports_adaptive_thinking": true, + "supports_anthropic_compaction": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "azure_ai/claude-mythos-5-2": { + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://platform.claude.com/docs/en/about-claude/pricing", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": false, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_web_search": true, + "thinking_always_on": true + }, + "azure_ai/claude-mythos-5-2-fast": { + "cache_creation_input_token_cost": 2e-05, + "cache_creation_input_token_cost_above_1hr": 3.2e-05, + "cache_read_input_token_cost": 4e-07, + "input_cost_per_token": 1.6e-05, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 8e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://platform.claude.com/docs/en/about-claude/pricing", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": false, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_web_search": true, + "thinking_always_on": true + }, + "azure_ai/claude-fable-5-2": { + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://platform.claude.com/docs/en/about-claude/pricing", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": false, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_web_search": true, + "thinking_always_on": true + }, + "azure_ai/claude-fable-5-2-fast": { + "cache_creation_input_token_cost": 2e-05, + "cache_creation_input_token_cost_above_1hr": 3.2e-05, + "cache_read_input_token_cost": 4e-07, + "input_cost_per_token": 1.6e-05, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 8e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://platform.claude.com/docs/en/about-claude/pricing", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": false, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_web_search": true, + "thinking_always_on": true + }, + "bedrock/us-gov-east-1/anthropic.claude-mythos-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.2e-05, + "cache_creation_input_token_cost_above_1hr": 1.92e-05, + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 9.6e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.8e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "bedrock/us-gov-west-1/anthropic.claude-mythos-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.2e-05, + "cache_creation_input_token_cost_above_1hr": 1.92e-05, + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 9.6e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.8e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "github_copilot/claude-fable-5.2": { + "cache_creation_input_token_cost": 1e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/messages" + ], + "supports_adaptive_thinking": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "thinking_always_on": true + }, + "together_ai/elorian-labs/glimpse-1.0": { + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 6e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://api.together.ai/v1/models", + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true + }, + "gemini/gemini-4-carbon": { + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "cache_read_input_token_cost_flex": 5e-08, + "cache_read_input_token_cost_priority": 1.8e-07, + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.6e-06, + "litellm_provider": "gemini", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_reasoning_token": 1e-05, + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_flex": 5e-06, + "output_cost_per_token_priority": 1.8e-05, + "prompt_cache_min_tokens": 4096.0, + "rpm": 2000.0, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "source": "https://aistudio.google.com/docs/pricing#gemini-4-carbon", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_computer_use": true, + "supports_continuation": true, + "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 800000.0, + "web_search_billing_unit": "per_query" + }, + "vertex_ai/gemini-4-carbon": { + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "cache_read_input_token_cost_priority": 1.8e-07, + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token": 2e-06, + "input_cost_per_audio_token_batches": 1e-06, + "input_cost_per_audio_token_priority": 3.6e-06, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_priority": 3.6e-06, + "litellm_provider": "vertex_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_reasoning_token": 1e-05, + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_priority": 1.8e-05, + "prompt_cache_min_tokens": 4096.0, + "regional_endpoint_uplift_multiplier": 1.1, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_computer_use": true, + "supports_continuation": true, + "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "web_search_billing_unit": "per_query" + }, + "vertex_ai/gemini-4-carbon-cyber-permissive": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "cache_read_input_token_cost_priority": 3.6e-07, + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token": 4e-06, + "input_cost_per_audio_token_batches": 2e-06, + "input_cost_per_audio_token_priority": 7.2e-06, + "input_cost_per_token": 4e-06, + "input_cost_per_token_batches": 2e-06, + "input_cost_per_token_priority": 7.2e-06, + "litellm_provider": "vertex_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_reasoning_token": 2e-05, + "output_cost_per_token": 2e-05, + "output_cost_per_token_batches": 1e-05, + "output_cost_per_token_priority": 3.6e-05, + "prompt_cache_min_tokens": 4096.0, + "regional_endpoint_uplift_multiplier": 1.1, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_computer_use": false, + "supports_continuation": true, + "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "web_search_billing_unit": "per_query" + }, + "github_copilot/gemini-4-carbon": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://github.blog/changelog/2026-11-09-gemini-4-carbon-in-github-copilot", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_vision": true + }, + "fal_ai/alibaba/happy-horse/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.28, + "output_cost_per_second_1080p": 0.28, + "output_cost_per_second_720p": 0.14, + "source": "https://fal.ai/models/alibaba/happy-horse/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/alibaba/happy-horse/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.28, + "output_cost_per_second_1080p": 0.28, + "output_cost_per_second_720p": 0.14, + "source": "https://fal.ai/models/alibaba/happy-horse/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/alibaba/happy-horse/v1.1/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.18, + "output_cost_per_second_1080p": 0.18, + "output_cost_per_second_720p": 0.14, + "source": "https://fal.ai/models/alibaba/happy-horse/v1.1/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/alibaba/happy-horse/v1.1/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.18, + "output_cost_per_second_1080p": 0.18, + "output_cost_per_second_720p": 0.14, + "source": "https://fal.ai/models/alibaba/happy-horse/v1.1/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/alibaba/happy-horse/v1.1/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.18, + "output_cost_per_second_1080p": 0.18, + "output_cost_per_second_720p": 0.14, + "source": "https://fal.ai/models/alibaba/happy-horse/v1.1/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/alibaba/wan-3.0-prime/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.28, + "output_cost_per_second_1080p": 0.28, + "output_cost_per_second_480p": 0.068, + "output_cost_per_second_720p": 0.14, + "source": "https://fal.ai/models/alibaba/wan-3.0-prime/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/alibaba/wan-3.0-prime/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.28, + "output_cost_per_second_1080p": 0.28, + "output_cost_per_second_480p": 0.068, + "output_cost_per_second_720p": 0.14, + "source": "https://fal.ai/models/alibaba/wan-3.0-prime/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/alibaba/wan-3.0-prime/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.28, + "output_cost_per_second_1080p": 0.28, + "output_cost_per_second_480p": 0.068, + "output_cost_per_second_720p": 0.14, + "source": "https://fal.ai/models/alibaba/wan-3.0-prime/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/alibaba/wan-3.0/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.2, + "output_cost_per_second_1080p": 0.2, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/alibaba/wan-3.0/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/alibaba/wan-3.0/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.2, + "output_cost_per_second_1080p": 0.2, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/alibaba/wan-3.0/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/alibaba/wan-3.0/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.2, + "output_cost_per_second_1080p": 0.2, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/alibaba/wan-3.0/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/blackforestlabs/flux-3/draft-enhance": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.29, + "output_cost_per_second_1080p": 0.29, + "source": "https://fal.ai/models/blackforestlabs/flux-3/draft-enhance", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/blackforestlabs/flux-3/edit-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.03, + "output_cost_per_second_720p": 0.03, + "source": "https://fal.ai/models/blackforestlabs/flux-3/edit-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/blackforestlabs/flux-3/extend-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.41, + "output_cost_per_second_1080p": 0.53, + "output_cost_per_second_720p": 0.41, + "source": "https://fal.ai/models/blackforestlabs/flux-3/extend-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/blackforestlabs/flux-3/extend-video/draft": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.12, + "output_cost_per_second_720p": 0.12, + "source": "https://fal.ai/models/blackforestlabs/flux-3/extend-video/draft", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/blackforestlabs/flux-3/first-last-frame-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.17, + "output_cost_per_second_1080p": 0.29, + "output_cost_per_second_720p": 0.17, + "source": "https://fal.ai/models/blackforestlabs/flux-3/first-last-frame-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/blackforestlabs/flux-3/first-last-frame-to-video/draft": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.06, + "output_cost_per_second_720p": 0.06, + "source": "https://fal.ai/models/blackforestlabs/flux-3/first-last-frame-to-video/draft", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/blackforestlabs/flux-3/image-to-video/draft": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.06, + "output_cost_per_second_720p": 0.06, + "source": "https://fal.ai/models/blackforestlabs/flux-3/image-to-video/draft", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/blackforestlabs/flux-3/keyframes-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.17, + "output_cost_per_second_1080p": 0.29, + "output_cost_per_second_720p": 0.17, + "source": "https://fal.ai/models/blackforestlabs/flux-3/keyframes-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/blackforestlabs/flux-3/keyframes-to-video/draft": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.06, + "output_cost_per_second_720p": 0.06, + "source": "https://fal.ai/models/blackforestlabs/flux-3/keyframes-to-video/draft", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/blackforestlabs/flux-3/klein/base/edit-image/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills blackforestlabs/flux-3/klein/base/edit-image/lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/blackforestlabs/flux-3/klein/base/edit-image/lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/blackforestlabs/flux-3/klein/base/text-to-image/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills blackforestlabs/flux-3/klein/base/text-to-image/lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/blackforestlabs/flux-3/klein/base/text-to-image/lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/blackforestlabs/flux-3/klein/edit-image/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills blackforestlabs/flux-3/klein/edit-image/lora at $0.012 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.012, + "output_cost_per_pixel": 1.1444091796875e-08, + "source": "https://fal.ai/models/blackforestlabs/flux-3/klein/edit-image/lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/blackforestlabs/flux-3/klein/text-to-image/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills blackforestlabs/flux-3/klein/text-to-image/lora at $0.012 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.012, + "output_cost_per_pixel": 1.1444091796875e-08, + "source": "https://fal.ai/models/blackforestlabs/flux-3/klein/text-to-image/lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/blackforestlabs/flux-3/text-to-video/draft": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.06, + "output_cost_per_second_720p": 0.06, + "source": "https://fal.ai/models/blackforestlabs/flux-3/text-to-video/draft", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bria/bria_video_eraser/erase/keypoints": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.14, + "source": "https://fal.ai/models/bria/bria_video_eraser/erase/keypoints", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bria/bria_video_eraser/erase/mask": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.14, + "source": "https://fal.ai/models/bria/bria_video_eraser/erase/mask", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bria/bria_video_eraser/erase/prompt": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.14, + "source": "https://fal.ai/models/bria/bria_video_eraser/erase/prompt", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bria/embed-product": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/embed-product", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/extract-object": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://fal.ai/models/bria/extract-object", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-2/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-2/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-bbq-preview/generate": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-bbq-preview/generate", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/bria/fibo-edit-1.5/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit-1.5/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-edit-1.5/expand": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit-1.5/expand", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-edit-1.5/product-holding": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit-1.5/product-holding", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-edit-1.5/virtual-try-on": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit-1.5/virtual-try-on", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-edit/add_object_by_text": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit/add_object_by_text", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-edit/blend": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit/blend", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-edit/colorize": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit/colorize", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-edit/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-edit/erase_by_text": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit/erase_by_text", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-edit/relight": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit/relight", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-edit/replace_object_by_text": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit/replace_object_by_text", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-edit/reseason": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit/reseason", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-edit/restore": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit/restore", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-edit/restyle": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit/restyle", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-edit/rewrite_text": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit/rewrite_text", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-edit/sketch_to_colored_image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit/sketch_to_colored_image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-gen-1.5/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-gen-1.5/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/bria/fibo-lite/generate": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.036, + "source": "https://fal.ai/models/bria/fibo-lite/generate", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/bria/fibo/generate": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo/generate", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/bria/genfill/v2": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills bria/genfill/v2 at $0.04 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.04, + "output_cost_per_pixel": 3.814697265625e-08, + "source": "https://fal.ai/models/bria/genfill/v2", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/guided-remove-background": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://fal.ai/models/bria/guided-remove-background", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/increase-resolution": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/increase-resolution", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/product-dimensions": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/product-dimensions", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/replace-background": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/replace-background", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/upscale/creative": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/upscale/creative", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/video/background-removal": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.14, + "source": "https://fal.ai/models/bria/video/background-removal", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bria/video/background-removal/green-screen-despill": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://fal.ai/models/bria/video/background-removal/green-screen-despill", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bria/video/background-removal/realtime": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.0042, + "source": "https://fal.ai/models/bria/video/background-removal/realtime", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bria/video/background-removal/v3": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://fal.ai/models/bria/video/background-removal/v3", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bria/video/erase/keypoints": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.14, + "source": "https://fal.ai/models/bria/video/erase/keypoints", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bria/video/erase/mask": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.14, + "source": "https://fal.ai/models/bria/video/erase/mask", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bria/video/erase/prompt": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.14, + "source": "https://fal.ai/models/bria/video/erase/prompt", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bria/video/increase-resolution": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.14, + "source": "https://fal.ai/models/bria/video/increase-resolution", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/omnihuman/v2": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.105, + "source": "https://fal.ai/models/bytedance/omnihuman/v2", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/seedance-2.0/fast/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.2419, + "output_cost_per_second_720p": 0.2419, + "source": "https://fal.ai/models/bytedance/seedance-2.0/fast/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/seedance-2.0/fast/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.2419, + "output_cost_per_second_720p": 0.2419, + "source": "https://fal.ai/models/bytedance/seedance-2.0/fast/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/seedance-2.0/mini/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.1547, + "output_cost_per_second_480p": 0.0721, + "output_cost_per_second_720p": 0.1547, + "source": "https://fal.ai/models/bytedance/seedance-2.0/mini/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/seedance-2.0/mini/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 480p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.007, + "output_cost_per_second_480p": 0.007, + "source": "https://fal.ai/models/bytedance/seedance-2.0/mini/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/seedance-2.0/mini/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.1547, + "output_cost_per_second_480p": 0.0721, + "output_cost_per_second_720p": 0.1547, + "source": "https://fal.ai/models/bytedance/seedance-2.0/mini/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/seedance-2.0/us/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.3034, + "output_cost_per_second_1080p": 0.682, + "output_cost_per_second_720p": 0.3034, + "source": "https://fal.ai/models/bytedance/seedance-2.0/us/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/seedance-2.0/us/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.37, + "output_cost_per_second_480p": 0.1731, + "output_cost_per_second_720p": 0.37, + "source": "https://fal.ai/models/bytedance/seedance-2.0/us/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/seedance-2.5/us/draft/complete": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 1.164, + "source": "https://fal.ai/models/bytedance/seedance-2.5/us/draft/complete", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/seedance-2.5/us/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.473, + "output_cost_per_second_1080p": 1.164, + "output_cost_per_second_480p": 0.2205, + "output_cost_per_second_720p": 0.473, + "source": "https://fal.ai/models/bytedance/seedance-2.5/us/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/seedance-2.5/us/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.473, + "output_cost_per_second_1080p": 1.164, + "output_cost_per_second_480p": 0.2205, + "output_cost_per_second_720p": 0.473, + "source": "https://fal.ai/models/bytedance/seedance-2.5/us/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/seedream/v5/flash/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.027, + "source": "https://fal.ai/models/bytedance/seedream/v5/flash/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bytedance/seedream/v5/flash/layerize": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.027, + "source": "https://fal.ai/models/bytedance/seedream/v5/flash/layerize", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bytedance/seedream/v5/flash/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.027, + "source": "https://fal.ai/models/bytedance/seedream/v5/flash/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/bytedance/seedream/v5/lite/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.035, + "source": "https://fal.ai/models/bytedance/seedream/v5/lite/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bytedance/seedream/v5/lite/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.035, + "source": "https://fal.ai/models/bytedance/seedream/v5/lite/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/clarityai/crystal-upscaler": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills clarityai/crystal-upscaler at $0.016 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.016, + "output_cost_per_pixel": 1.52587890625e-08, + "source": "https://fal.ai/models/clarityai/crystal-upscaler", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/decart/lucy-2-5/realtime": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.02, + "source": "https://fal.ai/models/decart/lucy-2-5/realtime", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/decart/lucy-2-6/realtime": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.02, + "source": "https://fal.ai/models/decart/lucy-2-6/realtime", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/decart/lucy-restyle": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.01, + "source": "https://fal.ai/models/decart/lucy-restyle", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/decart/lucy2-vton/realtime": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.02, + "source": "https://fal.ai/models/decart/lucy2-vton/realtime", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ai-avatar/multi": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.2, + "source": "https://fal.ai/models/fal-ai/ai-avatar/multi", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ai-avatar/multi-text": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.2, + "source": "https://fal.ai/models/fal-ai/ai-avatar/multi-text", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ai-avatar/single-text": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.2, + "source": "https://fal.ai/models/fal-ai/ai-avatar/single-text", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/bagel": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.1, + "source": "https://fal.ai/models/fal-ai/bagel", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/bagel/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.1, + "source": "https://fal.ai/models/fal-ai/bagel/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ben/v2/image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/ben/v2/image at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/ben/v2/image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/boogu-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/boogu-image at $0.04 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.04, + "output_cost_per_pixel": 3.814697265625e-08, + "source": "https://fal.ai/models/fal-ai/boogu-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/boogu-image/edit": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/boogu-image/edit at $0.04 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.04, + "output_cost_per_pixel": 3.814697265625e-08, + "source": "https://fal.ai/models/fal-ai/boogu-image/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/bria/background/replace": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/bria/background/replace", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/bria/eraser": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/bria/eraser", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/bria/expand": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/bria/expand", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/bria/genfill": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/bria/genfill", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/bria/product-shot": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/bria/product-shot", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/bria/reimagine": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/bria/reimagine", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/bria/text-to-image/base": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/bria/text-to-image/base", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/bria/text-to-image/fast": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.028, + "source": "https://fal.ai/models/fal-ai/bria/text-to-image/fast", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/bria/text-to-image/hd": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/bria/text-to-image/hd", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/bytedance/dreamactor/v2": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://fal.ai/models/fal-ai/bytedance/dreamactor/v2", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/bytedance/omnihuman": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.14, + "source": "https://fal.ai/models/fal-ai/bytedance/omnihuman", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/bytedance/omnihuman/v1.5": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.16, + "source": "https://fal.ai/models/fal-ai/bytedance/omnihuman/v1.5", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/bytedance/seedream/v4.5/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/bytedance/seedream/v4.5/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/bytedance/seedream/v4.5/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/bytedance/seedream/v4.5/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/bytedance/seedream/v4/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://fal.ai/models/fal-ai/bytedance/seedream/v4/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/bytedance/seedream/v4/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://fal.ai/models/fal-ai/bytedance/seedream/v4/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/clarity-upscaler": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/clarity-upscaler at $0.03 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.03, + "output_cost_per_pixel": 2.86102294921875e-08, + "source": "https://fal.ai/models/fal-ai/clarity-upscaler", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/codeformer": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/codeformer at $0.0021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.0021, + "output_cost_per_pixel": 2.002716064453125e-09, + "source": "https://fal.ai/models/fal-ai/codeformer", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/control-light": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/control-light at $0.03 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.03, + "output_cost_per_pixel": 2.86102294921875e-08, + "source": "https://fal.ai/models/fal-ai/control-light", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/davinci-magihuman": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://fal.ai/models/fal-ai/davinci-magihuman", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ddcolor": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/ddcolor at $0.001 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.001, + "output_cost_per_pixel": 9.5367431640625e-10, + "source": "https://fal.ai/models/fal-ai/ddcolor", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/depth-anything-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.04, + "source": "https://fal.ai/models/fal-ai/depth-anything-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/echomimic-v3": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.2, + "source": "https://fal.ai/models/fal-ai/echomimic-v3", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ernie-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/ernie-image at $0.03 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.03, + "output_cost_per_pixel": 2.86102294921875e-08, + "source": "https://fal.ai/models/fal-ai/ernie-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/ernie-image/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/ernie-image/lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/ernie-image/lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/ernie-image/lora/turbo": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/ernie-image/lora/turbo at $0.015 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.015, + "output_cost_per_pixel": 1.430511474609375e-08, + "source": "https://fal.ai/models/fal-ai/ernie-image/lora/turbo", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/ernie-image/turbo": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/ernie-image/turbo at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "output_cost_per_pixel": 9.5367431640625e-09, + "source": "https://fal.ai/models/fal-ai/ernie-image/turbo", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/fashn/tryon/v1.5": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.075, + "source": "https://fal.ai/models/fal-ai/fashn/tryon/v1.5", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/fashn/tryon/v1.6": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.075, + "source": "https://fal.ai/models/fal-ai/fashn/tryon/v1.6", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/feynobg": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.001, + "source": "https://fal.ai/models/fal-ai/feynobg", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ffmpeg-api/compose": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.0002, + "source": "https://fal.ai/models/fal-ai/ffmpeg-api/compose", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ffmpeg-api/merge-audio-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.0002, + "source": "https://fal.ai/models/fal-ai/ffmpeg-api/merge-audio-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/finegrain-eraser": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.27, + "source": "https://fal.ai/models/fal-ai/finegrain-eraser", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/finegrain-eraser/bbox": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.18, + "source": "https://fal.ai/models/fal-ai/finegrain-eraser/bbox", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/finegrain-eraser/mask": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.13, + "source": "https://fal.ai/models/fal-ai/finegrain-eraser/mask", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/firered-image-edit-v1.1": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/firered-image-edit-v1.1 at $0.0325 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.0325, + "output_cost_per_pixel": 3.0994415283203126e-08, + "source": "https://fal.ai/models/fal-ai/firered-image-edit-v1.1", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flashhead": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.005, + "source": "https://fal.ai/models/fal-ai/flashhead", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/flux-1/dev": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-1/dev at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux-1/dev", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-1/dev/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-1/dev/image-to-image at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux-1/dev/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-1/dev/redux": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-1/dev/redux at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux-1/dev/redux", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-1/krea": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-1/krea at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux-1/krea", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-1/krea/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-1/krea/image-to-image at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux-1/krea/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-1/krea/redux": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-1/krea/redux at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux-1/krea/redux", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-1/schnell": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-1/schnell at $0.003 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.003, + "output_cost_per_pixel": 2.86102294921875e-09, + "source": "https://fal.ai/models/fal-ai/flux-1/schnell", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-1/schnell/redux": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-1/schnell/redux at $0.003 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.003, + "output_cost_per_pixel": 2.86102294921875e-09, + "source": "https://fal.ai/models/fal-ai/flux-1/schnell/redux", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-1/srpo": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-1/srpo at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux-1/srpo", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-1/srpo/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-1/srpo/image-to-image at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux-1/srpo/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2 at $0.012 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.012, + "output_cost_per_pixel": 1.1444091796875e-08, + "source": "https://fal.ai/models/fal-ai/flux-2", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2-flex": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2-flex at $0.05 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, + "mode": "image_generation", + "output_cost_per_image": 0.05, + "output_cost_per_pixel": 4.76837158203125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2-flex", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2-flex/edit": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2-flex/edit at $0.05 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, + "mode": "image_generation", + "output_cost_per_image": 0.05, + "output_cost_per_pixel": 4.76837158203125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2-flex/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2-lora-gallery/add-background": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/add-background at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, + "mode": "image_generation", + "output_cost_per_image": 0.021, + "output_cost_per_pixel": 2.002716064453125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/add-background", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2-lora-gallery/apartment-staging": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/apartment-staging at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, + "mode": "image_generation", + "output_cost_per_image": 0.021, + "output_cost_per_pixel": 2.002716064453125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/apartment-staging", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2-lora-gallery/ballpoint-pen-sketch": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/ballpoint-pen-sketch at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.021, + "output_cost_per_pixel": 2.002716064453125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/ballpoint-pen-sketch", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2-lora-gallery/digital-comic-art": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/digital-comic-art at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.021, + "output_cost_per_pixel": 2.002716064453125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/digital-comic-art", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2-lora-gallery/face-to-full-portrait": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/face-to-full-portrait at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, + "mode": "image_generation", + "output_cost_per_image": 0.021, + "output_cost_per_pixel": 2.002716064453125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/face-to-full-portrait", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2-lora-gallery/hdr-style": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/hdr-style at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.021, + "output_cost_per_pixel": 2.002716064453125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/hdr-style", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2-lora-gallery/multiple-angles": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/multiple-angles at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, + "mode": "image_generation", + "output_cost_per_image": 0.021, + "output_cost_per_pixel": 2.002716064453125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/multiple-angles", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2-lora-gallery/realism": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/realism at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.021, + "output_cost_per_pixel": 2.002716064453125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/realism", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2-lora-gallery/satellite-view-style": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/satellite-view-style at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.021, + "output_cost_per_pixel": 2.002716064453125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/satellite-view-style", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2-lora-gallery/sepia-vintage": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/sepia-vintage at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.021, + "output_cost_per_pixel": 2.002716064453125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/sepia-vintage", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2-lora-gallery/virtual-tryon": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/virtual-tryon at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, + "mode": "image_generation", + "output_cost_per_image": 0.021, + "output_cost_per_pixel": 2.002716064453125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/virtual-tryon", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2/edit": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/edit at $0.012 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, + "mode": "image_generation", + "output_cost_per_image": 0.012, + "output_cost_per_pixel": 1.1444091796875e-08, + "source": "https://fal.ai/models/fal-ai/flux-2/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2/flash": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/flash at $0.005 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.005, + "output_cost_per_pixel": 4.76837158203125e-09, + "source": "https://fal.ai/models/fal-ai/flux-2/flash", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2/flash/edit": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/flash/edit at $0.005 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, + "mode": "image_generation", + "output_cost_per_image": 0.005, + "output_cost_per_pixel": 4.76837158203125e-09, + "source": "https://fal.ai/models/fal-ai/flux-2/flash/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2/klein/4b": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/4b at $0.005 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.005, + "output_cost_per_pixel": 4.76837158203125e-09, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/4b", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2/klein/4b/base": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/4b/base at $0.009 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.009, + "output_cost_per_pixel": 8.58306884765625e-09, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/4b/base", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2/klein/4b/base/edit": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/4b/base/edit at $0.009 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.009, + "output_cost_per_pixel": 8.58306884765625e-09, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/4b/base/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2/klein/4b/base/edit/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/4b/base/edit/lora at $0.016 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.016, + "output_cost_per_pixel": 1.52587890625e-08, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/4b/base/edit/lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2/klein/4b/base/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/4b/base/lora at $0.016 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.016, + "output_cost_per_pixel": 1.52587890625e-08, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/4b/base/lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2/klein/4b/edit": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/4b/edit at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "output_cost_per_pixel": 9.5367431640625e-09, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/4b/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2/klein/4b/edit/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/4b/edit/lora at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "output_cost_per_pixel": 9.5367431640625e-09, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/4b/edit/lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2/klein/4b/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/4b/lora at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "output_cost_per_pixel": 9.5367431640625e-09, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/4b/lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2/klein/9b": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/9b at $0.006 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.006, + "output_cost_per_pixel": 5.7220458984375e-09, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/9b", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2/klein/9b/base": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/9b/base at $0.011 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.011, + "output_cost_per_pixel": 1.049041748046875e-08, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/9b/base", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2/klein/9b/base/edit": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/9b/base/edit at $0.011 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.011, + "output_cost_per_pixel": 1.049041748046875e-08, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/9b/base/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2/klein/9b/base/edit/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/9b/base/edit/lora at $0.02 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.02, + "output_cost_per_pixel": 1.9073486328125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/9b/base/edit/lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2/klein/9b/base/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/9b/base/lora at $0.02 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.02, + "output_cost_per_pixel": 1.9073486328125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/9b/base/lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2/klein/9b/edit": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/9b/edit at $0.011 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.011, + "output_cost_per_pixel": 1.049041748046875e-08, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/9b/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2/klein/9b/edit/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/9b/edit/lora at $0.015 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.015, + "output_cost_per_pixel": 1.430511474609375e-08, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/9b/edit/lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2/klein/9b/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/9b/lora at $0.015 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.015, + "output_cost_per_pixel": 1.430511474609375e-08, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/9b/lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/lora at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.021, + "output_cost_per_pixel": 2.002716064453125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2/lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2/lora/edit": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/lora/edit at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, + "mode": "image_generation", + "output_cost_per_image": 0.021, + "output_cost_per_pixel": 2.002716064453125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2/lora/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2/turbo": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/turbo at $0.008 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.008, + "output_cost_per_pixel": 7.62939453125e-09, + "source": "https://fal.ai/models/fal-ai/flux-2/turbo", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2/turbo/edit": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/turbo/edit at $0.008 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, + "mode": "image_generation", + "output_cost_per_image": 0.008, + "output_cost_per_pixel": 7.62939453125e-09, + "source": "https://fal.ai/models/fal-ai/flux-2/turbo/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-general": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-general at $0.075 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.075, + "output_cost_per_pixel": 7.152557373046875e-08, + "source": "https://fal.ai/models/fal-ai/flux-general", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-general/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-general/image-to-image at $0.075 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.075, + "output_cost_per_pixel": 7.152557373046875e-08, + "source": "https://fal.ai/models/fal-ai/flux-general/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-general/inpainting": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-general/inpainting at $0.075 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.075, + "output_cost_per_pixel": 7.152557373046875e-08, + "source": "https://fal.ai/models/fal-ai/flux-general/inpainting", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-kontext-lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-kontext-lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/flux-kontext-lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-kontext-lora/inpaint": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-kontext-lora/inpaint at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/flux-kontext-lora/inpaint", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-kontext-lora/text-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-kontext-lora/text-to-image at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/flux-kontext-lora/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-kontext/dev": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-kontext/dev at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux-kontext/dev", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-krea-lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-krea-lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/flux-krea-lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-krea-lora/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-krea-lora/image-to-image at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/flux-krea-lora/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-krea-lora/inpainting": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-krea-lora/inpainting at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/flux-krea-lora/inpainting", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-krea-lora/stream": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-krea-lora/stream at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/flux-krea-lora/stream", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/flux-lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-lora-canny": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-lora-canny at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/flux-lora-canny", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-lora-fill": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-lora-fill at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/flux-lora-fill", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-lora/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-lora/image-to-image at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/flux-lora/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-lora/inpainting": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-lora/inpainting at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/flux-lora/inpainting", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-lora/stream": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-lora/stream at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/flux-lora/stream", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-pro/kontext": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/flux-pro/kontext", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-pro/kontext/max": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://fal.ai/models/fal-ai/flux-pro/kontext/max", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-pro/kontext/max/multi": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://fal.ai/models/fal-ai/flux-pro/kontext/max/multi", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-pro/kontext/max/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://fal.ai/models/fal-ai/flux-pro/kontext/max/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-pro/kontext/multi": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/flux-pro/kontext/multi", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-pro/kontext/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/flux-pro/kontext/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-pro/v1.1-ultra-finetuned": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.07, + "source": "https://fal.ai/models/fal-ai/flux-pro/v1.1-ultra-finetuned", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-pro/v1.1-ultra/redux": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-pro/v1.1-ultra/redux at $0.05 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.05, + "output_cost_per_pixel": 4.76837158203125e-08, + "source": "https://fal.ai/models/fal-ai/flux-pro/v1.1-ultra/redux", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-pro/v1.1/redux": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-pro/v1.1/redux at $0.05 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.05, + "output_cost_per_pixel": 4.76837158203125e-08, + "source": "https://fal.ai/models/fal-ai/flux-pro/v1.1/redux", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-pro/v1/fill": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-pro/v1/fill at $0.05 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.05, + "output_cost_per_pixel": 4.76837158203125e-08, + "source": "https://fal.ai/models/fal-ai/flux-pro/v1/fill", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-pro/v1/fill-finetuned": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-pro/v1/fill-finetuned at $0.06 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.06, + "output_cost_per_pixel": 5.7220458984375e-08, + "source": "https://fal.ai/models/fal-ai/flux-pro/v1/fill-finetuned", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-pulid": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-pulid at $0.0333 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.0333, + "output_cost_per_pixel": 3.175735473632813e-08, + "source": "https://fal.ai/models/fal-ai/flux-pulid", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-vision-upscaler": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-vision-upscaler at $0.1 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.1, + "output_cost_per_pixel": 9.5367431640625e-08, + "source": "https://fal.ai/models/fal-ai/flux-vision-upscaler", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux/dev/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux/dev/image-to-image at $0.03 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.03, + "output_cost_per_pixel": 2.86102294921875e-08, + "source": "https://fal.ai/models/fal-ai/flux/dev/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux/dev/redux": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux/dev/redux at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux/dev/redux", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux/krea": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux/krea at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux/krea", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux/krea/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux/krea/image-to-image at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux/krea/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux/krea/redux": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux/krea/redux at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux/krea/redux", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux/schnell/redux": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux/schnell/redux at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux/schnell/redux", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux/srpo": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux/srpo at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux/srpo", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux/srpo/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux/srpo/image-to-image at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux/srpo/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/framepack": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.0333, + "source": "https://fal.ai/models/fal-ai/framepack", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/framepack/f1": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.0333, + "source": "https://fal.ai/models/fal-ai/framepack/f1", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/framepack/flf2v": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.0333, + "source": "https://fal.ai/models/fal-ai/framepack/flf2v", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/gemini-25-flash-image/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.0398, + "source": "https://fal.ai/models/fal-ai/gemini-25-flash-image/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/gemini-3-pro-image-preview": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.15, + "source": "https://fal.ai/models/fal-ai/gemini-3-pro-image-preview", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/gemini-3-pro-image-preview/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.15, + "source": "https://fal.ai/models/fal-ai/gemini-3-pro-image-preview/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/gemini-3.1-flash-image-preview": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://fal.ai/models/fal-ai/gemini-3.1-flash-image-preview", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/gemini-3.1-flash-image-preview/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://fal.ai/models/fal-ai/gemini-3.1-flash-image-preview/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/glm-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/glm-image at $0.05 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.05, + "output_cost_per_pixel": 4.76837158203125e-08, + "source": "https://fal.ai/models/fal-ai/glm-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/glm-image/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/glm-image/image-to-image at $0.05 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.05, + "output_cost_per_pixel": 4.76837158203125e-08, + "source": "https://fal.ai/models/fal-ai/glm-image/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/heygen/avatar3/digital-twin": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.034, + "source": "https://fal.ai/models/fal-ai/heygen/avatar3/digital-twin", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/heygen/avatar4/digital-twin": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://fal.ai/models/fal-ai/heygen/avatar4/digital-twin", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/heygen/avatar4/image-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://fal.ai/models/fal-ai/heygen/avatar4/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/heygen/avatar5/digital-twin": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://fal.ai/models/fal-ai/heygen/avatar5/digital-twin", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/heygen/v2/translate/precision": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://fal.ai/models/fal-ai/heygen/v2/translate/precision", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/heygen/v2/translate/speed": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://fal.ai/models/fal-ai/heygen/v2/translate/speed", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/heygen/v2/video-agent": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.034, + "source": "https://fal.ai/models/fal-ai/heygen/v2/video-agent", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/heygen/v3/filler-word-removal": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.01, + "source": "https://fal.ai/models/fal-ai/heygen/v3/filler-word-removal", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/heygen/v3/lipsync/precision": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://fal.ai/models/fal-ai/heygen/v3/lipsync/precision", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/heygen/v3/lipsync/speed": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://fal.ai/models/fal-ai/heygen/v3/lipsync/speed", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/heygen/v3/video-agent": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.034, + "source": "https://fal.ai/models/fal-ai/heygen/v3/video-agent", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/hidream-i1-fast": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/hidream-i1-fast at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "output_cost_per_pixel": 9.5367431640625e-09, + "source": "https://fal.ai/models/fal-ai/hidream-i1-fast", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/hidream-i1-full": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/hidream-i1-full at $0.05 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.05, + "output_cost_per_pixel": 4.76837158203125e-08, + "source": "https://fal.ai/models/fal-ai/hidream-i1-full", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/hidream-i1-full/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/hidream-i1-full/image-to-image at $0.05 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.05, + "output_cost_per_pixel": 4.76837158203125e-08, + "source": "https://fal.ai/models/fal-ai/hidream-i1-full/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/hidream-o1-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/hidream-o1-image at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "output_cost_per_pixel": 9.5367431640625e-09, + "source": "https://fal.ai/models/fal-ai/hidream-o1-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/hidream-o1-image/dev": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/hidream-o1-image/dev at $0.005 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.005, + "output_cost_per_pixel": 4.76837158203125e-09, + "source": "https://fal.ai/models/fal-ai/hidream-o1-image/dev", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/hidream-o1-image/dev/edit": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/hidream-o1-image/dev/edit at $0.005 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.005, + "output_cost_per_pixel": 4.76837158203125e-09, + "source": "https://fal.ai/models/fal-ai/hidream-o1-image/dev/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/hidream-o1-image/edit": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/hidream-o1-image/edit at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "output_cost_per_pixel": 9.5367431640625e-09, + "source": "https://fal.ai/models/fal-ai/hidream-o1-image/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/hunyuan_world": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.15, + "source": "https://fal.ai/models/fal-ai/hunyuan_world", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/hunyuan-image/v2.1/text-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/hunyuan-image/v2.1/text-to-image at $0.1 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.1, + "output_cost_per_pixel": 9.5367431640625e-08, + "source": "https://fal.ai/models/fal-ai/hunyuan-image/v2.1/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/hunyuan-image/v3/instruct/edit": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/hunyuan-image/v3/instruct/edit at $0.09 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.09, + "output_cost_per_pixel": 8.58306884765625e-08, + "source": "https://fal.ai/models/fal-ai/hunyuan-image/v3/instruct/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/hunyuan-image/v3/instruct/text-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/hunyuan-image/v3/instruct/text-to-image at $0.09 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.09, + "output_cost_per_pixel": 8.58306884765625e-08, + "source": "https://fal.ai/models/fal-ai/hunyuan-image/v3/instruct/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/hunyuan-image/v3/text-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/hunyuan-image/v3/text-to-image at $0.1 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.1, + "output_cost_per_pixel": 9.5367431640625e-08, + "source": "https://fal.ai/models/fal-ai/hunyuan-image/v3/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/hunyuan-video-v1.5/image-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.075, + "source": "https://fal.ai/models/fal-ai/hunyuan-video-v1.5/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/hunyuan-video-v1.5/text-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.075, + "source": "https://fal.ai/models/fal-ai/hunyuan-video-v1.5/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/iclight-v2": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/iclight-v2 at $0.1 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.1, + "output_cost_per_pixel": 9.5367431640625e-08, + "source": "https://fal.ai/models/fal-ai/iclight-v2", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/id-v2v": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.2, + "source": "https://fal.ai/models/fal-ai/id-v2v", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/id-v2v/relight": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.2, + "source": "https://fal.ai/models/fal-ai/id-v2v/relight", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ideogram/character": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.15, + "source": "https://fal.ai/models/fal-ai/ideogram/character", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/character/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.15, + "source": "https://fal.ai/models/fal-ai/ideogram/character/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/character/remix": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.15, + "source": "https://fal.ai/models/fal-ai/ideogram/character/remix", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/object-removal": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://fal.ai/models/fal-ai/ideogram/object-removal", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/remove-background": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://fal.ai/models/fal-ai/ideogram/remove-background", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/upscale": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://fal.ai/models/fal-ai/ideogram/upscale", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/v2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://fal.ai/models/fal-ai/ideogram/v2", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/ideogram/v2/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://fal.ai/models/fal-ai/ideogram/v2/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/v2/remix": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://fal.ai/models/fal-ai/ideogram/v2/remix", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/v2/turbo": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://fal.ai/models/fal-ai/ideogram/v2/turbo", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/ideogram/v2/turbo/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://fal.ai/models/fal-ai/ideogram/v2/turbo/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/v2/turbo/remix": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://fal.ai/models/fal-ai/ideogram/v2/turbo/remix", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/v2a": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/ideogram/v2a", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/ideogram/v2a/remix": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/ideogram/v2a/remix", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/v2a/turbo": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.025, + "source": "https://fal.ai/models/fal-ai/ideogram/v2a/turbo", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/ideogram/v2a/turbo/remix": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.025, + "source": "https://fal.ai/models/fal-ai/ideogram/v2a/turbo/remix", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/v3/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://fal.ai/models/fal-ai/ideogram/v3/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/v3/generate-transparent": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://fal.ai/models/fal-ai/ideogram/v3/generate-transparent", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/ideogram/v3/layerize-text": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.09, + "source": "https://fal.ai/models/fal-ai/ideogram/v3/layerize-text", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/v3/reframe": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://fal.ai/models/fal-ai/ideogram/v3/reframe", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/v3/remix": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://fal.ai/models/fal-ai/ideogram/v3/remix", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/v3/replace-background": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://fal.ai/models/fal-ai/ideogram/v3/replace-background", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/age-modify": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/age-modify", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/city-teleport": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/city-teleport", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/expression-change": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/expression-change", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/hair-change": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/hair-change", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/headshot-photo": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/headshot-photo", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/makeup-application": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/makeup-application", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/object-removal": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/object-removal", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/outpaint": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/image-apps-v2/outpaint at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/outpaint", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/perspective": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/perspective", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/photo-restoration": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/photo-restoration", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/photography-effects": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.4, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/photography-effects", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/portrait-enhance": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.4, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/portrait-enhance", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/product-holding": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/product-holding", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/product-photography": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/product-photography", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/relighting": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/relighting", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/style-transfer": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/style-transfer", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/texture-transform": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/texture-transform", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/virtual-try-on": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/virtual-try-on", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/age-progression": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/age-progression", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/baby-version": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/baby-version", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/background-change": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/background-change", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/broccoli-haircut": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/broccoli-haircut", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/cartoonify": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/cartoonify", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/color-correction": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/color-correction", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/expression-change": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/expression-change", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/face-enhancement": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/face-enhancement", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/hair-change": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/hair-change", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/object-removal": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/object-removal", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/photo-restoration": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/photo-restoration", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/plushie-style": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/plushie-style", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/professional-photo": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/professional-photo", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/realism": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/realism", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/reframe": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/reframe", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/retouch": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/retouch", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/scene-composition": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/scene-composition", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/style-transfer": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/style-transfer", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/text-removal": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/text-removal", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/time-of-day": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/time-of-day", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/weather-effect": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/weather-effect", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/wojak-style": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/wojak-style", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/youtube-thumbnails": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/youtube-thumbnails", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image2svg": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.005, + "source": "https://fal.ai/models/fal-ai/image2svg", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/instant-character": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/instant-character at $0.1 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.1, + "output_cost_per_pixel": 9.5367431640625e-08, + "source": "https://fal.ai/models/fal-ai/instant-character", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/kling-image/o1": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.028, + "source": "https://fal.ai/models/fal-ai/kling-image/o1", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/kling-image/o3/image-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.028, + "source": "https://fal.ai/models/fal-ai/kling-image/o3/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/kling-image/o3/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.028, + "source": "https://fal.ai/models/fal-ai/kling-image/o3/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/kling-image/v3/image-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.028, + "source": "https://fal.ai/models/fal-ai/kling-image/v3/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/kling-image/v3/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.028, + "source": "https://fal.ai/models/fal-ai/kling-image/v3/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/kling-video/ai-avatar/v2/pro": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.115, + "source": "https://fal.ai/models/fal-ai/kling-video/ai-avatar/v2/pro", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/ai-avatar/v2/standard": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.0562, + "source": "https://fal.ai/models/fal-ai/kling-video/ai-avatar/v2/standard", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o1/image-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.112, + "source": "https://fal.ai/models/fal-ai/kling-video/o1/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o1/reference-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.112, + "source": "https://fal.ai/models/fal-ai/kling-video/o1/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o1/standard/image-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.084, + "source": "https://fal.ai/models/fal-ai/kling-video/o1/standard/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o1/standard/reference-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.084, + "source": "https://fal.ai/models/fal-ai/kling-video/o1/standard/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o1/standard/video-to-video/edit": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.126, + "source": "https://fal.ai/models/fal-ai/kling-video/o1/standard/video-to-video/edit", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o1/standard/video-to-video/reference": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.126, + "source": "https://fal.ai/models/fal-ai/kling-video/o1/standard/video-to-video/reference", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o1/video-to-video/edit": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.168, + "source": "https://fal.ai/models/fal-ai/kling-video/o1/video-to-video/edit", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o1/video-to-video/reference": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.168, + "source": "https://fal.ai/models/fal-ai/kling-video/o1/video-to-video/reference", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o3/4k/image-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.42, + "source": "https://fal.ai/models/fal-ai/kling-video/o3/4k/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o3/4k/reference-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.42, + "source": "https://fal.ai/models/fal-ai/kling-video/o3/4k/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o3/4k/text-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.42, + "source": "https://fal.ai/models/fal-ai/kling-video/o3/4k/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o3/4k/video-to-video/edit": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.42, + "source": "https://fal.ai/models/fal-ai/kling-video/o3/4k/video-to-video/edit", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o3/4k/video-to-video/reference": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.42, + "source": "https://fal.ai/models/fal-ai/kling-video/o3/4k/video-to-video/reference", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o3/pro/video-to-video/edit": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.168, + "source": "https://fal.ai/models/fal-ai/kling-video/o3/pro/video-to-video/edit", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o3/pro/video-to-video/reference": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.168, + "source": "https://fal.ai/models/fal-ai/kling-video/o3/pro/video-to-video/reference", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o3/standard/video-to-video/edit": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.126, + "source": "https://fal.ai/models/fal-ai/kling-video/o3/standard/video-to-video/edit", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o3/standard/video-to-video/reference": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.126, + "source": "https://fal.ai/models/fal-ai/kling-video/o3/standard/video-to-video/reference", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v1.5/pro/effects": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://fal.ai/models/fal-ai/kling-video/v1.5/pro/effects", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v1.6/pro/effects": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.098, + "source": "https://fal.ai/models/fal-ai/kling-video/v1.6/pro/effects", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v1.6/standard/effects": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.056, + "source": "https://fal.ai/models/fal-ai/kling-video/v1.6/standard/effects", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v1/pro/ai-avatar": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.115, + "source": "https://fal.ai/models/fal-ai/kling-video/v1/pro/ai-avatar", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v1/standard/ai-avatar": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.0562, + "source": "https://fal.ai/models/fal-ai/kling-video/v1/standard/ai-avatar", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v1/standard/effects": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.045, + "source": "https://fal.ai/models/fal-ai/kling-video/v1/standard/effects", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v2.6/pro/motion-control": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.112, + "source": "https://fal.ai/models/fal-ai/kling-video/v2.6/pro/motion-control", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v2.6/standard/motion-control": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.07, + "source": "https://fal.ai/models/fal-ai/kling-video/v2.6/standard/motion-control", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v3/4k/image-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.42, + "source": "https://fal.ai/models/fal-ai/kling-video/v3/4k/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v3/4k/text-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.42, + "source": "https://fal.ai/models/fal-ai/kling-video/v3/4k/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v3/pro/motion-control": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.168, + "source": "https://fal.ai/models/fal-ai/kling-video/v3/pro/motion-control", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v3/standard/motion-control": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.126, + "source": "https://fal.ai/models/fal-ai/kling-video/v3/standard/motion-control", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v3/turbo/pro/image-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.14, + "source": "https://fal.ai/models/fal-ai/kling-video/v3/turbo/pro/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v3/turbo/pro/text-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.14, + "source": "https://fal.ai/models/fal-ai/kling-video/v3/turbo/pro/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v3/turbo/standard/image-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.112, + "source": "https://fal.ai/models/fal-ai/kling-video/v3/turbo/standard/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v3/turbo/standard/text-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.112, + "source": "https://fal.ai/models/fal-ai/kling-video/v3/turbo/standard/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/krea-2/turbo": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/krea-2/turbo at $0.008 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.008, + "output_cost_per_pixel": 7.62939453125e-09, + "source": "https://fal.ai/models/fal-ai/krea-2/turbo", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/krea-2/turbo/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/krea-2/turbo/lora at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "output_cost_per_pixel": 9.5367431640625e-09, + "source": "https://fal.ai/models/fal-ai/krea-2/turbo/lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/krea-2/turbo/style": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/krea-2/turbo/style at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "output_cost_per_pixel": 9.5367431640625e-09, + "source": "https://fal.ai/models/fal-ai/krea-2/turbo/style", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/krea-wan-14b/text-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.025, + "source": "https://fal.ai/models/fal-ai/krea-wan-14b/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/krea-wan-14b/video-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.025, + "source": "https://fal.ai/models/fal-ai/krea-wan-14b/video-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/latentsync": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.005, + "source": "https://fal.ai/models/fal-ai/latentsync", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/leffa/pose-transfer": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.1, + "source": "https://fal.ai/models/fal-ai/leffa/pose-transfer", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/leffa/virtual-tryon": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.1, + "source": "https://fal.ai/models/fal-ai/leffa/virtual-tryon", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/lightx/recamera": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://fal.ai/models/fal-ai/lightx/recamera", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/lightx/relight": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://fal.ai/models/fal-ai/lightx/relight", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/longcat-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/longcat-image at $0.13 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.13, + "output_cost_per_pixel": 1.239776611328125e-07, + "source": "https://fal.ai/models/fal-ai/longcat-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/longcat-image/edit": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/longcat-image/edit at $0.15 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.15, + "output_cost_per_pixel": 1.430511474609375e-07, + "source": "https://fal.ai/models/fal-ai/longcat-image/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/longcat-video/distilled/image-to-video/480p": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.005, + "source": "https://fal.ai/models/fal-ai/longcat-video/distilled/image-to-video/480p", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/longcat-video/distilled/image-to-video/720p": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.01, + "source": "https://fal.ai/models/fal-ai/longcat-video/distilled/image-to-video/720p", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/longcat-video/distilled/text-to-video/480p": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.005, + "source": "https://fal.ai/models/fal-ai/longcat-video/distilled/text-to-video/480p", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/longcat-video/distilled/text-to-video/720p": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.01, + "source": "https://fal.ai/models/fal-ai/longcat-video/distilled/text-to-video/720p", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/longcat-video/image-to-video/480p": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.025, + "source": "https://fal.ai/models/fal-ai/longcat-video/image-to-video/480p", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/longcat-video/image-to-video/720p": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.04, + "source": "https://fal.ai/models/fal-ai/longcat-video/image-to-video/720p", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/longcat-video/text-to-video/480p": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.025, + "source": "https://fal.ai/models/fal-ai/longcat-video/text-to-video/480p", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/longcat-video/text-to-video/720p": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.04, + "source": "https://fal.ai/models/fal-ai/longcat-video/text-to-video/720p", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ltx-2.3/audio-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://fal.ai/models/fal-ai/ltx-2.3/audio-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ltx-2.3/extend-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://fal.ai/models/fal-ai/ltx-2.3/extend-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ltx-2.3/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate; tiers without a catalog field: 1440p $0.16, 2160p $0.32"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_1080p": 0.08, + "source": "https://fal.ai/models/fal-ai/ltx-2.3/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ltx-2.3/image-to-video/fast": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate; tiers without a catalog field: 1440p $0.12, 2160p $0.24"}, + "mode": "video_generation", + "output_cost_per_second": 0.06, + "output_cost_per_second_1080p": 0.06, + "source": "https://fal.ai/models/fal-ai/ltx-2.3/image-to-video/fast", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ltx-2.3/reframe": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.2, + "output_cost_per_second_1080p": 0.2, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/fal-ai/ltx-2.3/reframe", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ltx-2.3/retake-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://fal.ai/models/fal-ai/ltx-2.3/retake-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ltx-2.3/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate; tiers without a catalog field: 1440p $0.16, 2160p $0.32"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_1080p": 0.08, + "source": "https://fal.ai/models/fal-ai/ltx-2.3/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ltx-2.3/text-to-video/fast": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate; tiers without a catalog field: 1440p $0.12, 2160p $0.24"}, + "mode": "video_generation", + "output_cost_per_second": 0.06, + "output_cost_per_second_1080p": 0.06, + "source": "https://fal.ai/models/fal-ai/ltx-2.3/text-to-video/fast", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ltxv-13b-098-distilled": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.02, + "source": "https://fal.ai/models/fal-ai/ltxv-13b-098-distilled", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ltxv-13b-098-distilled/extend": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.02, + "source": "https://fal.ai/models/fal-ai/ltxv-13b-098-distilled/extend", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ltxv-13b-098-distilled/image-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.02, + "source": "https://fal.ai/models/fal-ai/ltxv-13b-098-distilled/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ltxv-13b-098-distilled/multiconditioning": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.02, + "source": "https://fal.ai/models/fal-ai/ltxv-13b-098-distilled/multiconditioning", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/lumina-image/v2": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/lumina-image/v2 at $0.075 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.075, + "output_cost_per_pixel": 7.152557373046875e-08, + "source": "https://fal.ai/models/fal-ai/lumina-image/v2", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/marigold-v2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://fal.ai/models/fal-ai/marigold-v2", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/minimax/hailuo-02-fast/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 512p rate; tiers without a catalog field: 512p $0.017"}, + "mode": "video_generation", + "output_cost_per_second": 0.017, + "source": "https://fal.ai/models/fal-ai/minimax/hailuo-02-fast/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/minimax/hailuo-02/pro/image-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.08, + "source": "https://fal.ai/models/fal-ai/minimax/hailuo-02/pro/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/minimax/hailuo-02/pro/text-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.08, + "source": "https://fal.ai/models/fal-ai/minimax/hailuo-02/pro/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/minimax/hailuo-02/standard/text-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.045, + "source": "https://fal.ai/models/fal-ai/minimax/hailuo-02/standard/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/minimax/image-01/subject-reference": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://fal.ai/models/fal-ai/minimax/image-01/subject-reference", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/mmaudio-v2": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.001, + "source": "https://fal.ai/models/fal-ai/mmaudio-v2", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/moss-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/moss-image at $0.05 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.05, + "output_cost_per_pixel": 4.76837158203125e-08, + "source": "https://fal.ai/models/fal-ai/moss-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/nafnet/deblur": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/nafnet/deblur at $0.0225 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.0225, + "output_cost_per_pixel": 2.1457672119140624e-08, + "source": "https://fal.ai/models/fal-ai/nafnet/deblur", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/nafnet/denoise": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/nafnet/denoise at $0.0225 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.0225, + "output_cost_per_pixel": 2.1457672119140624e-08, + "source": "https://fal.ai/models/fal-ai/nafnet/denoise", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/nano-banana-2/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://fal.ai/models/fal-ai/nano-banana-2/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/nano-banana-pro/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.15, + "source": "https://fal.ai/models/fal-ai/nano-banana-pro/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/nano-banana/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.0398, + "source": "https://fal.ai/models/fal-ai/nano-banana/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/nucleus-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/nucleus-image at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "output_cost_per_pixel": 9.5367431640625e-09, + "source": "https://fal.ai/models/fal-ai/nucleus-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/omnigen-v2": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/omnigen-v2 at $0.15 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.15, + "output_cost_per_pixel": 1.430511474609375e-07, + "source": "https://fal.ai/models/fal-ai/omnigen-v2", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/one-to-all-animation/1.3b": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 480p rate; tiers without a catalog field: 580p $0.045"}, + "mode": "video_generation", + "output_cost_per_second": 0.03, + "output_cost_per_second_480p": 0.03, + "output_cost_per_second_720p": 0.06, + "source": "https://fal.ai/models/fal-ai/one-to-all-animation/1.3b", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/one-to-all-animation/14b": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 480p rate; tiers without a catalog field: 580p $0.09"}, + "mode": "video_generation", + "output_cost_per_second": 0.06, + "output_cost_per_second_480p": 0.06, + "output_cost_per_second_720p": 0.12, + "source": "https://fal.ai/models/fal-ai/one-to-all-animation/14b", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/patina": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/patina at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "output_cost_per_pixel": 9.5367431640625e-09, + "source": "https://fal.ai/models/fal-ai/patina", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/phota/enhance": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.13, + "source": "https://fal.ai/models/fal-ai/phota/enhance", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/post-processing/blur": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.001, + "source": "https://fal.ai/models/fal-ai/post-processing/blur", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/post-processing/chromatic-aberration": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.001, + "source": "https://fal.ai/models/fal-ai/post-processing/chromatic-aberration", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/post-processing/color-correction": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.001, + "source": "https://fal.ai/models/fal-ai/post-processing/color-correction", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/post-processing/color-tint": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.001, + "source": "https://fal.ai/models/fal-ai/post-processing/color-tint", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/post-processing/desaturate": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.001, + "source": "https://fal.ai/models/fal-ai/post-processing/desaturate", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/post-processing/dissolve": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.001, + "source": "https://fal.ai/models/fal-ai/post-processing/dissolve", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/post-processing/dodge-burn": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.001, + "source": "https://fal.ai/models/fal-ai/post-processing/dodge-burn", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/post-processing/grain": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.001, + "source": "https://fal.ai/models/fal-ai/post-processing/grain", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/post-processing/parabolize": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.001, + "source": "https://fal.ai/models/fal-ai/post-processing/parabolize", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/post-processing/sharpen": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.001, + "source": "https://fal.ai/models/fal-ai/post-processing/sharpen", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/post-processing/solarize": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.001, + "source": "https://fal.ai/models/fal-ai/post-processing/solarize", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/post-processing/vignette": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.001, + "source": "https://fal.ai/models/fal-ai/post-processing/vignette", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image at $0.02 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.02, + "output_cost_per_pixel": 1.9073486328125e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/qwen-image-2512": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-2512 at $0.02 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.02, + "output_cost_per_pixel": 1.9073486328125e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-2512", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/qwen-image-2512/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-2512/lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-2512/lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/qwen-image-edit-2509": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509 at $0.03 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.03, + "output_cost_per_pixel": 2.86102294921875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-2509-lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-2509-lora-gallery/add-background": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora-gallery/add-background at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora-gallery/add-background", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-2509-lora-gallery/face-to-full-portrait": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora-gallery/face-to-full-portrait at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora-gallery/face-to-full-portrait", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-2509-lora-gallery/group-photo": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora-gallery/group-photo at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora-gallery/group-photo", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-2509-lora-gallery/integrate-product": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora-gallery/integrate-product at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora-gallery/integrate-product", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-2509-lora-gallery/lighting-restoration": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora-gallery/lighting-restoration at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora-gallery/lighting-restoration", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-2509-lora-gallery/multiple-angles": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora-gallery/multiple-angles at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora-gallery/multiple-angles", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-2509-lora-gallery/next-scene": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora-gallery/next-scene at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora-gallery/next-scene", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-2509-lora-gallery/remove-element": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora-gallery/remove-element at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora-gallery/remove-element", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-2509-lora-gallery/remove-lighting": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora-gallery/remove-lighting at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora-gallery/remove-lighting", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-2509-lora-gallery/shirt-design": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora-gallery/shirt-design at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora-gallery/shirt-design", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-2511": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2511 at $0.03 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.03, + "output_cost_per_pixel": 2.86102294921875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2511", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-2511-multiple-angles": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2511-multiple-angles at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2511-multiple-angles", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-2511/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2511/lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2511/lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-plus": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus at $0.03 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.03, + "output_cost_per_pixel": 2.86102294921875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-plus-lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-plus-lora-gallery/add-background": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora-gallery/add-background at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora-gallery/add-background", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-plus-lora-gallery/face-to-full-portrait": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora-gallery/face-to-full-portrait at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora-gallery/face-to-full-portrait", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-plus-lora-gallery/group-photo": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora-gallery/group-photo at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora-gallery/group-photo", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-plus-lora-gallery/integrate-product": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora-gallery/integrate-product at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora-gallery/integrate-product", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-plus-lora-gallery/lighting-restoration": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora-gallery/lighting-restoration at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora-gallery/lighting-restoration", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-plus-lora-gallery/multiple-angles": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora-gallery/multiple-angles at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora-gallery/multiple-angles", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-plus-lora-gallery/next-scene": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora-gallery/next-scene at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora-gallery/next-scene", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-plus-lora-gallery/remove-element": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora-gallery/remove-element at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora-gallery/remove-element", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-plus-lora-gallery/remove-lighting": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora-gallery/remove-lighting at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora-gallery/remove-lighting", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-plus-lora-gallery/shirt-design": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora-gallery/shirt-design at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora-gallery/shirt-design", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit/image-to-image at $0.03 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.03, + "output_cost_per_pixel": 2.86102294921875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit/inpaint": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit/inpaint at $0.03 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.03, + "output_cost_per_pixel": 2.86102294921875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit/inpaint", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-layered": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://fal.ai/models/fal-ai/qwen-image-layered", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-layered/lora": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://fal.ai/models/fal-ai/qwen-image-layered/lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image/image-to-image at $0.02 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.02, + "output_cost_per_pixel": 1.9073486328125e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/recraft/upscale/creative": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.25, + "source": "https://fal.ai/models/fal-ai/recraft/upscale/creative", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/recraft/upscale/crisp": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.004, + "source": "https://fal.ai/models/fal-ai/recraft/upscale/crisp", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/recraft/v4.1/pro/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.21, + "source": "https://fal.ai/models/fal-ai/recraft/v4.1/pro/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/recraft/v4.1/pro/text-to-vector": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.3, + "source": "https://fal.ai/models/fal-ai/recraft/v4.1/pro/text-to-vector", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/recraft/v4.1/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.035, + "source": "https://fal.ai/models/fal-ai/recraft/v4.1/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/recraft/v4.1/text-to-vector": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://fal.ai/models/fal-ai/recraft/v4.1/text-to-vector", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/recraft/v4.1/utility/pro/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.21, + "source": "https://fal.ai/models/fal-ai/recraft/v4.1/utility/pro/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/recraft/v4.1/utility/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.035, + "source": "https://fal.ai/models/fal-ai/recraft/v4.1/utility/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/recraft/v4/pro/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.25, + "source": "https://fal.ai/models/fal-ai/recraft/v4/pro/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/recraft/v4/pro/text-to-vector": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.3, + "source": "https://fal.ai/models/fal-ai/recraft/v4/pro/text-to-vector", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/recraft/v4/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/recraft/v4/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/recraft/v4/text-to-vector": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://fal.ai/models/fal-ai/recraft/v4/text-to-vector", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/recraft/vectorize": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://fal.ai/models/fal-ai/recraft/vectorize", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/sana": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/sana at $0.001 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.001, + "output_cost_per_pixel": 9.5367431640625e-10, + "source": "https://fal.ai/models/fal-ai/sana", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/sana/sprint": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/sana/sprint at $0.0025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.0025, + "output_cost_per_pixel": 2.384185791015625e-09, + "source": "https://fal.ai/models/fal-ai/sana/sprint", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/sana/v1.5/1.6b": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/sana/v1.5/1.6b at $0.0075 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.0075, + "output_cost_per_pixel": 7.152557373046875e-09, + "source": "https://fal.ai/models/fal-ai/sana/v1.5/1.6b", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/sana/v1.5/4.8b": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/sana/v1.5/4.8b at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "output_cost_per_pixel": 9.5367431640625e-09, + "source": "https://fal.ai/models/fal-ai/sana/v1.5/4.8b", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/seedvr/upscale/image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/seedvr/upscale/image at $0.001 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.001, + "output_cost_per_pixel": 9.5367431640625e-10, + "source": "https://fal.ai/models/fal-ai/seedvr/upscale/image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/seedvr/upscale/image/seamless": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/seedvr/upscale/image/seamless at $0.0025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.0025, + "output_cost_per_pixel": 2.384185791015625e-09, + "source": "https://fal.ai/models/fal-ai/seedvr/upscale/image/seamless", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/stable-diffusion-v3-medium": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.035, + "source": "https://fal.ai/models/fal-ai/stable-diffusion-v3-medium", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/stable-diffusion-v35-large": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/stable-diffusion-v35-large at $0.065 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.065, + "output_cost_per_pixel": 6.198883056640625e-08, + "source": "https://fal.ai/models/fal-ai/stable-diffusion-v35-large", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/stepx-edit2": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/stepx-edit2 at $0.2 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.2, + "output_cost_per_pixel": 1.9073486328125e-07, + "source": "https://fal.ai/models/fal-ai/stepx-edit2", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/telestyle-v2": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/telestyle-v2 at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/telestyle-v2", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/uso": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/uso at $0.1 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.1, + "output_cost_per_pixel": 9.5367431640625e-08, + "source": "https://fal.ai/models/fal-ai/uso", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/vidu/q2/reference-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.1, + "source": "https://fal.ai/models/fal-ai/vidu/q2/reference-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/vidu/q2/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.1, + "source": "https://fal.ai/models/fal-ai/vidu/q2/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/vidu/reference-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.1, + "source": "https://fal.ai/models/fal-ai/vidu/reference-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/wan-22-vace-fun-a14b/depth": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.075"}, + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/fal-ai/wan-22-vace-fun-a14b/depth", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan-22-vace-fun-a14b/inpainting": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.075"}, + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/fal-ai/wan-22-vace-fun-a14b/inpainting", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan-22-vace-fun-a14b/outpainting": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.075"}, + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/fal-ai/wan-22-vace-fun-a14b/outpainting", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan-22-vace-fun-a14b/reframe": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.075"}, + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/fal-ai/wan-22-vace-fun-a14b/reframe", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan-25-preview/image-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://fal.ai/models/fal-ai/wan-25-preview/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/wan-25-preview/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/fal-ai/wan-25-preview/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan-25-preview/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://fal.ai/models/fal-ai/wan-25-preview/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/wan-25-preview/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/fal-ai/wan-25-preview/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan-vace-14b": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.06"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_480p": 0.04, + "output_cost_per_second_720p": 0.08, + "source": "https://fal.ai/models/fal-ai/wan-vace-14b", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan-vace-14b/depth": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.06"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_480p": 0.04, + "output_cost_per_second_720p": 0.08, + "source": "https://fal.ai/models/fal-ai/wan-vace-14b/depth", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan-vace-14b/inpainting": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.06"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_480p": 0.04, + "output_cost_per_second_720p": 0.08, + "source": "https://fal.ai/models/fal-ai/wan-vace-14b/inpainting", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan-vace-14b/outpainting": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.06"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_480p": 0.04, + "output_cost_per_second_720p": 0.08, + "source": "https://fal.ai/models/fal-ai/wan-vace-14b/outpainting", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan-vace-14b/pose": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.06"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_480p": 0.04, + "output_cost_per_second_720p": 0.08, + "source": "https://fal.ai/models/fal-ai/wan-vace-14b/pose", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan-vace-14b/reframe": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.06"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_480p": 0.04, + "output_cost_per_second_720p": 0.08, + "source": "https://fal.ai/models/fal-ai/wan-vace-14b/reframe", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan-vace-apps/video-edit": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.075"}, + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/fal-ai/wan-vace-apps/video-edit", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan/v2.2-14b/speech-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 480p rate; tiers without a catalog field: 580p $0.15"}, + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_480p": 0.1, + "output_cost_per_second_720p": 0.2, + "source": "https://fal.ai/models/fal-ai/wan/v2.2-14b/speech-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan/v2.2-5b/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.016, + "source": "https://fal.ai/models/fal-ai/wan/v2.2-5b/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/wan/v2.2-a14b/image-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://fal.ai/models/fal-ai/wan/v2.2-a14b/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/wan/v2.2-a14b/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; tiers without a catalog field: 580p $0.06"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_480p": 0.04, + "output_cost_per_second_720p": 0.08, + "source": "https://fal.ai/models/fal-ai/wan/v2.2-a14b/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan/v2.2-a14b/image-to-video/lora": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://fal.ai/models/fal-ai/wan/v2.2-a14b/image-to-video/lora", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan/v2.2-a14b/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.025, + "source": "https://fal.ai/models/fal-ai/wan/v2.2-a14b/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/wan/v2.2-a14b/text-to-image/lora": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://fal.ai/models/fal-ai/wan/v2.2-a14b/text-to-image/lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/wan/v2.2-a14b/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; tiers without a catalog field: 580p $0.06"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_480p": 0.04, + "output_cost_per_second_720p": 0.08, + "source": "https://fal.ai/models/fal-ai/wan/v2.2-a14b/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan/v2.2-a14b/text-to-video/lora": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://fal.ai/models/fal-ai/wan/v2.2-a14b/text-to-video/lora", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan/v2.2-a14b/video-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; tiers without a catalog field: 580p $0.06"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_480p": 0.04, + "output_cost_per_second_720p": 0.08, + "source": "https://fal.ai/models/fal-ai/wan/v2.2-a14b/video-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan/v2.7/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://fal.ai/models/fal-ai/wan/v2.7/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/wan/v2.7/edit-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/fal-ai/wan/v2.7/edit-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan/v2.7/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/fal-ai/wan/v2.7/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan/v2.7/pro/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.075, + "source": "https://fal.ai/models/fal-ai/wan/v2.7/pro/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/wan/v2.7/pro/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.075, + "source": "https://fal.ai/models/fal-ai/wan/v2.7/pro/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/wan/v2.7/reference-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://fal.ai/models/fal-ai/wan/v2.7/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan/v2.7/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://fal.ai/models/fal-ai/wan/v2.7/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/wan/v2.7/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/fal-ai/wan/v2.7/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/z-image/base": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/z-image/base at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "output_cost_per_pixel": 9.5367431640625e-09, + "source": "https://fal.ai/models/fal-ai/z-image/base", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/z-image/base/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/z-image/base/lora at $0.012 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.012, + "output_cost_per_pixel": 1.1444091796875e-08, + "source": "https://fal.ai/models/fal-ai/z-image/base/lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/z-image/turbo": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/z-image/turbo at $0.005 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.005, + "output_cost_per_pixel": 4.76837158203125e-09, + "source": "https://fal.ai/models/fal-ai/z-image/turbo", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/z-image/turbo/controlnet": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/z-image/turbo/controlnet at $0.0065 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.0065, + "output_cost_per_pixel": 6.198883056640625e-09, + "source": "https://fal.ai/models/fal-ai/z-image/turbo/controlnet", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/z-image/turbo/controlnet/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/z-image/turbo/controlnet/lora at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "output_cost_per_pixel": 9.5367431640625e-09, + "source": "https://fal.ai/models/fal-ai/z-image/turbo/controlnet/lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/z-image/turbo/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/z-image/turbo/image-to-image at $0.005 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.005, + "output_cost_per_pixel": 4.76837158203125e-09, + "source": "https://fal.ai/models/fal-ai/z-image/turbo/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/z-image/turbo/image-to-image/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/z-image/turbo/image-to-image/lora at $0.0085 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.0085, + "output_cost_per_pixel": 8.106231689453126e-09, + "source": "https://fal.ai/models/fal-ai/z-image/turbo/image-to-image/lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/z-image/turbo/inpaint": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/z-image/turbo/inpaint at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "output_cost_per_pixel": 9.5367431640625e-09, + "source": "https://fal.ai/models/fal-ai/z-image/turbo/inpaint", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/z-image/turbo/inpaint/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/z-image/turbo/inpaint/lora at $0.0115 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.0115, + "output_cost_per_pixel": 1.0967254638671875e-08, + "source": "https://fal.ai/models/fal-ai/z-image/turbo/inpaint/lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/z-image/turbo/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/z-image/turbo/lora at $0.0085 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.0085, + "output_cost_per_pixel": 8.106231689453126e-09, + "source": "https://fal.ai/models/fal-ai/z-image/turbo/lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/z-image/turbo/tiling": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/z-image/turbo/tiling at $0.02 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.02, + "output_cost_per_pixel": 1.9073486328125e-08, + "source": "https://fal.ai/models/fal-ai/z-image/turbo/tiling", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/z-image/turbo/tiling/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/z-image/turbo/tiling/lora at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/z-image/turbo/tiling/lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/google/gemini-omni-flash/v1.1/edit": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; tiers without a catalog field: 360p $0.03"}, + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_4k": 0.3, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/google/gemini-omni-flash/v1.1/edit", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/google/gemini-omni-flash/v1.1/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; tiers without a catalog field: 360p $0.03"}, + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_4k": 0.3, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/google/gemini-omni-flash/v1.1/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/google/gemini-omni-flash/v1.1/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; tiers without a catalog field: 360p $0.03"}, + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_4k": 0.3, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/google/gemini-omni-flash/v1.1/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/google/gemini-omni-flash/v1.1/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; tiers without a catalog field: 360p $0.03"}, + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_4k": 0.3, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/google/gemini-omni-flash/v1.1/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/kling/v4/flash/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.094, + "output_cost_per_second_720p": 0.094, + "source": "https://fal.ai/models/kling/v4/flash/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/kling/v4/flash/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.094, + "output_cost_per_second_720p": 0.094, + "source": "https://fal.ai/models/kling/v4/flash/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/kling/v4/flash/video-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.063, + "output_cost_per_second_720p": 0.063, + "source": "https://fal.ai/models/kling/v4/flash/video-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/kling/v4/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.235, + "output_cost_per_second_1080p": 0.235, + "output_cost_per_second_720p": 0.157, + "source": "https://fal.ai/models/kling/v4/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/kling/v4/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.235, + "output_cost_per_second_1080p": 0.235, + "output_cost_per_second_720p": 0.157, + "source": "https://fal.ai/models/kling/v4/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/kling/v4/video-to-video/edit": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.141, + "output_cost_per_second_1080p": 0.141, + "output_cost_per_second_720p": 0.094, + "source": "https://fal.ai/models/kling/v4/video-to-video/edit", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/krea/v3/edit": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills krea/v3/edit at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/krea/v3/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/krea/v3/text-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills krea/v3/text-to-image at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/krea/v3/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/luma/agent/uni-1/v1/max": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.102, + "source": "https://fal.ai/models/luma/agent/uni-1/v1/max", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/luma/agent/uni-1/v1/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.042, + "source": "https://fal.ai/models/luma/agent/uni-1/v1/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/meta/muse-image/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://fal.ai/models/meta/muse-image/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/meta/muse-image/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://fal.ai/models/meta/muse-image/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/minimax/h3-max-turbo/extend-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.04, + "output_cost_per_second_1080p": 0.08, + "output_cost_per_second_2k": 0.16, + "output_cost_per_second_480p": 0.025, + "output_cost_per_second_768p": 0.04, + "source": "https://fal.ai/models/minimax/h3-max-turbo/extend-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max-turbo/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_1080p": 0.16, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_768p": 0.08, + "source": "https://fal.ai/models/minimax/h3-max-turbo/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max/extend-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_1080p": 0.16, + "output_cost_per_second_2k": 0.32, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_768p": 0.08, + "source": "https://fal.ai/models/minimax/h3-max/extend-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max/insert-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.06, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_768p": 0.06, + "source": "https://fal.ai/models/minimax/h3-max/insert-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max/lip-sync/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_1080p": 0.16, + "output_cost_per_second_2k": 0.32, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_768p": 0.08, + "source": "https://fal.ai/models/minimax/h3-max/lip-sync/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 2k rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.13, + "output_cost_per_second_2k": 0.13, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_4k": 0.16, + "output_cost_per_second_768p": 0.06, + "source": "https://fal.ai/models/minimax/h3/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3/image-to-video/lora": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 2k rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.1625, + "output_cost_per_second_2k": 0.1625, + "output_cost_per_second_480p": 0.0625, + "output_cost_per_second_4k": 0.2, + "output_cost_per_second_768p": 0.075, + "source": "https://fal.ai/models/minimax/h3/image-to-video/lora", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3/reference-to-video/lora": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 2k rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.1625, + "output_cost_per_second_2k": 0.1625, + "output_cost_per_second_480p": 0.0625, + "output_cost_per_second_4k": 0.2, + "output_cost_per_second_768p": 0.075, + "source": "https://fal.ai/models/minimax/h3/reference-to-video/lora", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3/text-to-video/lora": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 2k rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.1625, + "output_cost_per_second_2k": 0.1625, + "output_cost_per_second_480p": 0.0625, + "output_cost_per_second_4k": 0.2, + "output_cost_per_second_768p": 0.075, + "source": "https://fal.ai/models/minimax/h3/text-to-video/lora", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/nvidia/cosmos-3-super/image-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://fal.ai/models/nvidia/cosmos-3-super/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/pixelcut/background-removal": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.016, + "source": "https://fal.ai/models/pixelcut/background-removal", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/pixelcut/looping-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.32, + "output_cost_per_second_1080p": 0.32, + "output_cost_per_second_480p": 0.08, + "output_cost_per_second_768p": 0.16, + "source": "https://fal.ai/models/pixelcut/looping-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/pixelcut/product-photo": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.024, + "source": "https://fal.ai/models/pixelcut/product-photo", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/pixverse/music-video/vibemv": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.06, + "output_cost_per_second_1080p": 0.09, + "output_cost_per_second_720p": 0.06, + "source": "https://fal.ai/models/pixverse/music-video/vibemv", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/recraft/v4.1/flash/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.007, + "source": "https://fal.ai/models/recraft/v4.1/flash/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/rundiffusion-fal/juggernaut-flux/base": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills rundiffusion-fal/juggernaut-flux/base at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/rundiffusion-fal/juggernaut-flux/base", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/rundiffusion-fal/juggernaut-flux/base/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills rundiffusion-fal/juggernaut-flux/base/image-to-image at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/rundiffusion-fal/juggernaut-flux/base/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/rundiffusion-fal/juggernaut-flux/lightning": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills rundiffusion-fal/juggernaut-flux/lightning at $0.006 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.006, + "output_cost_per_pixel": 5.7220458984375e-09, + "source": "https://fal.ai/models/rundiffusion-fal/juggernaut-flux/lightning", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/rundiffusion-fal/juggernaut-flux/pro": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills rundiffusion-fal/juggernaut-flux/pro at $0.055 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.055, + "output_cost_per_pixel": 5.245208740234375e-08, + "source": "https://fal.ai/models/rundiffusion-fal/juggernaut-flux/pro", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/rundiffusion-fal/juggernaut-flux/pro/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills rundiffusion-fal/juggernaut-flux/pro/image-to-image at $0.055 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.055, + "output_cost_per_pixel": 5.245208740234375e-08, + "source": "https://fal.ai/models/rundiffusion-fal/juggernaut-flux/pro/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/rundiffusion-fal/rundiffusion-photo-flux": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills rundiffusion-fal/rundiffusion-photo-flux at $0.045 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.045, + "output_cost_per_pixel": 4.291534423828125e-08, + "source": "https://fal.ai/models/rundiffusion-fal/rundiffusion-photo-flux", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/smoretalk-ai/rembg-enhance": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.006, + "source": "https://fal.ai/models/smoretalk-ai/rembg-enhance", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/sonilo/v1.1/video-to-video-music": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.009, + "source": "https://fal.ai/models/sonilo/v1.1/video-to-video-music", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/sonilo/v1.1/video-to-video-sound-effects": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.009, + "source": "https://fal.ai/models/sonilo/v1.1/video-to-video-sound-effects", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/tbc/mischief-1/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.01, + "output_cost_per_second_480p": 0.005, + "output_cost_per_second_720p": 0.01, + "source": "https://fal.ai/models/tbc/mischief-1/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/veed/fabric-1.0": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p)"}, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "output_cost_per_second_480p": 0.08, + "output_cost_per_second_720p": 0.15, + "source": "https://fal.ai/models/veed/fabric-1.0", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/veed/fabric-1.0/fast": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p)"}, + "mode": "video_generation", + "output_cost_per_second": 0.2, + "output_cost_per_second_480p": 0.1, + "output_cost_per_second_720p": 0.2, + "source": "https://fal.ai/models/veed/fabric-1.0/fast", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/veed/fabric-1.0/text": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p)"}, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "output_cost_per_second_480p": 0.08, + "output_cost_per_second_720p": 0.15, + "source": "https://fal.ai/models/veed/fabric-1.0/text", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/wan/v2.6/image-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://fal.ai/models/wan/v2.6/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/wan/v2.6/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/wan/v2.6/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/wan/v2.6/image-to-video/flash": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.075, + "output_cost_per_second_1080p": 0.075, + "output_cost_per_second_720p": 0.05, + "source": "https://fal.ai/models/wan/v2.6/image-to-video/flash", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/wan/v2.6/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/wan/v2.6/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/wan/v2.6/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://fal.ai/models/wan/v2.6/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/wan/v2.6/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/wan/v2.6/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/xai/grok-imagine-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://fal.ai/models/xai/grok-imagine-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/xai/grok-imagine-video/v1.5/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.14, + "output_cost_per_second_1080p": 0.25, + "output_cost_per_second_480p": 0.08, + "output_cost_per_second_720p": 0.14, + "source": "https://fal.ai/models/xai/grok-imagine-video/v1.5/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/alibaba/happy-horse/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.28, + "output_cost_per_second_1080p": 0.28, + "output_cost_per_second_720p": 0.14, + "source": "https://fal.ai/models/alibaba/happy-horse/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/creatify/boreal": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.01, + "output_cost_per_second_1080p": 0.03, + "output_cost_per_second_2k": 0.12, + "output_cost_per_second_720p": 0.01, + "source": "https://fal.ai/models/creatify/boreal", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/creatify/aurora": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.14, + "output_cost_per_second_480p": 0.07, + "output_cost_per_second_720p": 0.14, + "source": "https://fal.ai/models/fal-ai/creatify/aurora", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/vidu/q4/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; tiers without a catalog field: 540p $0.0315"}, + "mode": "video_generation", + "output_cost_per_second": 0.0665, + "output_cost_per_second_1080p": 0.084, + "output_cost_per_second_2k": 0.133, + "output_cost_per_second_4k": 0.273, + "output_cost_per_second_720p": 0.0665, + "source": "https://fal.ai/models/fal-ai/vidu/q4/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/vidu/q4/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; tiers without a catalog field: 540p $0.0315"}, + "mode": "video_generation", + "output_cost_per_second": 0.0665, + "output_cost_per_second_1080p": 0.084, + "output_cost_per_second_2k": 0.133, + "output_cost_per_second_4k": 0.273, + "output_cost_per_second_720p": 0.0665, + "source": "https://fal.ai/models/fal-ai/vidu/q4/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/ideogram/v4.5": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://fal.ai/models/ideogram/v4.5", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/ideogram/v4.5/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://fal.ai/models/ideogram/v4.5/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/ideogram/v4/instant": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills ideogram/v4/instant at $0.0075 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.0075, + "output_cost_per_pixel": 7.152557373046875e-09, + "source": "https://fal.ai/models/ideogram/v4/instant", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/lightricks/ltx-2.5/image-to-video/fast": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate; tiers without a catalog field: 1440p $0.19"}, + "mode": "video_generation", + "output_cost_per_second": 0.13, + "output_cost_per_second_1080p": 0.13, + "output_cost_per_second_4k": 0.3, + "output_cost_per_second_720p": 0.09, + "source": "https://fal.ai/models/lightricks/ltx-2.5/image-to-video/fast", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/lightricks/ltx-2.5/image-to-video/pro": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.17, + "output_cost_per_second_1080p": 0.17, + "output_cost_per_second_720p": 0.12, + "source": "https://fal.ai/models/lightricks/ltx-2.5/image-to-video/pro", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/lightricks/ltx-2.5/text-to-video/fast": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate; tiers without a catalog field: 1440p $0.19"}, + "mode": "video_generation", + "output_cost_per_second": 0.13, + "output_cost_per_second_1080p": 0.13, + "output_cost_per_second_4k": 0.3, + "output_cost_per_second_720p": 0.09, + "source": "https://fal.ai/models/lightricks/ltx-2.5/text-to-video/fast", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/lightricks/ltx-2.5/text-to-video/pro": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.17, + "output_cost_per_second_1080p": 0.17, + "output_cost_per_second_720p": 0.12, + "source": "https://fal.ai/models/lightricks/ltx-2.5/text-to-video/pro", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max/recast": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.45, + "output_cost_per_second_1080p": 0.45, + "output_cost_per_second_768p": 0.3, + "source": "https://fal.ai/models/minimax/h3-max/recast", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max/reframe-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_768p": 0.08, + "source": "https://fal.ai/models/minimax/h3-max/reframe-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max/relight": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_1080p": 0.16, + "output_cost_per_second_2k": 0.32, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_768p": 0.08, + "source": "https://fal.ai/models/minimax/h3-max/relight", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/wan/v2.6/reference-to-video/flash": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/wan/v2.6/reference-to-video/flash", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/xai/grok-imagine-video/v1.5/lite/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.03, + "output_cost_per_second_1080p": 0.14, + "output_cost_per_second_480p": 0.02, + "output_cost_per_second_720p": 0.03, + "source": "https://fal.ai/models/xai/grok-imagine-video/v1.5/lite/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/xai/grok-imagine-video/v1.5/lite/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.03, + "output_cost_per_second_1080p": 0.14, + "output_cost_per_second_480p": 0.02, + "output_cost_per_second_720p": 0.03, + "source": "https://fal.ai/models/xai/grok-imagine-video/v1.5/lite/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/blackforestlabs/flux-3-max/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; promotional 50% off rate through 2026-11-22 23:59 UTC per the page; regular rates $0.17 (720p) and $0.29 (1080p) per second resume 2026-11-23 00:00 UTC (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, + "mode": "video_generation", + "output_cost_per_second": 0.085, + "output_cost_per_second_1080p": 0.145, + "output_cost_per_second_720p": 0.085, + "source": "https://fal.ai/models/blackforestlabs/flux-3-max/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/blackforestlabs/flux-3-max/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; promotional 50% off rate through 2026-11-22 23:59 UTC per the page; regular rates $0.17 (720p) and $0.29 (1080p) per second resume 2026-11-23 00:00 UTC (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, + "mode": "video_generation", + "output_cost_per_second": 0.085, + "output_cost_per_second_1080p": 0.145, + "output_cost_per_second_720p": 0.085, + "source": "https://fal.ai/models/blackforestlabs/flux-3-max/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/blackforestlabs/flux-3-max/keyframes-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; regular rate; the page's 75% promotion ran October 15 to November 7, 2026 and has ended (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, + "mode": "video_generation", + "output_cost_per_second": 0.17, + "output_cost_per_second_1080p": 0.29, + "output_cost_per_second_720p": 0.17, + "source": "https://fal.ai/models/blackforestlabs/flux-3-max/keyframes-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/heygen/heygen-video/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate; regular rate; the page's 50% promotion ended October 31, 2026 (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, + "mode": "video_generation", + "output_cost_per_second": 0.02, + "output_cost_per_second_1080p": 0.06, + "output_cost_per_second_2k": 0.06, + "output_cost_per_second_480p": 0.02, + "output_cost_per_second_768p": 0.02, + "source": "https://fal.ai/models/heygen/heygen-video/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/heygen/heygen-video/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate; regular rate; the page's 50% promotion ended October 31, 2026 (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, + "mode": "video_generation", + "output_cost_per_second": 0.02, + "output_cost_per_second_1080p": 0.06, + "output_cost_per_second_2k": 0.06, + "output_cost_per_second_480p": 0.02, + "output_cost_per_second_768p": 0.02, + "source": "https://fal.ai/models/heygen/heygen-video/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/heygen/heygen-video/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate; regular rate; the page's 50% promotion ended October 31, 2026 (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, + "mode": "video_generation", + "output_cost_per_second": 0.02, + "output_cost_per_second_1080p": 0.06, + "output_cost_per_second_2k": 0.06, + "output_cost_per_second_480p": 0.02, + "output_cost_per_second_768p": 0.02, + "source": "https://fal.ai/models/heygen/heygen-video/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max-turbo/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate; promotional 30% off rate through 2026-11-15 per the page; standard rates $0.025 (480p), $0.04 (768p), $0.08 (1080p) per second from 2026-11-16 (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, + "mode": "video_generation", + "output_cost_per_second": 0.028, + "output_cost_per_second_1080p": 0.056, + "output_cost_per_second_480p": 0.0175, + "output_cost_per_second_768p": 0.028, + "source": "https://fal.ai/models/minimax/h3-max-turbo/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max-turbo/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate; promotional 30% off rate through 2026-11-15 per the page; standard rates $0.025 (480p), $0.04 (768p), $0.08 (1080p) per second from 2026-11-16 (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, + "mode": "video_generation", + "output_cost_per_second": 0.028, + "output_cost_per_second_1080p": 0.056, + "output_cost_per_second_480p": 0.0175, + "output_cost_per_second_768p": 0.028, + "source": "https://fal.ai/models/minimax/h3-max-turbo/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max/camera-controls": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 480p rate; promotional 30% off rate through 2026-11-15 per the page; standard rates $0.05 (480p), $0.08 (768p), $0.16 (1080p) per second from 2026-11-16 (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, + "mode": "video_generation", + "output_cost_per_second": 0.035, + "output_cost_per_second_1080p": 0.112, + "output_cost_per_second_480p": 0.035, + "output_cost_per_second_768p": 0.056, + "source": "https://fal.ai/models/minimax/h3-max/camera-controls", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate; promotional 30% off rate through 2026-11-15 per the page; standard rates $0.05 (480p), $0.08 (768p), $0.16 (1080p) per second from 2026-11-16 (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, + "mode": "video_generation", + "output_cost_per_second": 0.056, + "output_cost_per_second_1080p": 0.112, + "output_cost_per_second_480p": 0.035, + "output_cost_per_second_768p": 0.056, + "source": "https://fal.ai/models/minimax/h3-max/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate; promotional 30% off rate through 2026-11-15 per the page; standard rates $0.05 (480p), $0.08 (768p), $0.16 (1080p) per second from 2026-11-16 (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, + "mode": "video_generation", + "output_cost_per_second": 0.056, + "output_cost_per_second_1080p": 0.112, + "output_cost_per_second_480p": 0.035, + "output_cost_per_second_768p": 0.056, + "source": "https://fal.ai/models/minimax/h3-max/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "replicate/alibaba/happyhorse-1.0": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.28, + "output_cost_per_second_1080p": 0.28, + "output_cost_per_second_720p": 0.14, + "source": "https://replicate.com/alibaba/happyhorse-1.0" + }, + "replicate/alibaba/happyhorse-1.1": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.18, + "output_cost_per_second_1080p": 0.18, + "output_cost_per_second_720p": 0.14, + "source": "https://replicate.com/alibaba/happyhorse-1.1" + }, + "replicate/alibaba/qwen-image-3": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/alibaba/qwen-image-3" + }, + "replicate/alibaba/qwen-image-3-pro": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/alibaba/qwen-image-3-pro" + }, + "replicate/alibaba/wan-3": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.14, + "output_cost_per_second_1080p": 0.14, + "output_cost_per_second_480p": 0.035, + "output_cost_per_second_720p": 0.07, + "source": "https://replicate.com/alibaba/wan-3" + }, + "replicate/alibaba/wan-3-prime": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.28, + "output_cost_per_second_1080p": 0.28, + "output_cost_per_second_480p": 0.068, + "output_cost_per_second_720p": 0.14, + "source": "https://replicate.com/alibaba/wan-3-prime" + }, + "replicate/anthropic/claude-fable-5": { + "input_cost_per_token": 1e-05, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 5e-05, + "source": "https://replicate.com/anthropic/claude-fable-5", + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/anthropic/claude-fable-5.2": { + "input_cost_per_token": 8e-06, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 4e-05, + "source": "https://replicate.com/anthropic/claude-fable-5.2", + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/anthropic/claude-opus-4.6": { + "input_cost_per_token": 5e-06, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://replicate.com/anthropic/claude-opus-4.6", + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/anthropic/claude-opus-4.7": { + "input_cost_per_token": 5e-06, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://replicate.com/anthropic/claude-opus-4.7", + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/anthropic/claude-opus-5.5": { + "input_cost_per_token": 4e-06, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2e-05, + "source": "https://replicate.com/anthropic/claude-opus-5.5", + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/anthropic/claude-sonnet-4.6": { + "input_cost_per_token": 3e-06, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://replicate.com/anthropic/claude-sonnet-4.6", + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/anthropic/claude-sonnet-5": { + "input_cost_per_token": 2e-06, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://replicate.com/anthropic/claude-sonnet-5", + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/black-forest-labs/flux-1.1-pro": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/black-forest-labs/flux-1.1-pro" + }, + "replicate/black-forest-labs/flux-1.1-pro-ultra": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://replicate.com/black-forest-labs/flux-1.1-pro-ultra" + }, + "replicate/black-forest-labs/flux-1.1-pro-ultra-finetuned": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.07, + "source": "https://replicate.com/black-forest-labs/flux-1.1-pro-ultra-finetuned" + }, + "replicate/black-forest-labs/flux-2-flex": { + "input_cost_per_pixel": 6e-08, + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_pixel": 6e-08, + "source": "https://replicate.com/black-forest-labs/flux-2-flex" + }, + "replicate/black-forest-labs/flux-2-klein-4b": { + "input_cost_per_pixel": 1e-09, + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_pixel": 1e-09, + "source": "https://replicate.com/black-forest-labs/flux-2-klein-4b" + }, + "replicate/black-forest-labs/flux-2-klein-4b-base": { + "input_cost_per_pixel": 9e-09, + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_pixel": 9e-09, + "source": "https://replicate.com/black-forest-labs/flux-2-klein-4b-base" + }, + "replicate/black-forest-labs/flux-2-klein-4b-base-lora": { + "input_cost_per_pixel": 9e-09, + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_pixel": 1.9e-08, + "source": "https://replicate.com/black-forest-labs/flux-2-klein-4b-base-lora" + }, + "replicate/black-forest-labs/flux-2-klein-9b": { + "input_cost_per_pixel": 2e-09, + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_pixel": 1.5e-08, + "source": "https://replicate.com/black-forest-labs/flux-2-klein-9b" + }, + "replicate/black-forest-labs/flux-2-klein-9b-base": { + "input_cost_per_pixel": 1.1e-08, + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_pixel": 1.1e-08, + "source": "https://replicate.com/black-forest-labs/flux-2-klein-9b-base" + }, + "replicate/black-forest-labs/flux-2-klein-9b-base-lora": { + "input_cost_per_pixel": 1.1e-08, + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_pixel": 2.1e-08, + "source": "https://replicate.com/black-forest-labs/flux-2-klein-9b-base-lora" + }, + "replicate/black-forest-labs/flux-canny-dev": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.025, + "source": "https://replicate.com/black-forest-labs/flux-canny-dev" + }, + "replicate/black-forest-labs/flux-canny-pro": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://replicate.com/black-forest-labs/flux-canny-pro" + }, + "replicate/black-forest-labs/flux-depth-dev": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.025, + "source": "https://replicate.com/black-forest-labs/flux-depth-dev" + }, + "replicate/black-forest-labs/flux-depth-pro": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://replicate.com/black-forest-labs/flux-depth-pro" + }, + "replicate/black-forest-labs/flux-dev": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.025, + "source": "https://replicate.com/black-forest-labs/flux-dev" + }, + "replicate/black-forest-labs/flux-dev-lora": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.032, + "source": "https://replicate.com/black-forest-labs/flux-dev-lora" + }, + "replicate/black-forest-labs/flux-fill-dev": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/black-forest-labs/flux-fill-dev" + }, + "replicate/black-forest-labs/flux-fill-pro": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://replicate.com/black-forest-labs/flux-fill-pro" + }, + "replicate/black-forest-labs/flux-kontext-dev": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.025, + "source": "https://replicate.com/black-forest-labs/flux-kontext-dev" + }, + "replicate/black-forest-labs/flux-kontext-dev-lora": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.032, + "source": "https://replicate.com/black-forest-labs/flux-kontext-dev-lora" + }, + "replicate/black-forest-labs/flux-kontext-max": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://replicate.com/black-forest-labs/flux-kontext-max" + }, + "replicate/black-forest-labs/flux-kontext-pro": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/black-forest-labs/flux-kontext-pro" + }, + "replicate/black-forest-labs/flux-krea-dev": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.025, + "source": "https://replicate.com/black-forest-labs/flux-krea-dev" + }, + "replicate/black-forest-labs/flux-pro": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.055, + "source": "https://replicate.com/black-forest-labs/flux-pro" + }, + "replicate/black-forest-labs/flux-pro-finetuned": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://replicate.com/black-forest-labs/flux-pro-finetuned" + }, + "replicate/black-forest-labs/flux-redux-dev": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.025, + "source": "https://replicate.com/black-forest-labs/flux-redux-dev" + }, + "replicate/black-forest-labs/flux-redux-schnell": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.003, + "source": "https://replicate.com/black-forest-labs/flux-redux-schnell" + }, + "replicate/black-forest-labs/flux-schnell": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.003, + "source": "https://replicate.com/black-forest-labs/flux-schnell" + }, + "replicate/black-forest-labs/flux-schnell-lora": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://replicate.com/black-forest-labs/flux-schnell-lora" + }, + "replicate/bria/eraser": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/bria/eraser" + }, + "replicate/bria/expand-image": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/bria/expand-image" + }, + "replicate/bria/fibo": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/bria/fibo" + }, + "replicate/bria/fibo-edit": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/bria/fibo-edit" + }, + "replicate/bria/generate-background": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/bria/generate-background" + }, + "replicate/bria/genfill": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/bria/genfill" + }, + "replicate/bria/image-3.2": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/bria/image-3.2" + }, + "replicate/bria/increase-resolution": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/bria/increase-resolution" + }, + "replicate/bria/product-cutout": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/bria/product-cutout" + }, + "replicate/bria/product-packshot": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/bria/product-packshot" + }, + "replicate/bria/product-shadow": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/bria/product-shadow" + }, + "replicate/bria/remove-background": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.018, + "source": "https://replicate.com/bria/remove-background" + }, + "replicate/bria/video-erase-object": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://replicate.com/bria/video-erase-object" + }, + "replicate/bria/video-increase-resolution": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://replicate.com/bria/video-increase-resolution" + }, + "replicate/bria/video-remove-background": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://replicate.com/bria/video-remove-background" + }, + "replicate/bytedance/dreamactor-m2.0": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://replicate.com/bytedance/dreamactor-m2.0" + }, + "replicate/bytedance/dreamina-3.1": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/bytedance/dreamina-3.1" + }, + "replicate/bytedance/omni-human": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.14, + "source": "https://replicate.com/bytedance/omni-human" + }, + "replicate/bytedance/omni-human-1.5": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.16, + "source": "https://replicate.com/bytedance/omni-human-1.5" + }, + "replicate/bytedance/seedance-1-lite": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.036, + "output_cost_per_second_1080p": 0.072, + "output_cost_per_second_480p": 0.018, + "output_cost_per_second_720p": 0.036, + "source": "https://replicate.com/bytedance/seedance-1-lite" + }, + "replicate/bytedance/seedance-1-pro": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.15, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_480p": 0.03, + "output_cost_per_second_720p": 0.06, + "source": "https://replicate.com/bytedance/seedance-1-pro" + }, + "replicate/bytedance/seedance-1-pro-fast": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.06, + "output_cost_per_second_1080p": 0.06, + "output_cost_per_second_480p": 0.015, + "output_cost_per_second_720p": 0.025, + "source": "https://replicate.com/bytedance/seedance-1-pro-fast" + }, + "replicate/bytedance/seedream-3": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/bytedance/seedream-3" + }, + "replicate/bytedance/seedream-4": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/bytedance/seedream-4" + }, + "replicate/bytedance/seedream-4.5": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/bytedance/seedream-4.5" + }, + "replicate/bytedance/seedream-5-lite": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.035, + "source": "https://replicate.com/bytedance/seedream-5-lite" + }, + "replicate/datalab-to/ocr": { + "litellm_provider": "replicate", + "mode": "ocr", + "ocr_cost_per_page": 0.002, + "source": "https://replicate.com/datalab-to/ocr" + }, + "replicate/decart/lucy-edit-2": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.04, + "source": "https://replicate.com/decart/lucy-edit-2" + }, + "replicate/easel/ai-avatars": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://replicate.com/easel/ai-avatars" + }, + "replicate/elevenlabs/dubbing": { + "litellm_provider": "replicate", + "mode": "audio_speech", + "output_cost_per_second": 0.0366667, + "source": "https://replicate.com/elevenlabs/dubbing" + }, + "replicate/elevenlabs/flash-v2.5": { + "input_cost_per_character": 5e-05, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/elevenlabs/flash-v2.5" + }, + "replicate/elevenlabs/turbo-v2.5": { + "input_cost_per_character": 5e-05, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/elevenlabs/turbo-v2.5" + }, + "replicate/elevenlabs/v2-multilingual": { + "input_cost_per_character": 0.0001, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/elevenlabs/v2-multilingual" + }, + "replicate/elevenlabs/v3": { + "input_cost_per_character": 0.0001, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/elevenlabs/v3" + }, + "replicate/flux-kontext-apps/cartoonify": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/flux-kontext-apps/cartoonify" + }, + "replicate/flux-kontext-apps/change-haircut": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/flux-kontext-apps/change-haircut" + }, + "replicate/flux-kontext-apps/depth-of-field": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/flux-kontext-apps/depth-of-field" + }, + "replicate/flux-kontext-apps/face-to-many-kontext": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/flux-kontext-apps/face-to-many-kontext" + }, + "replicate/flux-kontext-apps/filters": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/flux-kontext-apps/filters" + }, + "replicate/flux-kontext-apps/iconic-locations": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/flux-kontext-apps/iconic-locations" + }, + "replicate/flux-kontext-apps/impossible-scenarios": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/flux-kontext-apps/impossible-scenarios" + }, + "replicate/flux-kontext-apps/multi-image-kontext-max": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://replicate.com/flux-kontext-apps/multi-image-kontext-max" + }, + "replicate/flux-kontext-apps/multi-image-kontext-pro": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/flux-kontext-apps/multi-image-kontext-pro" + }, + "replicate/flux-kontext-apps/multi-image-list": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://replicate.com/flux-kontext-apps/multi-image-list" + }, + "replicate/flux-kontext-apps/portrait-series": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/flux-kontext-apps/portrait-series" + }, + "replicate/flux-kontext-apps/professional-headshot": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/flux-kontext-apps/professional-headshot" + }, + "replicate/flux-kontext-apps/restore-image": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/flux-kontext-apps/restore-image" + }, + "replicate/flux-kontext-apps/restyle-video-frame": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/flux-kontext-apps/restyle-video-frame" + }, + "replicate/flux-kontext-apps/text-removal": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/flux-kontext-apps/text-removal" + }, + "replicate/google/gemini-2.5-flash-image": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.039, + "source": "https://replicate.com/google/gemini-2.5-flash-image" + }, + "replicate/google/gemini-3-flash": { + "input_cost_per_token": 5e-07, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://replicate.com/google/gemini-3-flash", + "supports_reasoning": true, + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/google/gemini-3.1-flash-tts": { + "input_cost_per_token": 2e-06, + "litellm_provider": "replicate", + "mode": "audio_speech", + "output_cost_per_token": 4e-05, + "source": "https://replicate.com/google/gemini-3.1-flash-tts" + }, + "replicate/google/gemini-3.1-pro": { + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_200k_tokens": 1.8e-05, + "source": "https://replicate.com/google/gemini-3.1-pro", + "supports_reasoning": true, + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/google/gemini-3.5-flash": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 9e-06, + "source": "https://replicate.com/google/gemini-3.5-flash", + "supports_reasoning": true, + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/google/gemini-3.8-flash-lite-tts": { + "input_cost_per_token": 5e-07, + "litellm_provider": "replicate", + "mode": "audio_speech", + "output_cost_per_token": 6e-06, + "source": "https://replicate.com/google/gemini-3.8-flash-lite-tts" + }, + "replicate/google/gemini-3.8-flash-tts": { + "input_cost_per_token": 5e-07, + "litellm_provider": "replicate", + "mode": "audio_speech", + "output_cost_per_token": 9e-06, + "source": "https://replicate.com/google/gemini-3.8-flash-tts" + }, + "replicate/google/nano-banana": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.039, + "source": "https://replicate.com/google/nano-banana" + }, + "replicate/google/nano-banana-2": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.067, + "output_cost_per_image_1K": 0.067, + "output_cost_per_image_2K": 0.101, + "output_cost_per_image_4K": 0.151, + "source": "https://replicate.com/google/nano-banana-2" + }, + "replicate/google/nano-banana-2-lite": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.034, + "source": "https://replicate.com/google/nano-banana-2-lite" + }, + "replicate/google/nano-banana-2.1": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.0336, + "output_cost_per_image_1K": 0.0336, + "output_cost_per_image_2K": 0.0504, + "output_cost_per_image_4K": 0.1134, + "source": "https://replicate.com/google/nano-banana-2.1" + }, + "replicate/heygen/avatar-iv": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.075, + "source": "https://replicate.com/heygen/avatar-iv" + }, + "replicate/heygen/avatar-v": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.075, + "source": "https://replicate.com/heygen/avatar-v" + }, + "replicate/heygen/lipsync-precision": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.0667, + "source": "https://replicate.com/heygen/lipsync-precision" + }, + "replicate/heygen/lipsync-speed": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.0333, + "source": "https://replicate.com/heygen/lipsync-speed" + }, + "replicate/heygen/video-agent": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.0333, + "source": "https://replicate.com/heygen/video-agent" + }, + "replicate/ibm-granite/granite-20b-code-instruct-8k": { + "input_cost_per_token": 1e-07, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://replicate.com/ibm-granite/granite-20b-code-instruct-8k", + "supports_system_messages": true + }, + "replicate/ibm-granite/granite-3.0-2b-instruct": { + "input_cost_per_token": 3e-08, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/ibm-granite/granite-3.0-2b-instruct", + "supports_system_messages": true + }, + "replicate/ibm-granite/granite-3.0-8b-instruct": { + "input_cost_per_token": 5e-08, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/ibm-granite/granite-3.0-8b-instruct", + "supports_system_messages": true + }, + "replicate/ibm-granite/granite-3.1-2b-instruct": { + "input_cost_per_token": 3e-08, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/ibm-granite/granite-3.1-2b-instruct", + "supports_system_messages": true + }, + "replicate/ibm-granite/granite-3.1-8b-instruct": { + "input_cost_per_token": 3e-08, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/ibm-granite/granite-3.1-8b-instruct", + "supports_system_messages": true + }, + "replicate/ibm-granite/granite-3.2-8b-instruct": { + "input_cost_per_token": 3e-08, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/ibm-granite/granite-3.2-8b-instruct", + "supports_system_messages": true + }, + "replicate/ibm-granite/granite-4.0-h-small": { + "input_cost_per_token": 6e-08, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/ibm-granite/granite-4.0-h-small", + "supports_function_calling": true, + "supports_system_messages": true + }, + "replicate/ibm-granite/granite-4.1-8b": { + "input_cost_per_token": 6e-08, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/ibm-granite/granite-4.1-8b", + "supports_function_calling": true, + "supports_system_messages": true + }, + "replicate/ibm-granite/granite-4.2-8b": { + "input_cost_per_token": 6e-08, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/ibm-granite/granite-4.2-8b", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true + }, + "replicate/ibm-granite/granite-8b-code-instruct-128k": { + "input_cost_per_token": 5e-08, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/ibm-granite/granite-8b-code-instruct-128k", + "supports_system_messages": true + }, + "replicate/ibm-granite/granite-speech-3.3-8b": { + "litellm_provider": "replicate", + "mode": "audio_transcription", + "output_cost_per_token": 4.9e-06, + "source": "https://replicate.com/ibm-granite/granite-speech-3.3-8b" + }, + "replicate/ibm-granite/granite-speech-4.1-2b": { + "input_cost_per_token": 3e-08, + "litellm_provider": "replicate", + "mode": "audio_transcription", + "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/ibm-granite/granite-speech-4.1-2b" + }, + "replicate/ibm-granite/granite-vision-3.3-2b": { + "input_cost_per_token": 0.0, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/ibm-granite/granite-vision-3.3-2b", + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/ibm-granite/granite-vision-4.1-4b": { + "input_cost_per_token": 6e-08, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/ibm-granite/granite-vision-4.1-4b", + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/ideogram-ai/ideogram-v2": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://replicate.com/ideogram-ai/ideogram-v2" + }, + "replicate/ideogram-ai/ideogram-v2-turbo": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://replicate.com/ideogram-ai/ideogram-v2-turbo" + }, + "replicate/ideogram-ai/ideogram-v2a": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/ideogram-ai/ideogram-v2a" + }, + "replicate/ideogram-ai/ideogram-v2a-turbo": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.025, + "source": "https://replicate.com/ideogram-ai/ideogram-v2a-turbo" + }, + "replicate/ideogram-ai/ideogram-v3-balanced": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://replicate.com/ideogram-ai/ideogram-v3-balanced" + }, + "replicate/ideogram-ai/ideogram-v3-quality": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.09, + "source": "https://replicate.com/ideogram-ai/ideogram-v3-quality" + }, + "replicate/ideogram-ai/ideogram-v3-turbo": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/ideogram-ai/ideogram-v3-turbo" + }, + "replicate/ideogram-ai/ideogram-v4-balanced": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://replicate.com/ideogram-ai/ideogram-v4-balanced" + }, + "replicate/ideogram-ai/ideogram-v4-quality": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.1, + "source": "https://replicate.com/ideogram-ai/ideogram-v4-quality" + }, + "replicate/ideogram-ai/layerize": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.09, + "source": "https://replicate.com/ideogram-ai/layerize" + }, + "replicate/intelligent-utilities/html-to-image": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.001, + "source": "https://replicate.com/intelligent-utilities/html-to-image" + }, + "replicate/inworld/realtime-tts-1.5-max": { + "input_cost_per_character": 3.5e-05, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/inworld/realtime-tts-1.5-max" + }, + "replicate/inworld/realtime-tts-1.5-mini": { + "input_cost_per_character": 1.5e-05, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/inworld/realtime-tts-1.5-mini" + }, + "replicate/inworld/realtime-tts-2": { + "input_cost_per_character": 2.5e-05, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/inworld/realtime-tts-2" + }, + "replicate/kwaivgi/kling-lip-sync": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.014, + "source": "https://replicate.com/kwaivgi/kling-lip-sync" + }, + "replicate/kwaivgi/kling-v2.1-master": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.28, + "source": "https://replicate.com/kwaivgi/kling-v2.1-master" + }, + "replicate/kwaivgi/kling-v2.5-turbo-pro": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.07, + "source": "https://replicate.com/kwaivgi/kling-v2.5-turbo-pro" + }, + "replicate/lightricks/audio-to-video": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://replicate.com/lightricks/audio-to-video" + }, + "replicate/lightricks/ltx-2-distilled": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.02, + "source": "https://replicate.com/lightricks/ltx-2-distilled" + }, + "replicate/lightricks/ltx-2-fast": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.04, + "output_cost_per_second_1080p": 0.04, + "output_cost_per_second_2k": 0.08, + "output_cost_per_second_4k": 0.16, + "source": "https://replicate.com/lightricks/ltx-2-fast" + }, + "replicate/lightricks/ltx-2-pro": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.06, + "output_cost_per_second_1080p": 0.06, + "output_cost_per_second_2k": 0.12, + "output_cost_per_second_4k": 0.24, + "source": "https://replicate.com/lightricks/ltx-2-pro" + }, + "replicate/lightricks/ltx-2-retake": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://replicate.com/lightricks/ltx-2-retake" + }, + "replicate/lightricks/ltx-2.3-fast": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.06, + "output_cost_per_second_1080p": 0.06, + "output_cost_per_second_2k": 0.12, + "output_cost_per_second_4k": 0.24, + "source": "https://replicate.com/lightricks/ltx-2.3-fast" + }, + "replicate/lightricks/ltx-2.3-pro": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_1080p": 0.08, + "output_cost_per_second_2k": 0.16, + "output_cost_per_second_4k": 0.32, + "source": "https://replicate.com/lightricks/ltx-2.3-pro" + }, + "replicate/lightricks/ltx-2.5-fast": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.06, + "output_cost_per_second_1080p": 0.06, + "output_cost_per_second_2k": 0.12, + "output_cost_per_second_4k": 0.24, + "output_cost_per_second_720p": 0.03, + "source": "https://replicate.com/lightricks/ltx-2.5-fast" + }, + "replicate/luma/photon": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/luma/photon" + }, + "replicate/luma/photon-flash": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://replicate.com/luma/photon-flash" + }, + "replicate/luma/reframe-video": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.06, + "source": "https://replicate.com/luma/reframe-video" + }, + "replicate/meta/llama-4-maverick-instruct": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 9.5e-07, + "source": "https://replicate.com/meta/llama-4-maverick-instruct", + "supports_system_messages": true + }, + "replicate/meta/llama-4-scout-instruct": { + "input_cost_per_token": 1.7e-07, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 6.5e-07, + "source": "https://replicate.com/meta/llama-4-scout-instruct", + "supports_system_messages": true + }, + "replicate/meta/llama-guard-4-12b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://replicate.com/meta/llama-guard-4-12b", + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/meta/meta-llama-3-70b": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.75e-06, + "source": "https://replicate.com/meta/meta-llama-3-70b" + }, + "replicate/meta/meta-llama-3-70b-instruct": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.75e-06, + "source": "https://replicate.com/meta/meta-llama-3-70b-instruct", + "supports_system_messages": true + }, + "replicate/meta/meta-llama-3-8b": { + "input_cost_per_token": 5e-08, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/meta/meta-llama-3-8b" + }, + "replicate/meta/meta-llama-3-8b-instruct": { + "input_cost_per_token": 5e-08, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/meta/meta-llama-3-8b-instruct", + "supports_system_messages": true + }, + "replicate/minimax/h3": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.13, + "output_cost_per_second_2k": 0.13, + "output_cost_per_second_768p": 0.08, + "source": "https://replicate.com/minimax/h3" + }, + "replicate/minimax/h3-highspeed": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.03, + "source": "https://replicate.com/minimax/h3-highspeed" + }, + "replicate/minimax/h3-lite": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.02, + "output_cost_per_second_480p": 0.0125, + "output_cost_per_second_768p": 0.02, + "source": "https://replicate.com/minimax/h3-lite" + }, + "replicate/minimax/image-01": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://replicate.com/minimax/image-01" + }, + "replicate/minimax/speech-02-hd": { + "input_cost_per_token": 0.0001, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/minimax/speech-02-hd" + }, + "replicate/minimax/speech-02-turbo": { + "input_cost_per_token": 6e-05, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/minimax/speech-02-turbo" + }, + "replicate/minimax/speech-2.6-hd": { + "input_cost_per_token": 0.0001, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/minimax/speech-2.6-hd" + }, + "replicate/minimax/speech-2.6-turbo": { + "input_cost_per_token": 6e-05, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/minimax/speech-2.6-turbo" + }, + "replicate/minimax/speech-2.8-hd": { + "input_cost_per_token": 0.0001, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/minimax/speech-2.8-hd" + }, + "replicate/minimax/speech-2.8-turbo": { + "input_cost_per_token": 6e-05, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/minimax/speech-2.8-turbo" + }, + "replicate/moonshotai/kimi-k2-thinking": { + "input_cost_per_token": 6.6e-07, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.7e-06, + "source": "https://replicate.com/moonshotai/kimi-k2-thinking" + }, + "replicate/moonshotai/kimi-k2.5": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 3.6e-06, + "source": "https://replicate.com/moonshotai/kimi-k2.5", + "supports_vision": true + }, + "replicate/moonshotai/kimi-k2.6": { + "input_cost_per_token": 9.5e-07, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://replicate.com/moonshotai/kimi-k2.6", + "supports_reasoning": true, + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/nightmareai/real-esrgan": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.002, + "source": "https://replicate.com/nightmareai/real-esrgan" + }, + "replicate/openai/gpt-4o-mini-transcribe": { + "input_cost_per_token": 3e-06, + "litellm_provider": "replicate", + "mode": "audio_transcription", + "output_cost_per_token": 5e-06, + "source": "https://replicate.com/openai/gpt-4o-mini-transcribe" + }, + "replicate/openai/gpt-4o-transcribe": { + "input_cost_per_token": 6e-06, + "litellm_provider": "replicate", + "mode": "audio_transcription", + "output_cost_per_token": 1e-05, + "source": "https://replicate.com/openai/gpt-4o-transcribe" + }, + "replicate/openai/gpt-5-pro": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 0.00012, + "source": "https://replicate.com/openai/gpt-5-pro", + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/openai/gpt-5.1": { + "input_cost_per_token": 1.25e-06, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://replicate.com/openai/gpt-5.1", + "supports_reasoning": true, + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/openai/gpt-5.2": { + "input_cost_per_token": 1.75e-06, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 1.4e-05, + "source": "https://replicate.com/openai/gpt-5.2", + "supports_reasoning": true, + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/openai/gpt-5.4": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://replicate.com/openai/gpt-5.4", + "supports_reasoning": true, + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/openai/gpt-5.6-luna": { + "input_cost_per_token": 1e-06, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://replicate.com/openai/gpt-5.6-luna", + "supports_reasoning": true, + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/openai/gpt-5.6-sol": { + "input_cost_per_token": 2e-06, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://replicate.com/openai/gpt-5.6-sol", + "supports_reasoning": true, + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/openai/gpt-5.6-terra": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://replicate.com/openai/gpt-5.6-terra", + "supports_reasoning": true, + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/perceptron-ai-inc/isaac-0.1": { + "input_cost_per_token": 2.6e-07, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.17e-06, + "source": "https://replicate.com/perceptron-ai-inc/isaac-0.1", + "supports_vision": true + }, + "replicate/philz1337x/clarity-pro-upscaler": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_pixel": 3e-08, + "source": "https://replicate.com/philz1337x/clarity-pro-upscaler" + }, + "replicate/pixverse/lipsync": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.04, + "source": "https://replicate.com/pixverse/lipsync" + }, + "replicate/playht/play-dialog": { + "litellm_provider": "replicate", + "mode": "audio_speech", + "output_cost_per_second": 0.001, + "source": "https://replicate.com/playht/play-dialog" + }, + "replicate/prunaai/flux-fast": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.005, + "source": "https://replicate.com/prunaai/flux-fast" + }, + "replicate/prunaai/flux-kontext-fast": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://replicate.com/prunaai/flux-kontext-fast" + }, + "replicate/prunaai/hidream-l1-fast": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.005, + "source": "https://replicate.com/prunaai/hidream-l1-fast" + }, + "replicate/prunaai/p-image": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.005, + "source": "https://replicate.com/prunaai/p-image" + }, + "replicate/prunaai/p-image-edit": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://replicate.com/prunaai/p-image-edit" + }, + "replicate/prunaai/p-image-edit-lora": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://replicate.com/prunaai/p-image-edit-lora" + }, + "replicate/prunaai/p-image-lora": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.005, + "source": "https://replicate.com/prunaai/p-image-lora" + }, + "replicate/prunaai/p-video-2-pro-avatar": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.04, + "output_cost_per_second_1080p": 0.06, + "output_cost_per_second_2k": 0.08, + "output_cost_per_second_480p": 0.02, + "output_cost_per_second_4k": 0.12, + "output_cost_per_second_768p": 0.04, + "source": "https://replicate.com/prunaai/p-video-2-pro-avatar" + }, + "replicate/prunaai/p-video-2-pro-replace": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "output_cost_per_second_1080p": 0.06, + "output_cost_per_second_2k": 0.07, + "output_cost_per_second_480p": 0.025, + "output_cost_per_second_4k": 0.09, + "output_cost_per_second_768p": 0.05, + "source": "https://replicate.com/prunaai/p-video-2-pro-replace" + }, + "replicate/prunaai/p-video-animate": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.03, + "output_cost_per_second_1080p": 0.06, + "output_cost_per_second_720p": 0.03, + "source": "https://replicate.com/prunaai/p-video-animate" + }, + "replicate/prunaai/p-video-avatar": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.025, + "output_cost_per_second_1080p": 0.045, + "output_cost_per_second_720p": 0.025, + "source": "https://replicate.com/prunaai/p-video-avatar" + }, + "replicate/prunaai/p-video-replace": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.03, + "output_cost_per_second_1080p": 0.06, + "output_cost_per_second_720p": 0.03, + "source": "https://replicate.com/prunaai/p-video-replace" + }, + "replicate/prunaai/wan-2.2-image": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://replicate.com/prunaai/wan-2.2-image" + }, + "replicate/quiverai/arrow-1.1": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.2, + "source": "https://replicate.com/quiverai/arrow-1.1" + }, + "replicate/quiverai/arrow-1.1-max": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.25, + "source": "https://replicate.com/quiverai/arrow-1.1-max" + }, + "replicate/quiverai/arrow-1.1-max-vectorize": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.2, + "source": "https://replicate.com/quiverai/arrow-1.1-max-vectorize" + }, + "replicate/quiverai/arrow-1.1-vectorize": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.15, + "source": "https://replicate.com/quiverai/arrow-1.1-vectorize" + }, + "replicate/qwen-edit-apps/qwen-image-edit-plus-lora-fusion": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/qwen-edit-apps/qwen-image-edit-plus-lora-fusion" + }, + "replicate/qwen-edit-apps/qwen-image-edit-plus-lora-next-scene": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/qwen-edit-apps/qwen-image-edit-plus-lora-next-scene" + }, + "replicate/qwen-edit-apps/qwen-image-edit-plus-lora-photo-to-anime": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/qwen-edit-apps/qwen-image-edit-plus-lora-photo-to-anime" + }, + "replicate/qwen-edit-apps/qwen-image-edit-plus-lora-relight": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/qwen-edit-apps/qwen-image-edit-plus-lora-relight" + }, + "replicate/qwen-edit-apps/qwen-image-edit-plus-lora-skin": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/qwen-edit-apps/qwen-image-edit-plus-lora-skin" + }, + "replicate/qwen-edit-apps/qwen-image-edit-plus-lora-upscale": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/qwen-edit-apps/qwen-image-edit-plus-lora-upscale" + }, + "replicate/qwen/qwen-edit-multiangle": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/qwen/qwen-edit-multiangle" + }, + "replicate/qwen/qwen-image": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.025, + "source": "https://replicate.com/qwen/qwen-image" + }, + "replicate/qwen/qwen-image-2": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.035, + "source": "https://replicate.com/qwen/qwen-image-2" + }, + "replicate/qwen/qwen-image-2-pro": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.075, + "source": "https://replicate.com/qwen/qwen-image-2-pro" + }, + "replicate/qwen/qwen-image-2512": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://replicate.com/qwen/qwen-image-2512" + }, + "replicate/qwen/qwen-image-edit": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/qwen/qwen-image-edit" + }, + "replicate/qwen/qwen-image-edit-2511": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/qwen/qwen-image-edit-2511" + }, + "replicate/qwen/qwen-image-edit-plus": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/qwen/qwen-image-edit-plus" + }, + "replicate/qwen/qwen-image-edit-plus-lora": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/qwen/qwen-image-edit-plus-lora" + }, + "replicate/qwen/qwen3-7-plus": { + "input_cost_per_token": 2.76e-07, + "input_cost_per_token_above_256k_tokens": 8.26e-07, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 1.101e-06, + "output_cost_per_token_above_256k_tokens": 3.301e-06, + "source": "https://replicate.com/qwen/qwen3-7-plus", + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/qwen/qwen3-tts": { + "input_cost_per_character": 2e-05, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/qwen/qwen3-tts" + }, + "replicate/recraft-ai/recraft-20b": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.022, + "source": "https://replicate.com/recraft-ai/recraft-20b" + }, + "replicate/recraft-ai/recraft-20b-svg": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.044, + "source": "https://replicate.com/recraft-ai/recraft-20b-svg" + }, + "replicate/recraft-ai/recraft-creative-upscale": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.3, + "source": "https://replicate.com/recraft-ai/recraft-creative-upscale" + }, + "replicate/recraft-ai/recraft-crisp-upscale": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.006, + "source": "https://replicate.com/recraft-ai/recraft-crisp-upscale" + }, + "replicate/recraft-ai/recraft-remove-background": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://replicate.com/recraft-ai/recraft-remove-background" + }, + "replicate/recraft-ai/recraft-v3": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/recraft-ai/recraft-v3" + }, + "replicate/recraft-ai/recraft-v3-svg": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://replicate.com/recraft-ai/recraft-v3-svg" + }, + "replicate/recraft-ai/recraft-v4": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/recraft-ai/recraft-v4" + }, + "replicate/recraft-ai/recraft-v4-pro": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.25, + "source": "https://replicate.com/recraft-ai/recraft-v4-pro" + }, + "replicate/recraft-ai/recraft-v4-pro-svg": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.3, + "source": "https://replicate.com/recraft-ai/recraft-v4-pro-svg" + }, + "replicate/recraft-ai/recraft-v4-styles-pro": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.1, + "source": "https://replicate.com/recraft-ai/recraft-v4-styles-pro" + }, + "replicate/recraft-ai/recraft-v4-styles-pro-svg": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.12, + "source": "https://replicate.com/recraft-ai/recraft-v4-styles-pro-svg" + }, + "replicate/recraft-ai/recraft-v4-svg": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://replicate.com/recraft-ai/recraft-v4-svg" + }, + "replicate/recraft-ai/recraft-v4.1": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/recraft-ai/recraft-v4.1" + }, + "replicate/recraft-ai/recraft-v4.1-pro": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.25, + "source": "https://replicate.com/recraft-ai/recraft-v4.1-pro" + }, + "replicate/recraft-ai/recraft-v4.1-pro-svg": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.25, + "source": "https://replicate.com/recraft-ai/recraft-v4.1-pro-svg" + }, + "replicate/recraft-ai/recraft-v4.1-svg": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/recraft-ai/recraft-v4.1-svg" + }, + "replicate/recraft-ai/recraft-v4.1-utility": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/recraft-ai/recraft-v4.1-utility" + }, + "replicate/recraft-ai/recraft-v4.1-utility-pro": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.25, + "source": "https://replicate.com/recraft-ai/recraft-v4.1-utility-pro" + }, + "replicate/recraft-ai/recraft-vectorize": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://replicate.com/recraft-ai/recraft-vectorize" + }, + "replicate/resemble-ai/chatterbox": { + "input_cost_per_character": 2.5e-05, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/resemble-ai/chatterbox" + }, + "replicate/resemble-ai/chatterbox-pro": { + "input_cost_per_character": 4e-05, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/resemble-ai/chatterbox-pro" + }, + "replicate/resemble-ai/chatterbox-turbo": { + "input_cost_per_character": 2.5e-05, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/resemble-ai/chatterbox-turbo" + }, + "replicate/retro-diffusion/rd-animation": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.07, + "source": "https://replicate.com/retro-diffusion/rd-animation" + }, + "replicate/runwayml/aleph-2": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.336, + "source": "https://replicate.com/runwayml/aleph-2" + }, + "replicate/runwayml/gen-4.5": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.12, + "source": "https://replicate.com/runwayml/gen-4.5" + }, + "replicate/runwayml/gen4-image-turbo": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/runwayml/gen4-image-turbo" + }, + "replicate/runwayml/gen4-turbo": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://replicate.com/runwayml/gen4-turbo" + }, + "replicate/snowflake/snowflake-arctic-instruct": { + "input_cost_per_token": 2e-05, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2e-05, + "source": "https://replicate.com/snowflake/snowflake-arctic-instruct", + "supports_system_messages": true + }, + "replicate/stability-ai/stable-diffusion-3": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.035, + "source": "https://replicate.com/stability-ai/stable-diffusion-3" + }, + "replicate/stability-ai/stable-diffusion-3.5-large": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.065, + "source": "https://replicate.com/stability-ai/stable-diffusion-3.5-large" + }, + "replicate/stability-ai/stable-diffusion-3.5-large-turbo": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/stability-ai/stable-diffusion-3.5-large-turbo" + }, + "replicate/stability-ai/stable-diffusion-3.5-medium": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.035, + "source": "https://replicate.com/stability-ai/stable-diffusion-3.5-medium" + }, + "replicate/sync/lipsync-2": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://replicate.com/sync/lipsync-2" + }, + "replicate/sync/lipsync-2-pro": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.08325, + "source": "https://replicate.com/sync/lipsync-2-pro" + }, + "replicate/sync/react-1": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.167, + "source": "https://replicate.com/sync/react-1" + }, + "replicate/tencent/hunyuan-image-2.1": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://replicate.com/tencent/hunyuan-image-2.1" + }, + "replicate/tencent/hunyuan-image-3": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://replicate.com/tencent/hunyuan-image-3" + }, + "replicate/veed/fabric-1.0": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.15, + "output_cost_per_second_480p": 0.08, + "output_cost_per_second_720p": 0.15, + "source": "https://replicate.com/veed/fabric-1.0" + }, + "replicate/wan-video/wan-2.2-s2v": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.02, + "source": "https://replicate.com/wan-video/wan-2.2-s2v" + }, + "replicate/wan-video/wan-2.5-i2v": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.1, + "source": "https://replicate.com/wan-video/wan-2.5-i2v" + }, + "replicate/wan-video/wan-2.5-i2v-fast": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.068, + "output_cost_per_second_1080p": 0.102, + "output_cost_per_second_720p": 0.068, + "source": "https://replicate.com/wan-video/wan-2.5-i2v-fast" + }, + "replicate/wan-video/wan-2.5-t2v": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.1, + "source": "https://replicate.com/wan-video/wan-2.5-t2v" + }, + "replicate/wan-video/wan-2.5-t2v-fast": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.068, + "output_cost_per_second_1080p": 0.102, + "output_cost_per_second_720p": 0.068, + "source": "https://replicate.com/wan-video/wan-2.5-t2v-fast" + }, + "replicate/wan-video/wan-2.6-i2v": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_720p": 0.1, + "source": "https://replicate.com/wan-video/wan-2.6-i2v" + }, + "replicate/wan-video/wan-2.6-t2v": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_720p": 0.1, + "source": "https://replicate.com/wan-video/wan-2.6-t2v" + }, + "replicate/wan-video/wan-2.7-i2v": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.15, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_720p": 0.1, + "source": "https://replicate.com/wan-video/wan-2.7-i2v" + }, + "replicate/wan-video/wan-2.7-image": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/wan-video/wan-2.7-image" + }, + "replicate/wan-video/wan-2.7-image-pro": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/wan-video/wan-2.7-image-pro" + }, + "replicate/wan-video/wan-2.7-r2v": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://replicate.com/wan-video/wan-2.7-r2v" + }, + "replicate/wan-video/wan-2.7-t2v": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://replicate.com/wan-video/wan-2.7-t2v" + }, + "replicate/wan-video/wan-2.7-videoedit": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://replicate.com/wan-video/wan-2.7-videoedit" + }, + "replicate/wan-video/wan2.6-i2v-flash": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "output_cost_per_second_1080p": 0.075, + "output_cost_per_second_720p": 0.05, + "source": "https://replicate.com/wan-video/wan2.6-i2v-flash" + }, + "replicate/wavespeedai/qwen-image": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.025, + "source": "https://replicate.com/wavespeedai/qwen-image" + }, + "replicate/wavespeedai/wan-2.1-i2v-480p": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.09, + "source": "https://replicate.com/wavespeedai/wan-2.1-i2v-480p" + }, + "replicate/wavespeedai/wan-2.1-i2v-720p": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.25, + "source": "https://replicate.com/wavespeedai/wan-2.1-i2v-720p" + }, + "replicate/wavespeedai/wan-2.1-t2v-480p": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.07, + "source": "https://replicate.com/wavespeedai/wan-2.1-t2v-480p" + }, + "replicate/wavespeedai/wan-2.1-t2v-720p": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.24, + "source": "https://replicate.com/wavespeedai/wan-2.1-t2v-720p" + }, + "replicate/xai/grok-imagine-image": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://replicate.com/xai/grok-imagine-image" + }, + "replicate/xai/grok-imagine-image-quality": { + "input_cost_per_pixel": 1e-08, + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "output_cost_per_image_1K": 0.04, + "output_cost_per_image_2K": 0.06, + "source": "https://replicate.com/xai/grok-imagine-image-quality" + }, + "replicate/xai/grok-imagine-r2v": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://replicate.com/xai/grok-imagine-r2v" + }, + "replicate/xai/grok-imagine-video": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.07, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.07, + "source": "https://replicate.com/xai/grok-imagine-video" + }, + "replicate/xai/grok-imagine-video-1.5": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.08, + "source": "https://replicate.com/xai/grok-imagine-video-1.5" + }, + "replicate/xai/grok-imagine-video-extension": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://replicate.com/xai/grok-imagine-video-extension" + }, + "replicate/xai/grok-text-to-speech": { + "input_cost_per_character": 1.5e-05, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/xai/grok-text-to-speech" + }, + "fal_ai/blackforestlabs/flux-3/edit-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"the page states only the 1K (1 MP) price of $0.048 and the pricing API bills in megapixels at $0.048, so the per-pixel rate is $0.048 per megapixel and the per-image price is the default 1k output; 768sq, 1.5k, 2k and 4k outputs are priced by the per-pixel rate"}, + "mode": "image_generation", + "output_cost_per_image": 0.048, + "output_cost_per_pixel": 4.57763671875e-08, + "source": "https://fal.ai/models/blackforestlabs/flux-3/edit-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/blackforestlabs/flux-3/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; the pricing API reports a $0.085 per second base price that the page does not state"}, + "mode": "video_generation", + "output_cost_per_second": 0.17, + "output_cost_per_second_1080p": 0.29, + "output_cost_per_second_2k": 0.32, + "output_cost_per_second_4k": 0.47, + "output_cost_per_second_720p": 0.17, + "source": "https://fal.ai/models/blackforestlabs/flux-3/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/blackforestlabs/flux-3/klein/edit-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per output image by resolution; output_cost_per_image is the 1K rate (image_size defaults to the input size, 1K is the page example); 768 x 768 is $0.008 and 1.5K is $0.011 per image, no catalog field"}, + "mode": "image_generation", + "output_cost_per_image": 0.009, + "output_cost_per_image_1K": 0.009, + "output_cost_per_image_2K": 0.014, + "output_cost_per_image_4K": 0.036, + "source": "https://fal.ai/models/blackforestlabs/flux-3/klein/edit-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/blackforestlabs/flux-3/klein/text-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per output image by resolution; output_cost_per_image is the 1K rate (default image_size square_hd); 768 x 768 is $0.008 and 1.5K is $0.011 per image, no catalog field"}, + "mode": "image_generation", + "output_cost_per_image": 0.009, + "output_cost_per_image_1K": 0.009, + "output_cost_per_image_2K": 0.014, + "output_cost_per_image_4K": 0.036, + "source": "https://fal.ai/models/blackforestlabs/flux-3/klein/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/blackforestlabs/flux-3/text-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"the page states only the 1K (1 MP) price of $0.048 and the pricing API bills in megapixels at $0.048, so the per-pixel rate is $0.048 per megapixel and the per-image price is the default 1k output; 768sq, 1.5k, 2k and 4k outputs are priced by the per-pixel rate"}, + "mode": "image_generation", + "output_cost_per_image": 0.048, + "output_cost_per_pixel": 4.57763671875e-08, + "source": "https://fal.ai/models/blackforestlabs/flux-3/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/blackforestlabs/flux-3/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; the pricing API reports a $0.085 per second base price that the page does not state"}, + "mode": "video_generation", + "output_cost_per_second": 0.17, + "output_cost_per_second_1080p": 0.29, + "output_cost_per_second_2k": 0.32, + "output_cost_per_second_4k": 0.47, + "output_cost_per_second_720p": 0.17, + "source": "https://fal.ai/models/blackforestlabs/flux-3/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/blackforestlabs/flux-video-upscale": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by resolution in the default creative mode (creativity=1); output_cost_per_second is the highest tier (4K) because the output resolution depends on the source and upscale_factor; precise mode (creativity=0) is $0.084 (1080p), $0.15 (2K) and $0.33 (4K) per second and has no catalog field"}, + "mode": "video_generation", + "output_cost_per_second": 0.474, + "output_cost_per_second_1080p": 0.12, + "output_cost_per_second_2k": 0.21, + "output_cost_per_second_4k": 0.474, + "source": "https://fal.ai/models/blackforestlabs/flux-video-upscale", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bria/fibo-2/generate": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per generated image at the default 1MP output; the 4MP output is $0.06 per image and has no catalog field"}, + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-2/generate", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/bytedance/seedance-2.0/fast/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video at the default resolution 720p, the only per-second rate the page states; fal bills tokens at $0.0112 per 1000 tokens, counts input video duration, and multiplies by 0.6 with video inputs"}, + "mode": "video_generation", + "output_cost_per_second": 0.2419, + "output_cost_per_second_720p": 0.2419, + "source": "https://fal.ai/models/bytedance/seedance-2.0/fast/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/seedance-2.0/us/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; 1080p and 4k are not priced on the page; fal bills tokens at $0.0168 per 1000 tokens, counts input video duration, and multiplies by 0.6 with video inputs"}, + "mode": "video_generation", + "output_cost_per_second": 0.37, + "output_cost_per_second_480p": 0.1731, + "output_cost_per_second_720p": 0.37, + "source": "https://fal.ai/models/bytedance/seedance-2.0/us/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/seedance-2.5/us/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; with video references fal bills input and output duration and multiplies by 0.6"}, + "mode": "video_generation", + "output_cost_per_second": 0.473, + "output_cost_per_second_1080p": 1.164, + "output_cost_per_second_480p": 0.2205, + "output_cost_per_second_720p": 0.473, + "source": "https://fal.ai/models/bytedance/seedance-2.5/us/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/bria/background/remove": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per image without a prompt (prompt is optional); $0.03 per image when a prompt is given has no catalog field"}, + "mode": "image_generation", + "output_cost_per_image": 0.018, + "source": "https://fal.ai/models/fal-ai/bria/background/remove", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/bytedance-upscaler/upscale/video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by target_resolution at 30fps in normal mode; output_cost_per_second is the default target_resolution 1080p rate; 6k $0.0574 and 8k $0.1148 per second have no catalog field; 30-60fps doubles, over 60fps quadruples and pro mode multiplies by 10, none of which is modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.0072, + "output_cost_per_second_1080p": 0.0072, + "output_cost_per_second_2k": 0.0144, + "output_cost_per_second_4k": 0.0288, + "source": "https://fal.ai/models/fal-ai/bytedance-upscaler/upscale/video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/emu-3.5-image/edit-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per image at the default 720p resolution; 480p is $0.15 per image and has no catalog field"}, + "mode": "image_generation", + "output_cost_per_image": 0.3, + "source": "https://fal.ai/models/fal-ai/emu-3.5-image/edit-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/emu-3.5-image/text-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per image at the default 720p resolution; 480p is $0.15 per image and has no catalog field"}, + "mode": "image_generation", + "output_cost_per_image": 0.3, + "source": "https://fal.ai/models/fal-ai/emu-3.5-image/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/kling-video/v2.5-turbo/pro/image-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.07, + "source": "https://fal.ai/models/fal-ai/kling-video/v2.5-turbo/pro/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v2.5-turbo/pro/text-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.07, + "source": "https://fal.ai/models/fal-ai/kling-video/v2.5-turbo/pro/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v2.5-turbo/standard/image-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.042, + "source": "https://fal.ai/models/fal-ai/kling-video/v2.5-turbo/standard/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/minimax/hailuo-02/standard/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768P rate; 512P is roughly $0.017 per second and has no catalog field"}, + "mode": "video_generation", + "output_cost_per_second": 0.045, + "output_cost_per_second_768p": 0.045, + "source": "https://fal.ai/models/fal-ai/minimax/hailuo-02/standard/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/minimax/image-01": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://fal.ai/models/fal-ai/minimax/image-01", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/object-removal": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per image at the default model best_quality; low_quality $0.006, medium_quality $0.012 and high_quality $0.018 per image have no catalog field"}, + "mode": "image_generation", + "output_cost_per_image": 0.024, + "source": "https://fal.ai/models/fal-ai/object-removal", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/object-removal/bbox": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per image at the default model best_quality; low_quality $0.006, medium_quality $0.012 and high_quality $0.018 per image have no catalog field"}, + "mode": "image_generation", + "output_cost_per_image": 0.024, + "source": "https://fal.ai/models/fal-ai/object-removal/bbox", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/object-removal/mask": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per image at the default model best_quality; low_quality $0.006, medium_quality $0.012 and high_quality $0.018 per image have no catalog field"}, + "mode": "image_generation", + "output_cost_per_image": 0.024, + "source": "https://fal.ai/models/fal-ai/object-removal/mask", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/recraft/v3/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per image at the default realistic_image style; vector styles are $0.08 per image and have no catalog field"}, + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/recraft/v3/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/scail-2": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.2, + "source": "https://fal.ai/models/fal-ai/scail-2", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan-vace-apps/long-reframe": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by resolution, converted from the page rate per 2 seconds ($0.08 per 2s at 720p, $0.04 per 2s at 480p); output_cost_per_second is the 720p rate because the default resolution is auto; 580p ($0.06 per 2s) has no catalog field, 240p and 360p are not priced on the page; seconds are rounded up to a multiple of 2"}, + "mode": "video_generation", + "output_cost_per_second": 0.04, + "output_cost_per_second_480p": 0.02, + "output_cost_per_second_720p": 0.04, + "source": "https://fal.ai/models/fal-ai/wan-vace-apps/long-reframe", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan/v2.2-14b/animate/move": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per video second of output by resolution, where a video second is 16 frames; output_cost_per_second is the default resolution 480p rate; 580p is $0.06 per video second and has no catalog field"}, + "mode": "video_generation", + "output_cost_per_second": 0.04, + "output_cost_per_second_480p": 0.04, + "output_cost_per_second_720p": 0.08, + "source": "https://fal.ai/models/fal-ai/wan/v2.2-14b/animate/move", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan/v2.2-14b/animate/replace": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per video second of output by resolution, where a video second is 16 frames; output_cost_per_second is the default resolution 480p rate; 580p is $0.06 per video second and has no catalog field"}, + "mode": "video_generation", + "output_cost_per_second": 0.04, + "output_cost_per_second_480p": 0.04, + "output_cost_per_second_720p": 0.08, + "source": "https://fal.ai/models/fal-ai/wan/v2.2-14b/animate/replace", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/google/gemini-omni-flash/v1.2/edit": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the default resolution 720p rate; 360p is $0.0273 per second and has no catalog field; input tokens (text, image, video) are billed at $1.50 per million"}, + "mode": "video_generation", + "output_cost_per_second": 0.0819, + "output_cost_per_second_1080p": 0.1229, + "output_cost_per_second_4k": 0.2457, + "output_cost_per_second_720p": 0.0819, + "source": "https://fal.ai/models/google/gemini-omni-flash/v1.2/edit", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/google/gemini-omni-flash/v1.2/extend": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the default resolution 720p rate; 360p is $0.0273 per second and has no catalog field; input tokens (text, image, video) are billed at $1.50 per million"}, + "mode": "video_generation", + "output_cost_per_second": 0.0819, + "output_cost_per_second_1080p": 0.1229, + "output_cost_per_second_4k": 0.2457, + "output_cost_per_second_720p": 0.0819, + "source": "https://fal.ai/models/google/gemini-omni-flash/v1.2/extend", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/google/gemini-omni-flash/v1.2/image-to-video": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the default resolution 720p rate; 360p is $0.0273 per second and has no catalog field; input tokens (text, image, video) are billed at $1.50 per million"}, + "mode": "video_generation", + "output_cost_per_second": 0.0819, + "output_cost_per_second_1080p": 0.1229, + "output_cost_per_second_4k": 0.2457, + "output_cost_per_second_720p": 0.0819, + "source": "https://fal.ai/models/google/gemini-omni-flash/v1.2/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/google/gemini-omni-flash/v1.2/reference-to-video": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the default resolution 720p rate; 360p is $0.0273 per second and has no catalog field; input tokens (text, image, video) are billed at $1.50 per million"}, + "mode": "video_generation", + "output_cost_per_second": 0.0819, + "output_cost_per_second_1080p": 0.1229, + "output_cost_per_second_4k": 0.2457, + "output_cost_per_second_720p": 0.0819, + "source": "https://fal.ai/models/google/gemini-omni-flash/v1.2/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/google/gemini-omni-flash/v1.2/text-to-video": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the default resolution 720p rate; 360p is $0.0273 per second and has no catalog field; input tokens (text, image, video) are billed at $1.50 per million"}, + "mode": "video_generation", + "output_cost_per_second": 0.0819, + "output_cost_per_second_1080p": 0.1229, + "output_cost_per_second_4k": 0.2457, + "output_cost_per_second_720p": 0.0819, + "source": "https://fal.ai/models/google/gemini-omni-flash/v1.2/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/google/virtual-try-on": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.075, + "source": "https://fal.ai/models/google/virtual-try-on", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/ideogram/v4/tiling": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per megapixel at the default rendering_speed BALANCED; TURBO is $0.03 and QUALITY is $0.10 per megapixel, no catalog field"}, + "mode": "image_generation", + "output_cost_per_image": 0.06, + "output_cost_per_pixel": 5.7220458984375e-08, + "source": "https://fal.ai/models/ideogram/v4/tiling", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/ideogram/v4/tiling/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per megapixel at the default rendering_speed BALANCED; TURBO is $0.03375 and QUALITY is $0.1125 per megapixel, no catalog field"}, + "mode": "image_generation", + "output_cost_per_image": 0.0675, + "output_cost_per_pixel": 6.437301635742188e-08, + "source": "https://fal.ai/models/ideogram/v4/tiling/lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/kling/v4/flash/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video at 720p (the only resolution) with image references; with video references fal bills $0.063 per second on the output duration plus the greater of the input and output durations, which has no catalog field"}, + "mode": "video_generation", + "output_cost_per_second": 0.094, + "output_cost_per_second_720p": 0.094, + "source": "https://fal.ai/models/kling/v4/flash/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/kling/v4/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by resolution with image references; output_cost_per_second is the default resolution 1080p rate; with video references or video elements fal bills $0.094 (720p) or $0.141 (1080p) per second on the input plus output length, which has no catalog field"}, + "mode": "video_generation", + "output_cost_per_second": 0.235, + "output_cost_per_second_1080p": 0.235, + "output_cost_per_second_720p": 0.157, + "source": "https://fal.ai/models/kling/v4/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/luma/agent/ray/v3.2/reframe": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per started source second by resolution; output_cost_per_second is the default resolution 540p rate ($0.06), which has no tier field"}, + "mode": "video_generation", + "output_cost_per_second": 0.06, + "output_cost_per_second_1080p": 0.36, + "output_cost_per_second_720p": 0.12, + "source": "https://fal.ai/models/luma/agent/ray/v3.2/reframe", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of requested output duration by resolution; output_cost_per_second is the default resolution 768P rate; the page states no promotion for this endpoint; reference tokens above the 4,096 included per request are $0.02 per 1,000 tokens and are not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_1080p": 0.16, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_768p": 0.08, + "source": "https://fal.ai/models/minimax/h3-max/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max/styles/16bit-pixel": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_768p": 0.08, + "source": "https://fal.ai/models/minimax/h3-max/styles/16bit-pixel", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max/styles/hand-drawn": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_768p": 0.08, + "source": "https://fal.ai/models/minimax/h3-max/styles/hand-drawn", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max/styles/low-poly": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_768p": 0.08, + "source": "https://fal.ai/models/minimax/h3-max/styles/low-poly", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max/styles/retro-toon-70s": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_768p": 0.08, + "source": "https://fal.ai/models/minimax/h3-max/styles/retro-toon-70s", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max/styles/vhs": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_768p": 0.08, + "source": "https://fal.ai/models/minimax/h3-max/styles/vhs", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/mirelo-ai/sfx2.0/video-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated audio per sample; promotional 33% off rate through 2026-12-13 per the page; the standard rate of $0.015 per second applies from 2026-12-14 (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10); mode and endpoint follow fal_ai/sonilo/v1.1/video-to-video-sound-effects"}, + "mode": "video_generation", + "output_cost_per_second": 0.01, + "source": "https://fal.ai/models/mirelo-ai/sfx2.0/video-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/nvidia/cosmos-3-super/text-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per generated image; the optional $0.02 per request prompt expansion surcharge is not modeled, and agentic generation bills every candidate image"}, + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/nvidia/cosmos-3-super/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/recraft/v4/style/pro/text-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per generated image when a style_id is provided; the one-time $0.005 style creation surcharge when no style_id is given is not modeled"}, + "mode": "image_generation", + "output_cost_per_image": 0.1, + "source": "https://fal.ai/models/recraft/v4/style/pro/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/recraft/v4/style/pro/text-to-vector": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per generated image when a style_id is provided; the one-time $0.005 style creation surcharge when no style_id is given is not modeled"}, + "mode": "image_generation", + "output_cost_per_image": 0.12, + "source": "https://fal.ai/models/recraft/v4/style/pro/text-to-vector", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/recraft/v4/style/text-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per generated image when a style_id is provided; the one-time $0.005 style creation surcharge when no style_id is given is not modeled"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "source": "https://fal.ai/models/recraft/v4/style/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/recraft/v4/style/text-to-vector": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per generated image when a style_id is provided; the one-time $0.005 style creation surcharge when no style_id is given is not modeled"}, + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://fal.ai/models/recraft/v4/style/text-to-vector", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/vast/eden-live-14b-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of video generated in a live session; the 10 billable second ($0.10) minimum per session is not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.01, + "source": "https://fal.ai/models/vast/eden-live-14b-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/vast/eden-live-5b-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of video generated in a live session; the 10 billable second ($0.035) minimum per session is not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.0035, + "source": "https://fal.ai/models/vast/eden-live-5b-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/xai/grok-imagine-image/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.022, + "source": "https://fal.ai/models/xai/grok-imagine-image/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/xai/grok-imagine-video/edit-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the 720p rate because the default resolution is auto; the $0.01 per second of input video charge is not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.07, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.07, + "source": "https://fal.ai/models/xai/grok-imagine-video/edit-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/xai/grok-imagine-video/extend-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the 720p rate because the endpoint has no resolution field; the $0.01 per second of input video charge is not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.07, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.07, + "source": "https://fal.ai/models/xai/grok-imagine-video/extend-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/xai/grok-imagine-video/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the default resolution 720p rate; the $0.002 per request image input charge is not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.07, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.07, + "source": "https://fal.ai/models/xai/grok-imagine-video/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/xai/grok-imagine-video/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the default resolution 480p rate; the $0.002 per request image input charge is not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.05, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.07, + "source": "https://fal.ai/models/xai/grok-imagine-video/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] }, - "openrouter/anthropic/claude-sonnet-5.5": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "supports_sampling_params": false, - "supports_adaptive_thinking": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-07, - "supports_prompt_caching": true, - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_1hr": 4e-06, - "supports_web_search": true + "fal_ai/xai/grok-imagine-video/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.07, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.07, + "source": "https://fal.ai/models/xai/grok-imagine-video/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] }, - "perplexity/anthropic/claude-sonnet-5-5": { - "litellm_provider": "perplexity", - "mode": "responses", - "supports_adaptive_thinking": true, - "supports_web_search": true, - "supports_function_calling": true, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 2e-07, - "source": "https://docs.perplexity.ai/docs/agent-api/models" + "fal_ai/xai/grok-imagine-video/v1.5/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the default resolution 720p rate; the $0.01 per reference image charge is not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.14, + "output_cost_per_second_1080p": 0.25, + "output_cost_per_second_480p": 0.08, + "output_cost_per_second_720p": 0.14, + "source": "https://fal.ai/models/xai/grok-imagine-video/v1.5/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] }, - "us-gov.anthropic.claude-sonnet-5-5": { - "bedrock_converse_supports_strict_tools": false, - "bedrock_output_config_effort_ceiling": "xhigh", - "cache_creation_input_token_cost": 3e-06, - "cache_creation_input_token_cost_above_1hr": 4.8e-06, - "cache_read_input_token_cost": 2.4e-07, - "input_cost_per_token": 2.4e-06, - "litellm_provider": "bedrock_converse", - "supports_tool_search": true, + "fal_ai/xai/grok-imagine-video/v1.5/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the default resolution 480p rate; the $0.01 per reference image charge is not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_480p": 0.08, + "output_cost_per_second_720p": 0.14, + "source": "https://fal.ai/models/xai/grok-imagine-video/v1.5/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "databricks/databricks-claude-fable-5-2": { + "cache_creation_input_token_cost": 9.99999e-06, + "cache_creation_input_token_cost_above_1hr": 1.599997e-05, + "cache_read_input_token_cost": 1.9999e-07, + "input_cost_per_token": 8.00002e-06, + "input_dbu_cost_per_token": 0.000114286, + "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, + "metadata": {"notes":"Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields."}, "mode": "chat", - "output_cost_per_token": 1.2e-05, - "supports_forced_tool_use": false, - "thinking_always_on": true, - "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token": 4.000003e-05, + "output_dbu_cost_per_token": 0.000571429, + "prompt_cache_min_tokens": 512.0, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_adaptive_thinking": true, + "supports_anthropic_thinking_payload": true, "supports_assistant_prefill": false, - "supports_computer_use": true, + "supports_forced_tool_use": false, "supports_function_calling": true, - "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, - "supports_native_structured_output": false, - "supports_output_config": true, - "supports_parallel_tool_use_config": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "thinking_always_on": true }, - "us.anthropic.claude-sonnet-5-5": { - "bedrock_converse_supports_strict_tools": false, - "cache_creation_input_token_cost": 2.75e-06, - "cache_creation_input_token_cost_above_1hr": 4.4e-06, - "cache_read_input_token_cost": 2.2e-07, - "input_cost_per_token": 2.2e-06, - "litellm_provider": "bedrock_converse", - "supports_tool_search": true, + "databricks/system.ai.claude-fable-5-2": { + "cache_creation_input_token_cost": 9.99999e-06, + "cache_creation_input_token_cost_above_1hr": 1.599997e-05, + "cache_read_input_token_cost": 1.9999e-07, + "input_cost_per_token": 8.00002e-06, + "input_dbu_cost_per_token": 0.000114286, + "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, + "metadata": {"notes":"Claude Fable 5.2 on Databricks is served through Unity Gateway with the model service name system.ai.claude-fable-5-2, hosted through Amazon Bedrock. Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields."}, "mode": "chat", - "output_cost_per_token": 1.1e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, + "output_cost_per_token": 4.000003e-05, + "output_dbu_cost_per_token": 0.000571429, + "prompt_cache_min_tokens": 512.0, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_adaptive_thinking": true, - "supports_mid_conversation_system": true, + "supports_anthropic_thinking_payload": true, "supports_assistant_prefill": false, - "supports_computer_use": true, + "supports_forced_tool_use": false, "supports_function_calling": true, - "supports_pdf_input": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": false, - "supports_max_reasoning_effort": true, - "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh", - "supports_parallel_tool_use_config": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, - "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "thinking_always_on": true }, - "vertex_ai/claude-sonnet-5-5": { - "regional_endpoint_uplift_multiplier": 1.1, - "supports_mid_conversation_system": true, - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_1hr": 4e-06, - "cache_creation_input_token_cost_batches": 1.25e-06, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_batches": 1e-07, + "replicate/google/gemini-4-carbon": { "input_cost_per_token": 2e-06, - "input_cost_per_token_batches": 1e-06, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "litellm_provider": "replicate", + "max_input_tokens": 1048576, + "max_output_tokens": 65535, "mode": "chat", + "output_cost_per_reasoning_token": 1e-05, "output_cost_per_token": 1e-05, - "output_cost_per_token_batches": 5e-06, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_adaptive_thinking": true, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "source": "https://replicate.com/google/gemini-4-carbon", + "supports_audio_input": true, + "supports_function_calling": false, + "supports_parallel_function_calling": false, "supports_reasoning": true, - "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_max_reasoning_effort": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, - "prompt_cache_min_tokens": 512, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": false, + "supports_video_input": true, + "supports_vision": true }, - "vertex_ai/claude-sonnet-5-5@default": { - "regional_endpoint_uplift_multiplier": 1.1, - "supports_mid_conversation_system": true, - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_1hr": 4e-06, - "cache_creation_input_token_cost_batches": 1.25e-06, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_batches": 1e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_batches": 1e-06, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "azure_ai/mistral-large-4-latest": { + "deprecation_date": "2027-10-27", + "deprecation_source": "https://management.azure.com/subscriptions/{subscriptionId}/providers/Microsoft.CognitiveServices/locations/eastus/models?api-version=2024-10-01", + "input_cost_per_token": 7e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_batches": 5e-06, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_adaptive_thinking": true, - "supports_assistant_prefill": false, - "supports_computer_use": true, + "output_cost_per_token": 2.1e-06, + "source": "https://docs.mistral.ai/models/mistral-large-4-0", + "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_pdf_input": false, "supports_reasoning": true, "supports_response_schema": true, - "supports_sampling_params": false, "supports_tool_choice": true, - "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_max_reasoning_effort": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, - "prompt_cache_min_tokens": 512, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "supports_vision": true }, - "prism/deepseek-v4.1-flash": { - "cache_read_input_token_cost": 7e-08, - "input_cost_per_token": 1.7e-07, - "litellm_provider": "prism", - "max_input_tokens": 1000000, - "max_output_tokens": 384000, - "max_tokens": 384000, - "mode": "chat", - "output_cost_per_token": 6.3e-07, - "source": "https://prisminference.com/pricing", + "fal_ai/fal-ai/recraft-20b": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per image at the default realistic_image style, from the fal pricing API; vector styles cost 2x and have no catalog field; the fal.ai page for this id redirects to fal-ai/recraft/v2/text-to-image, which rounds the rate to $0.022"}, + "mode": "image_generation", + "output_cost_per_image": 0.0219, + "source": "https://api.fal.ai/v1/models/pricing?endpoint_id=fal-ai/recraft-20b", "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses", - "/v1/messages" + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/stable-diffusion-v3-medium/image-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.035, + "source": "https://api.fal.ai/v1/models/pricing?endpoint_id=fal-ai/stable-diffusion-v3-medium/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, "supports_vision": true }, - "prism/deepseek-v4-flash": { - "cache_read_input_token_cost": 7e-08, - "input_cost_per_token": 1.7e-07, - "litellm_provider": "prism", - "max_input_tokens": 1000000, - "max_output_tokens": 384000, - "max_tokens": 384000, - "mode": "chat", - "output_cost_per_token": 2.1e-07, - "source": "https://prisminference.com/pricing", + "fal_ai/fal-ai/pixverse/lipsync": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video; when audio_url is not provided the text is spoken with TTS at $0.24 per 100 characters, which is not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.04, + "source": "https://fal.ai/models/fal-ai/pixverse/lipsync", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "bedrock_mantle/us-gov-east-1/openai.gpt-5.6-cyber": { + "cache_creation_input_token_cost": 2.109375e-05, + "cache_read_input_token_cost": 1.6875e-06, + "input_cost_per_token": 1.6875e-05, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 0.00010125, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-cyber.html", "supported_endpoints": [ "/v1/chat/completions", - "/v1/responses", - "/v1/messages" + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" ], "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true, + "supports_web_search": false, + "supports_xhigh_reasoning_effort": true, + "use_openai_responses_path": true }, - "global.xai.grok-4.7": { - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 2e-06, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 500000, - "max_output_tokens": 500000, - "max_tokens": 500000, - "mode": "chat", - "output_cost_per_token": 6e-06, - "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", - "supports_function_calling": true, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_tool_choice": true, + "fal_ai/fal-ai/kling-video/v2.6/pro/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video with the default generate_audio=true ($0.14); videos without audio are $0.07 per second and videos with audio and voice control are $0.168 per second, which have no catalog field"}, + "mode": "video_generation", + "output_cost_per_second": 0.14, + "source": "https://fal.ai/models/fal-ai/kling-video/v2.6/pro/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/vidu/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second derived from the fixed 4s clip price of $0.20 per video"}, + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://fal.ai/models/fal-ai/vidu/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/vidu/start-end-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second derived from the fixed 4s clip price of $0.20 per video"}, + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://fal.ai/models/fal-ai/vidu/start-end-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/vidu/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second derived from the fixed 4s clip price of $0.40 per video"}, + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://fal.ai/models/fal-ai/vidu/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/luma/agent/ray/v3.2/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second derived from the 5s clip prices by resolution ($0.15 at 540p, $0.30 at 720p, $1.20 at 1080p); output_cost_per_second is the default resolution 540p rate, which has no tier field; HDR ($0.60 at 720p, $2.40 at 1080p per 5s) and HDR+EXR ($0.90, $3.60) are not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.03, + "output_cost_per_second_1080p": 0.24, + "output_cost_per_second_720p": 0.06, + "source": "https://fal.ai/models/luma/agent/ray/v3.2/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/luma/agent/ray/v3.2/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second derived from the 5s and 10s clip prices by resolution ($0.50/$1.00 at 540p, $1.00/$2.00 at 720p, $2.00/$4.00 at 1080p); output_cost_per_second is the default resolution 540p rate, which has no tier field"}, + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_1080p": 0.4, + "output_cost_per_second_720p": 0.2, + "source": "https://fal.ai/models/luma/agent/ray/v3.2/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/luma/agent/ray/v3.2/video-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second derived from the 5s and 10s clip prices by resolution ($0.72/$1.44 at 540p, $1.08/$2.16 at 720p, $2.16/$4.32 at 1080p); output_cost_per_second is the default resolution 540p rate, which has no tier field; HDR and HDR+EXR prices are not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.144, + "output_cost_per_second_1080p": 0.432, + "output_cost_per_second_720p": 0.216, + "source": "https://fal.ai/models/luma/agent/ray/v3.2/video-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/pixverse/v6/max/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution without audio (the default generate_audio_switch=false); output_cost_per_second is the default resolution 720p rate; 360p $0.054 and 540p $0.081 have no catalog field; with audio the rates are $0.081/$0.099/$0.135/$0.252 per second, which is not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.099, + "output_cost_per_second_1080p": 0.198, + "output_cost_per_second_720p": 0.099, + "source": "https://fal.ai/models/pixverse/v6/max/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/pixverse/v6/max/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution without audio (the default generate_audio_switch=false); output_cost_per_second is the default resolution 720p rate; 360p $0.054 and 540p $0.081 have no catalog field; with audio the rates are $0.081/$0.099/$0.135/$0.252 per second, which is not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.099, + "output_cost_per_second_1080p": 0.198, + "output_cost_per_second_720p": 0.099, + "source": "https://fal.ai/models/pixverse/v6/max/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/flux-2-pro": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per image for the default 1 MP output; fal bills $0.03 for the first output megapixel plus $0.015 per additional input or output megapixel, rounded up, which is not modeled"}, + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://fal.ai/models/fal-ai/flux-2-pro", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2-pro/edit": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per image for the default 1 MP output; fal bills $0.03 for the first output megapixel plus $0.015 per additional input or output megapixel, rounded up, which is not modeled"}, + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://fal.ai/models/fal-ai/flux-2-pro/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], "supports_vision": true }, - "us.xai.grok-4.7": { - "cache_read_input_token_cost": 5.5e-07, - "input_cost_per_token": 2.2e-06, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 500000, - "max_output_tokens": 500000, - "max_tokens": 500000, - "mode": "chat", - "output_cost_per_token": 6.6e-06, - "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", - "supports_function_calling": true, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_tool_choice": true, + "fal_ai/fal-ai/flux-2-pro/outpaint": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per image for the default 1 MP output; fal bills $0.03 for the first output megapixel plus $0.015 per additional input or output megapixel, rounded up, which is not modeled"}, + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://fal.ai/models/fal-ai/flux-2-pro/outpaint", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2-max": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per image for the default 1 MP output; fal bills $0.07 for the first processed megapixel plus $0.03 per additional megapixel, which is not modeled"}, + "mode": "image_generation", + "output_cost_per_image": 0.07, + "source": "https://fal.ai/models/fal-ai/flux-2-max", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2-max/edit": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per image for the default 1 MP output; fal bills $0.07 for the first processed megapixel plus $0.03 per additional megapixel, which is not modeled"}, + "mode": "image_generation", + "output_cost_per_image": 0.07, + "source": "https://fal.ai/models/fal-ai/flux-2-max/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-pro/v1/erase": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per image for the first generated megapixel; fal bills $0.004 for each subsequent generated megapixel and $0.004 per reference megapixel with a 3 MP minimum, which is not modeled"}, + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://fal.ai/models/fal-ai/flux-pro/v1/erase", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/smart-resize": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per single-image request at standard resolution: $0.15 per output image plus the $0.05 minimum vision analysis fee per request; additional output images in one request ($0.15 each) and 4K outputs (charged double) are not modeled"}, + "mode": "image_generation", + "output_cost_per_image": 0.2, + "source": "https://fal.ai/models/fal-ai/smart-resize", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bytedance/seedream/v5/pro/layerize": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per generated layer for total pixel area under 1536x1536; layers for a base image over 1536x1536 are $0.0675 each, which has no catalog field"}, + "mode": "image_generation", + "output_cost_per_image": 0.03375, + "source": "https://fal.ai/models/bytedance/seedream/v5/pro/layerize", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], "supports_vision": true }, - "xai.grok-4.7": { - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 2e-06, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 500000, - "max_output_tokens": 500000, - "max_tokens": 500000, - "mode": "chat", - "output_cost_per_token": 6e-06, - "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", - "supports_function_calling": true, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_tool_choice": true, + "fal_ai/luma/agent/uni-1/v1/edit": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per edit with one source image ($0.042 per edit plus $0.003 per reference or source image); each additional reference image adds $0.003, which is not modeled"}, + "mode": "image_generation", + "output_cost_per_image": 0.045, + "source": "https://fal.ai/models/luma/agent/uni-1/v1/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], "supports_vision": true }, - "openrouter/anthropic/claude-sonnet-5.5:batch": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost_above_1hr": 2e-06, - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "fal_ai/luma/agent/uni-1/v1/max/edit": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per edit with one source image ($0.102 per edit plus $0.003 per reference or source image); each additional reference image adds $0.003, which is not modeled"}, + "mode": "image_generation", + "output_cost_per_image": 0.105, + "source": "https://fal.ai/models/luma/agent/uni-1/v1/max/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true }, - "baseten/deepseek-ai/DeepSeek-V4.1-Flash-Fast": { - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 6e-07, - "litellm_provider": "baseten", + "databricks/databricks-gemini-4-carbon": { + "cache_creation_input_token_cost": 2e-06, + "cache_read_input_token_cost": 2e-06, + "input_cost_per_token": 2e-06, + "litellm_provider": "databricks", "max_input_tokens": 1048576, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 1048576, + "metadata": {"notes":"Gemini 4 Carbon on Databricks is available only through Unity Gateway with the model service name system.ai.gemini-4-carbon on a global endpoint. The Databricks pricing pages list no row for it yet, so input and output are the Global rates on the Vertex AI pricing page for Gemini 4 Carbon (listed there through November 30, 2026), no '*_dbu_cost_per_token' fields are published, and cache tokens bill at the input rate until Databricks publishes cache DBU rates."}, "mode": "chat", - "output_cost_per_token": 2.4e-06, - "source": "https://inference.baseten.co/v1/models", + "output_cost_per_token": 1e-05, + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, "supports_tool_choice": true, + "supports_video_input": true, "supports_vision": true }, - "gpt-6.1-sol": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_creation_input_token_cost_above_272k_tokens_batches": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, - "cache_creation_input_token_cost_batches": 1.25e-06, - "cache_creation_input_token_cost_flex": 1.25e-06, - "cache_creation_input_token_cost_priority": 5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "cache_read_input_token_cost_above_272k_tokens_batches": 1e-07, - "cache_read_input_token_cost_above_272k_tokens_flex": 1e-07, - "cache_read_input_token_cost_above_272k_tokens_priority": 4e-07, - "cache_read_input_token_cost_batches": 5e-08, - "cache_read_input_token_cost_flex": 5e-08, - "cache_read_input_token_cost_priority": 2e-07, + "databricks/system.ai.gemini-4-carbon": { + "cache_creation_input_token_cost": 2e-06, + "cache_read_input_token_cost": 2e-06, "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "input_cost_per_token_above_272k_tokens_batches": 2e-06, - "input_cost_per_token_above_272k_tokens_flex": 2e-06, - "input_cost_per_token_above_272k_tokens_priority": 8e-06, - "input_cost_per_token_batches": 1e-06, - "input_cost_per_token_flex": 1e-06, - "input_cost_per_token_priority": 4e-06, - "litellm_provider": "openai", - "max_input_tokens": 922000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "metadata": {"notes":"Gemini 4 Carbon on Databricks is available only through Unity Gateway with the model service name system.ai.gemini-4-carbon on a global endpoint. The Databricks pricing pages list no row for it yet, so input and output are the Global rates on the Vertex AI pricing page for Gemini 4 Carbon (listed there through November 30, 2026), no '*_dbu_cost_per_token' fields are published, and cache tokens bill at the input rate until Databricks publishes cache DBU rates."}, "mode": "chat", "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "output_cost_per_token_above_272k_tokens_batches": 7.5e-06, - "output_cost_per_token_above_272k_tokens_flex": 7.5e-06, - "output_cost_per_token_above_272k_tokens_priority": 3e-05, - "output_cost_per_token_batches": 5e-06, - "output_cost_per_token_flex": 5e-06, - "output_cost_per_token_priority": 2e-05, - "regional_processing_uplift_multiplier_eu": 1.1, - "regional_processing_uplift_multiplier_us": 1.1, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "source": "https://developers.openai.com/api/docs/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text", - "image" + "image", + "audio", + "video" ], "supported_output_modalities": [ "text" ], - "supports_computer_use": true, + "supports_audio_input": true, "supports_function_calling": true, - "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": false, - "supports_native_streaming": true, - "supports_none_reasoning_effort": false, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_xhigh_reasoning_effort": true + "supports_video_input": true, + "supports_vision": true }, - "global.openai.gpt-6.1-sol": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "source": "https://developers.openai.com/api/docs/pricing", - "supported_endpoints": [ - "/v1/responses" + "runwayml/kling2.5_turbo_pro": { + "litellm_provider": "runwayml", + "metadata": {"comment":"12 credits per second @ $0.01 per credit = $0.12 per second"}, + "mode": "video_generation", + "output_cost_per_second": 0.12, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image" ], + "supported_output_modalities": [ + "video" + ] + }, + "runwayml/kling3.0_standard": { + "litellm_provider": "runwayml", + "metadata": {"comment":"13 credits per second with audio, 9 without @ $0.01 per credit; priced at the with-audio rate (audio defaults to true)"}, + "mode": "video_generation", + "output_cost_per_second": 0.13, + "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ - "text" + "video" + ] + }, + "runwayml/kling3.0_pro": { + "litellm_provider": "runwayml", + "metadata": {"comment":"17 credits per second with audio, 12 without @ $0.01 per credit; priced at the with-audio rate (audio defaults to true)"}, + "mode": "video_generation", + "output_cost_per_second": 0.17, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image" ], - "supports_function_calling": true, - "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supported_output_modalities": [ + "video" + ] }, - "openai.gpt-6.1-sol": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "source": "https://developers.openai.com/api/docs/pricing", + "runwayml/kling3.0_4k": { + "litellm_provider": "runwayml", + "metadata": {"comment":"43 credits per second @ $0.01 per credit = $0.43 per second, with or without audio"}, + "mode": "video_generation", + "output_cost_per_second": 0.43, + "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ - "text" + "video" + ] + }, + "runwayml/klingO3_standard": { + "litellm_provider": "runwayml", + "metadata": {"comment":"13 credits per second @ $0.01 per credit = $0.13 per second; video-to-video is billed per second of the input video, not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.13, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image", + "video" ], - "supports_function_calling": true, - "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supported_output_modalities": [ + "video" + ] }, - "bedrock_mantle/openai.gpt-6.1-sol": { - "cache_creation_input_token_cost": 2.75e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, - "cache_read_input_token_cost": 1.1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2.2e-07, - "input_cost_per_token": 2.2e-06, - "input_cost_per_token_above_272k_tokens": 4.4e-06, - "litellm_provider": "bedrock_mantle", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "responses", - "output_cost_per_token": 1.1e-05, - "output_cost_per_token_above_272k_tokens": 1.65e-05, - "source": "https://developers.openai.com/api/docs/models/gpt-6.1-sol", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" + "runwayml/klingO3_pro": { + "litellm_provider": "runwayml", + "metadata": {"comment":"17 credits per second @ $0.01 per credit = $0.17 per second; video-to-video is billed per second of the input video, not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.17, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "runwayml/klingO3_4k": { + "litellm_provider": "runwayml", + "metadata": {"comment":"43 credits per second @ $0.01 per credit = $0.43 per second; video-to-video is billed per second of the input video, not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.43, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "runwayml/kling_4_flash": { + "litellm_provider": "runwayml", + "metadata": {"comment":"9.4 credits per second (720p) without input video @ $0.01 per credit = $0.094 per second; the with-input-video rate (6.3 credits per output second plus 6.3 per second of the greater of input and output duration), rounding up to the next credit and the 29 credit minimum are not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.094, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image", + "video" ], + "supported_output_modalities": [ + "video" + ] + }, + "runwayml/wan3": { + "litellm_provider": "runwayml", + "metadata": {"comment":"5/10/20 credits per second at 480p/720p/1080p @ $0.01 per credit"}, + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_1080p": 0.2, + "output_cost_per_second_480p": 0.05, + "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ - "text" + "video" + ] + }, + "runwayml/wan3_prime": { + "litellm_provider": "runwayml", + "metadata": {"comment":"6.8/14/28 credits per second at 480p/720p/1080p @ $0.01 per credit"}, + "mode": "video_generation", + "output_cost_per_second": 0.14, + "output_cost_per_second_1080p": 0.28, + "output_cost_per_second_480p": 0.068, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image" ], - "supports_function_calling": true, - "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "use_openai_responses_path": true + "supported_output_modalities": [ + "video" + ] }, - "us.openai.gpt-6.1-sol": { - "cache_creation_input_token_cost": 2.75e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, - "cache_read_input_token_cost": 1.1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2.2e-07, - "input_cost_per_token": 2.2e-06, - "input_cost_per_token_above_272k_tokens": 4.4e-06, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.1e-05, - "output_cost_per_token_above_272k_tokens": 1.65e-05, - "source": "https://developers.openai.com/api/docs/pricing", - "supported_endpoints": [ - "/v1/responses" + "runwayml/grok_imagine_1_5": { + "litellm_provider": "runwayml", + "metadata": {"comment":"10/16/29 credits per second at 480p/720p/1080p @ $0.01 per credit; 1 credit per image or audio reference not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.16, + "output_cost_per_second_1080p": 0.29, + "output_cost_per_second_480p": 0.1, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image" ], + "supported_output_modalities": [ + "video" + ] + }, + "runwayml/grok_imagine_1_5_lite": { + "litellm_provider": "runwayml", + "metadata": {"comment":"2/3/14 credits per second at 480p/720p/1080p @ $0.01 per credit; 1 credit for an image-to-video start frame not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.03, + "output_cost_per_second_1080p": 0.14, + "output_cost_per_second_480p": 0.02, + "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ - "text" + "video" + ] + }, + "runwayml/h3_max": { + "litellm_provider": "runwayml", + "metadata": {"comment":"8 credits per second at 768p, 5 at 480p @ $0.01 per credit"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_480p": 0.05, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image" ], - "supports_function_calling": true, - "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, + "supported_output_modalities": [ + "video" + ] + }, + "runwayml/happyhorse_1_0": { + "litellm_provider": "runwayml", + "metadata": {"comment":"15 credits per second at 720p, 30 at 1080p @ $0.01 per credit"}, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "output_cost_per_second_1080p": 0.3, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "runwayml/gemini_omni_flash_1.2": { + "litellm_provider": "runwayml", + "metadata": {"comment":"7/10/21 credits per second at 720p/1080p/4K @ $0.01 per credit; the 360p rate (2 credits per second), 1 credit per reference image or keyframe, 1 credit per second of input video and the 6 credit minimum per request are not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.07, + "output_cost_per_second_1080p": 0.1, + "output_cost_per_second_4k": 0.21, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "runwayml/gemini_omni_flash_1.1": { + "litellm_provider": "runwayml", + "metadata": {"comment":"10/15/30 credits per second at 720p/1080p/4K @ $0.01 per credit; the 360p rate (3.4 credits per second), 1 credit per reference image and 1 credit per second of input video are not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_4k": 0.3, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "runwayml/muse_image": { + "litellm_provider": "runwayml", + "metadata": {"comment":"1 credit per image (any resolution) @ $0.01 per credit = $0.01 per image"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "image" + ] + }, + "runwayml/seedream5_lite": { + "litellm_provider": "runwayml", + "metadata": {"comment":"4 credits per image (any resolution) @ $0.01 per credit = $0.04 per image"}, + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "image" + ] + }, + "runwayml/seedream5_flash": { + "litellm_provider": "runwayml", + "metadata": {"comment":"2 credits per image (any resolution) @ $0.01 per credit = $0.02 per image"}, + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "image" + ] + }, + "runwayml/gemini_image3.1_flash_lite": { + "litellm_provider": "runwayml", + "metadata": {"comment":"4 credits per 1K image @ $0.01 per credit = $0.04 per image"}, + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "image" + ] + }, + "runwayml/bria_fibo_edit_1_5": { + "litellm_provider": "runwayml", + "metadata": {"comment":"5 credits per image @ $0.01 per credit = $0.05 per image"}, + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "image" + ] + }, + "runwayml/gemini_2.5_flash": { + "litellm_provider": "runwayml", + "metadata": {"comment":"5 credits per image (any resolution) @ $0.01 per credit = $0.05 per image"}, + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "image" + ] + }, + "runwayml/eleven_v3": { + "input_cost_per_character": 0.0002, + "litellm_provider": "runwayml", + "metadata": {"comment":"1 credit per 50 characters @ $0.01 per credit = $0.0002 per character; 1 credit minimum not modeled"}, + "mode": "audio_speech", + "source": "https://docs.dev.runwayml.com/guides/pricing/" + }, + "runwayml/eleven_v4": { + "input_cost_per_character": 5e-05, + "litellm_provider": "runwayml", + "metadata": {"comment":"5 credits per 1,000 characters @ $0.01 per credit = $0.00005 per character; 1 credit minimum not modeled"}, + "mode": "audio_speech", + "source": "https://docs.dev.runwayml.com/guides/pricing/" + }, + "gemini/gemini-decision-1": { + "input_cost_per_token": 1e-07, + "litellm_provider": "gemini", + "max_input_tokens": 262144, + "mode": "decisions", + "output_cost_per_token": 0.0, + "rpm": 1500, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/decisions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_computer_use": false, + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_url_context": false, + "supports_video_input": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_web_search": false, + "tpm": 1000000 } }