diff --git a/.changeset/sync-models.md b/.changeset/sync-models.md new file mode 100644 index 0000000000..cf6ce271d7 --- /dev/null +++ b/.changeset/sync-models.md @@ -0,0 +1,9 @@ +--- +'@tanstack/ai-elevenlabs': patch +'@tanstack/ai-gemini': patch +'@tanstack/ai-llmgateway': patch +'@tanstack/ai-openrouter': patch +'@tanstack/ai-vercel-gateway': patch +--- + +Update model metadata from OpenRouter API diff --git a/packages/ai-elevenlabs/src/model-meta.ts b/packages/ai-elevenlabs/src/model-meta.ts index 7e602ea07c..15555ceb3d 100644 --- a/packages/ai-elevenlabs/src/model-meta.ts +++ b/packages/ai-elevenlabs/src/model-meta.ts @@ -55,6 +55,7 @@ export type ElevenLabsTTSModel = (typeof ELEVENLABS_TTS_MODELS)[number] * @see https://elevenlabs.io/docs/overview/capabilities/sound-effects */ export const ELEVENLABS_AUDIO_MODELS = [ + 'eleven_text_to_sound_v3', 'music_v2_5', 'music_v2', 'eleven_text_to_sound_v2', diff --git a/packages/ai-gemini/src/model-meta.ts b/packages/ai-gemini/src/model-meta.ts index 9c0d216ecb..e5493443ad 100644 --- a/packages/ai-gemini/src/model-meta.ts +++ b/packages/ai-gemini/src/model-meta.ts @@ -931,7 +931,35 @@ const GEMINI_3_5_FLASH_LITE = { GeminiStructuredOutputOptions > +const GEMINI_4_ARGON = { + name: 'gemini-4-argon', + max_input_tokens: 1_048_576, + max_output_tokens: 943_718, + supports: { + input: ['audio', 'document', 'image', 'text', 'video'], + output: ['text'], + capabilities: ['function_calling', 'structured_output', 'thinking'], + tools: ['code_execution', 'file_search', 'google_search', 'url_context'], + }, + pricing: { + input: { + normal: 2, + cached: 0.1, + }, + output: { + normal: 10, + }, + }, +} as const satisfies ModelMeta< + GeminiToolConfigOptions & + GeminiSafetyOptions & + GeminiCommonConfigOptions & + GeminiCachedContentOptions & + GeminiStructuredOutputOptions +> + export const GEMINI_MODELS = [ + GEMINI_4_ARGON.name, GEMINI_3_8_FLASH.name, GEMINI_3_7_FLASH.name, GEMINI_3_6_FLASH.name, @@ -1144,6 +1172,11 @@ export type GeminiChatModelProviderOptionsByName = { GeminiCommonConfigOptions & GeminiCachedContentOptions & GeminiStructuredOutputOptions + [GEMINI_4_ARGON.name]: GeminiToolConfigOptions & + GeminiSafetyOptions & + GeminiCommonConfigOptions & + GeminiCachedContentOptions & + GeminiStructuredOutputOptions } /** @@ -1163,6 +1196,7 @@ export type GeminiChatModelToolCapabilitiesByName = { [GEMINI_2_5_PRO.name]: typeof GEMINI_2_5_PRO.supports.tools [GEMINI_2_5_FLASH.name]: typeof GEMINI_2_5_FLASH.supports.tools [GEMINI_2_5_FLASH_LITE.name]: typeof GEMINI_2_5_FLASH_LITE.supports.tools + [GEMINI_4_ARGON.name]: typeof GEMINI_4_ARGON.supports.tools } /** @@ -1194,6 +1228,7 @@ export type GeminiModelInputModalitiesByName = { // Models with text, image, audio, video (no document) [GEMINI_2_5_FLASH.name]: typeof GEMINI_2_5_FLASH.supports.input + [GEMINI_4_ARGON.name]: typeof GEMINI_4_ARGON.supports.input } /** @@ -1217,6 +1252,7 @@ export const GEMINI_MODEL_INPUT_MODALITIES: Readonly< [GEMINI_2_5_PRO.name]: GEMINI_2_5_PRO.supports.input, [GEMINI_2_5_FLASH_LITE.name]: GEMINI_2_5_FLASH_LITE.supports.input, [GEMINI_2_5_FLASH.name]: GEMINI_2_5_FLASH.supports.input, + [GEMINI_4_ARGON.name]: GEMINI_4_ARGON.supports.input, } satisfies GeminiModelInputModalitiesByName // Reasoning diff --git a/packages/ai-openrouter/src/model-meta.ts b/packages/ai-openrouter/src/model-meta.ts index de2270f0b6..74d79bedf7 100644 --- a/packages/ai-openrouter/src/model-meta.ts +++ b/packages/ai-openrouter/src/model-meta.ts @@ -257,21 +257,19 @@ const _ANTHROPIC_CLAUDE_HAIKU_LATEST = { 'reasoning', 'responseFormat', 'stop', - 'temperature', 'toolChoice', - 'topP', ], }, - context_window: 200000, - max_output_tokens: 64000, + context_window: 1000000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 1, - cached: 1.35, + normal: 0.1, + cached: 0.135, }, output: { - normal: 5, + normal: 0.5, }, }, image: 0, @@ -290,7 +288,6 @@ const _ANTHROPIC_CLAUDE_OPUS_LATEST = { 'reasoning', 'responseFormat', 'stop', - 'temperature', 'toolChoice', ], }, @@ -322,7 +319,6 @@ const _ANTHROPIC_CLAUDE_SONNET_LATEST = { 'reasoning', 'responseFormat', 'stop', - 'temperature', 'toolChoice', ], }, @@ -332,7 +328,7 @@ const _ANTHROPIC_CLAUDE_SONNET_LATEST = { text: { input: { normal: 2, - cached: 2.7, + cached: 2.6, }, output: { normal: 10, @@ -353,6 +349,8 @@ const _DEEPSEEK_DEEPSEEK_FLASH_LATEST = { 'logitBias', 'logprobs', 'maxCompletionTokens', + 'maxCompletionTokens', + 'parallelToolCalls', 'presencePenalty', 'reasoning', 'responseFormat', @@ -369,11 +367,11 @@ const _DEEPSEEK_DEEPSEEK_FLASH_LATEST = { pricing: { text: { input: { - normal: 0.05, - cached: 0.02, + normal: 0.07, + cached: 0.008, }, output: { - normal: 1.2, + normal: 0.5, }, }, image: 0, @@ -403,15 +401,15 @@ const _DEEPSEEK_DEEPSEEK_PRO_LATEST = { ], }, context_window: 1048576, - max_output_tokens: 943718, + max_output_tokens: 393216, pricing: { text: { input: { - normal: 0.19, - cached: 0.18, + normal: 0.2235, + cached: 0.22, }, output: { - normal: 5, + normal: 8, }, }, image: 0, @@ -446,11 +444,11 @@ const _DEEPSEEK_DEEPSEEK_V4_FLASH_LATEST = { pricing: { text: { input: { - normal: 0.018, - cached: 0.018, + normal: 0.0475, + cached: 0.028, }, output: { - normal: 1.28, + normal: 0.1568, }, }, image: 0, @@ -508,15 +506,15 @@ const _GOOGLE_GEMINI_PRO_LATEST = { ], }, context_window: 1048576, - max_output_tokens: 65536, + max_output_tokens: 943718, pricing: { text: { input: { normal: 2, - cached: 0.575, + cached: 0.2875, }, output: { - normal: 12, + normal: 10, }, }, image: 0.000002, @@ -550,11 +548,11 @@ const _MOONSHOTAI_KIMI_LATEST = { pricing: { text: { input: { - normal: 0.61, - cached: 0.45, + normal: 0.238, + cached: 0.228, }, output: { - normal: 13, + normal: 16, }, }, image: 0, @@ -716,6 +714,29 @@ const _OPENAI_GPT_TERRA_LATEST = { }, reasoning: EFFORT_NONE_LOW_TO_MAX, } as const +const _UNBIASED_PARETO_LATEST = { + id: '~unbiased/pareto-latest', + name: 'Pareto Latest', + supports: { + input: ['text', 'image'], + output: ['text'], + supports: ['maxCompletionTokens', 'temperature', 'toolChoice', 'topP'], + }, + context_window: 1048576, + max_output_tokens: 131072, + pricing: { + text: { + input: { + normal: 0.8, + cached: 0.03, + }, + output: { + normal: 3.2, + }, + }, + image: 0, + }, +} as const const _X_AI_GROK_LATEST = { id: '~x-ai/grok-latest', name: 'xAI: Grok Latest', @@ -774,15 +795,15 @@ const _Z_AI_GLM_FLASH_LATEST = { ], }, context_window: 1048576, - max_output_tokens: 131072, + max_output_tokens: 943718, pricing: { text: { input: { - normal: 0.0278, - cached: 0.0278, + normal: 0.0052, + cached: 0.0052, }, output: { - normal: 0.5, + normal: 0.1985, }, }, image: 0, @@ -813,15 +834,15 @@ const _Z_AI_GLM_LATEST = { ], }, context_window: 1048576, - max_output_tokens: 131072, + max_output_tokens: 943718, pricing: { text: { input: { - normal: 0.063, - cached: 0.0585, + normal: 0.079, + cached: 0.078, }, output: { - normal: 6.3, + normal: 1.4, }, }, image: 0, @@ -1351,6 +1372,65 @@ const ANTHROPIC_CLAUDE_HAIKU_4_5_BATCH = { }, reasoning: EFFORT_OFF_TO_HIGH, } as const +const ANTHROPIC_CLAUDE_HAIKU_5_5 = { + id: 'anthropic/claude-haiku-5.5', + name: 'Anthropic: Claude Haiku 5.5', + supports: { + input: ['text', 'image', 'document'], + output: ['text'], + supports: [ + 'maxCompletionTokens', + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'stop', + 'toolChoice', + ], + }, + context_window: 1000000, + max_output_tokens: 128000, + pricing: { + text: { + input: { + normal: 0.1, + cached: 0.135, + }, + output: { + normal: 0.5, + }, + }, + image: 0, + }, +} as const +const ANTHROPIC_CLAUDE_HAIKU_5_5_BATCH = { + id: 'anthropic/claude-haiku-5.5:batch', + name: 'Anthropic: Claude Haiku 5.5 (batch)', + supports: { + input: ['text', 'image', 'document'], + output: ['text'], + supports: [ + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'stop', + 'toolChoice', + ], + }, + context_window: 1000000, + max_output_tokens: 128000, + pricing: { + text: { + input: { + normal: 0.05, + cached: 0.0675, + }, + output: { + normal: 0.25, + }, + }, + image: 0, + }, +} as const const ANTHROPIC_CLAUDE_OPUS_4_1 = { id: 'anthropic/claude-opus-4.1', name: 'Anthropic: Claude Opus 4.1', @@ -1614,7 +1694,6 @@ const ANTHROPIC_CLAUDE_OPUS_4_8 = { 'reasoning', 'responseFormat', 'stop', - 'temperature', 'toolChoice', ], }, @@ -1676,7 +1755,6 @@ const ANTHROPIC_CLAUDE_OPUS_5 = { 'reasoning', 'responseFormat', 'stop', - 'temperature', 'toolChoice', ], }, @@ -1738,7 +1816,6 @@ const ANTHROPIC_CLAUDE_OPUS_5_5 = { 'reasoning', 'responseFormat', 'stop', - 'temperature', 'toolChoice', ], }, @@ -1788,37 +1865,6 @@ const ANTHROPIC_CLAUDE_OPUS_5_5_BATCH = { }, reasoning: EFFORT_LOW_TO_MAX, } as const -const ANTHROPIC_CLAUDE_SONNET_4 = { - id: 'anthropic/claude-sonnet-4', - name: 'Anthropic: Claude Sonnet 4', - supports: { - input: ['image', 'text', 'document'], - output: ['text'], - supports: [ - 'maxCompletionTokens', - 'reasoning', - 'stop', - 'temperature', - 'toolChoice', - 'topP', - ], - }, - context_window: 200000, - max_output_tokens: 64000, - pricing: { - text: { - input: { - normal: 3, - cached: 4.05, - }, - output: { - normal: 15, - }, - }, - image: 0, - }, - reasoning: EFFORT_OFF_HIGH, -} as const const ANTHROPIC_CLAUDE_SONNET_4_5 = { id: 'anthropic/claude-sonnet-4.5', name: 'Anthropic: Claude Sonnet 4.5', @@ -2022,7 +2068,6 @@ const ANTHROPIC_CLAUDE_SONNET_5_5 = { 'reasoning', 'responseFormat', 'stop', - 'temperature', 'toolChoice', ], }, @@ -2032,7 +2077,7 @@ const ANTHROPIC_CLAUDE_SONNET_5_5 = { text: { input: { normal: 2, - cached: 2.7, + cached: 2.6, }, output: { normal: 10, @@ -2062,7 +2107,7 @@ const ANTHROPIC_CLAUDE_SONNET_5_5_BATCH = { text: { input: { normal: 1, - cached: 1.35, + cached: 1.3, }, output: { normal: 5, @@ -2072,40 +2117,6 @@ const ANTHROPIC_CLAUDE_SONNET_5_5_BATCH = { }, reasoning: EFFORT_LOW_TO_MAX, } as const -const APODEX_APODEX_1_1_MINI_FREE = { - id: 'apodex/apodex-1.1-mini:free', - name: 'Apodex: Apodex 1.1 Mini (free)', - supports: { - input: ['text'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'maxCompletionTokens', - 'presencePenalty', - 'reasoning', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'toolChoice', - 'topP', - ], - }, - context_window: 262144, - max_output_tokens: 235929, - pricing: { - text: { - input: { - normal: 0, - cached: 0, - }, - output: { - normal: 0, - }, - }, - image: 0, - }, -} as const const ARCEE_AI_TRINITY_LARGE_THINKING = { id: 'arcee-ai/trinity-large-thinking', name: 'Arcee AI: Trinity Large Thinking', @@ -2136,39 +2147,6 @@ const ARCEE_AI_TRINITY_LARGE_THINKING = { }, reasoning: EFFORT_MINIMAL_TO_HIGH, } as const -const BAIDU_ERNIE_4_5_VL_424B_A47B = { - id: 'baidu/ernie-4.5-vl-424b-a47b', - name: 'Baidu: ERNIE 4.5 VL 424B A47B ', - supports: { - input: ['image', 'text'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'maxCompletionTokens', - 'presencePenalty', - 'reasoning', - 'seed', - 'stop', - 'temperature', - 'topP', - ], - }, - context_window: 123000, - max_output_tokens: 16000, - pricing: { - text: { - input: { - normal: 0.42, - cached: 0, - }, - output: { - normal: 1.25, - }, - }, - image: 0, - }, - reasoning: EFFORT_OFF_HIGH, -} as const const BYTEDANCE_SEED_SEED_1_6 = { id: 'bytedance-seed/seed-1.6', name: 'ByteDance Seed: Seed 1.6', @@ -2735,41 +2713,6 @@ const DEEPSEEK_DEEPSEEK_CHAT_V3_1 = { }, reasoning: EFFORT_OFF_HIGH, } as const -const DEEPSEEK_DEEPSEEK_R1 = { - id: 'deepseek/deepseek-r1', - name: 'DeepSeek: R1', - supports: { - input: ['text'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'maxCompletionTokens', - 'presencePenalty', - 'reasoning', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'toolChoice', - 'topP', - ], - }, - context_window: 64000, - max_output_tokens: 16000, - pricing: { - text: { - input: { - normal: 0.7, - cached: 0, - }, - output: { - normal: 2.5, - }, - }, - image: 0, - }, - reasoning: EFFORT_MINIMAL_TO_HIGH, -} as const const DEEPSEEK_DEEPSEEK_R1_0528 = { id: 'deepseek/deepseek-r1-0528', name: 'DeepSeek: R1 0528', @@ -2935,15 +2878,15 @@ const DEEPSEEK_DEEPSEEK_V4_FLASH = { ], }, context_window: 1048576, - max_output_tokens: 943718, + max_output_tokens: 943717, pricing: { text: { input: { - normal: 0.03, - cached: 0.03, + normal: 0.091, + cached: 0.0182, }, output: { - normal: 1.28, + normal: 0.182, }, }, image: 0, @@ -2974,15 +2917,15 @@ const DEEPSEEK_DEEPSEEK_V4_FLASH_0731 = { ], }, context_window: 1048576, - max_output_tokens: 943718, + max_output_tokens: 131072, pricing: { text: { input: { - normal: 0.018, - cached: 0.018, + normal: 0.44, + cached: 0.014, }, output: { - normal: 1.28, + normal: 1.32, }, }, image: 0, @@ -3055,11 +2998,11 @@ const DEEPSEEK_DEEPSEEK_V4_PRO = { pricing: { text: { input: { - normal: 0.2088, - cached: 0.0174, + normal: 0.95526, + cached: 0.079605, }, output: { - normal: 0.4176, + normal: 1.91052, }, }, image: 0, @@ -3131,8 +3074,8 @@ const DEEPSEEK_DEEPSEEK_V4_1_FLASH = { pricing: { text: { input: { - normal: 0.05, - cached: 0.02, + normal: 0.3, + cached: 0.006, }, output: { normal: 1.2, @@ -3142,6 +3085,45 @@ const DEEPSEEK_DEEPSEEK_V4_1_FLASH = { }, reasoning: EFFORT_NONE_LOW_HIGH_MAX, } as const +const DEEPSEEK_DEEPSEEK_V4_1_FLASH_1017 = { + id: 'deepseek/deepseek-v4.1-flash-1017', + name: 'DeepSeek: DeepSeek V4.1 Flash 1017', + supports: { + input: ['text', 'image'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', + 'maxCompletionTokens', + 'maxCompletionTokens', + 'parallelToolCalls', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 1048576, + max_output_tokens: 393216, + pricing: { + text: { + input: { + normal: 0.15, + cached: 0.003, + }, + output: { + normal: 0.6, + }, + }, + image: 0, + }, +} as const const DEEPSEEK_DEEPSEEK_V4_1_FLASH_BATCH = { id: 'deepseek/deepseek-v4.1-flash:batch', name: 'DeepSeek: DeepSeek V4.1 Flash (batch)', @@ -3151,6 +3133,7 @@ const DEEPSEEK_DEEPSEEK_V4_1_FLASH_BATCH = { supports: [ 'frequencyPenalty', 'logitBias', + 'logprobs', 'maxCompletionTokens', 'presencePenalty', 'reasoning', @@ -3159,19 +3142,20 @@ const DEEPSEEK_DEEPSEEK_V4_1_FLASH_BATCH = { 'stop', 'temperature', 'toolChoice', + 'topLogprobs', 'topP', ], }, context_window: 1048576, - max_output_tokens: 131072, + max_output_tokens: 384000, pricing: { text: { input: { - normal: 0.112, - cached: 0.00336, + normal: 0.05, + cached: 0.004, }, output: { - normal: 0.336, + normal: 0.15, }, }, image: 0, @@ -3209,6 +3193,42 @@ const DOTS_STUDIO_DOTS_3_NOTE_PREVIEW_FREE = { }, reasoning: EFFORT_OFF_HIGH, } as const +const ELORIAN_GLIMPSE = { + id: 'elorian/glimpse', + name: 'Elorian: Glimpse', + supports: { + input: ['text', 'image', 'video'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 262144, + max_output_tokens: 256000, + pricing: { + text: { + input: { + normal: 0.6, + cached: 0.06, + }, + output: { + normal: 3, + }, + }, + image: 0, + }, +} as const const FIREWORKS_EMBER_1 = { id: 'fireworks/ember-1', name: 'Fireworks: Ember-1', @@ -3342,72 +3362,6 @@ const GOOGLE_GEMINI_2_5_FLASH_LITE = { }, reasoning: EFFORT_OFF_HIGH, } as const -const GOOGLE_GEMINI_2_5_FLASH_LITE_BATCH = { - id: 'google/gemini-2.5-flash-lite:batch', - name: 'Google: Gemini 2.5 Flash Lite (batch)', - supports: { - input: ['text', 'image', 'document', 'audio', 'video'], - output: ['text'], - supports: [ - 'maxCompletionTokens', - 'reasoning', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'toolChoice', - 'topP', - ], - }, - context_window: 1048576, - max_output_tokens: 65535, - pricing: { - text: { - input: { - normal: 0.05, - cached: 0.01, - }, - output: { - normal: 0.2, - }, - }, - image: 5e-8, - }, - reasoning: EFFORT_OFF_TO_HIGH, -} as const -const GOOGLE_GEMINI_2_5_FLASH_BATCH = { - id: 'google/gemini-2.5-flash:batch', - name: 'Google: Gemini 2.5 Flash (batch)', - supports: { - input: ['document', 'image', 'text', 'audio', 'video'], - output: ['text'], - supports: [ - 'maxCompletionTokens', - 'reasoning', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'toolChoice', - 'topP', - ], - }, - context_window: 1048576, - max_output_tokens: 65535, - pricing: { - text: { - input: { - normal: 0.15, - cached: 0.03, - }, - output: { - normal: 1.25, - }, - }, - image: 1.5e-7, - }, - reasoning: EFFORT_OFF_TO_HIGH, -} as const const GOOGLE_GEMINI_2_5_PRO = { id: 'google/gemini-2.5-pro', name: 'Google: Gemini 2.5 Pro', @@ -3419,7 +3373,6 @@ const GOOGLE_GEMINI_2_5_PRO = { 'reasoning', 'responseFormat', 'seed', - 'stop', 'temperature', 'toolChoice', 'topP', @@ -3474,39 +3427,6 @@ const GOOGLE_GEMINI_2_5_PRO_PREVIEW = { }, reasoning: BUDGET_MINIMAL_TO_HIGH, } as const -const GOOGLE_GEMINI_2_5_PRO_BATCH = { - id: 'google/gemini-2.5-pro:batch', - name: 'Google: Gemini 2.5 Pro (batch)', - supports: { - input: ['text', 'image', 'document', 'audio', 'video'], - output: ['text'], - supports: [ - 'maxCompletionTokens', - 'reasoning', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'toolChoice', - 'topP', - ], - }, - context_window: 1048576, - max_output_tokens: 65536, - pricing: { - text: { - input: { - normal: 0.625, - cached: 0.125, - }, - output: { - normal: 5, - }, - }, - image: 6.25e-7, - }, - reasoning: EFFORT_MINIMAL_TO_HIGH, -} as const const GOOGLE_GEMINI_3_FLASH_PREVIEW = { id: 'google/gemini-3-flash-preview', name: 'Google: Gemini 3 Flash Preview', @@ -4207,14 +4127,14 @@ const GOOGLE_GEMINI_3_8_FLASH = { pricing: { text: { input: { - normal: 0.75, - cached: 0.1166666667, + normal: 0.825, + cached: 0.12416666670000001, }, output: { - normal: 3.75, + normal: 4.125, }, }, - image: 7.5e-7, + image: 8.25e-7, }, reasoning: EFFORT_LOW_TO_HIGH, } as const @@ -4249,6 +4169,70 @@ const GOOGLE_GEMINI_3_8_FLASH_BATCH = { }, reasoning: EFFORT_LOW_TO_HIGH, } as const +const GOOGLE_GEMINI_4_ARGON = { + id: 'google/gemini-4-argon', + name: 'Google: Gemini 4 Argon', + supports: { + input: ['audio', 'document', 'image', 'text', 'video'], + output: ['text'], + supports: [ + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topP', + ], + }, + context_window: 1048576, + max_output_tokens: 943718, + pricing: { + text: { + input: { + normal: 2, + cached: 0.2875, + }, + output: { + normal: 10, + }, + }, + image: 0.000002, + }, +} as const +const GOOGLE_GEMINI_4_ARGON_BATCH = { + id: 'google/gemini-4-argon:batch', + name: 'Google: Gemini 4 Argon (batch)', + supports: { + input: ['audio', 'document', 'image', 'text', 'video'], + output: ['text'], + supports: [ + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topP', + ], + }, + context_window: 1048576, + max_output_tokens: 943718, + pricing: { + text: { + input: { + normal: 1, + cached: 0.2375, + }, + output: { + normal: 5, + }, + }, + image: 0.000001, + }, +} as const const GOOGLE_GEMINI_NANO_BANANA_2_1 = { id: 'google/gemini-nano-banana-2.1', name: 'Google: Nano Banana 2.1', @@ -4376,7 +4360,7 @@ const GOOGLE_GEMMA_3_27B_IT = { cached: 0.04, }, output: { - normal: 0.45, + normal: 0.35, }, }, image: 0, @@ -4391,25 +4375,27 @@ const GOOGLE_GEMMA_3_4B_IT = { supports: [ 'frequencyPenalty', 'logitBias', + 'logprobs', 'maxCompletionTokens', 'presencePenalty', 'responseFormat', 'seed', 'stop', 'temperature', + 'topLogprobs', 'topP', ], }, context_window: 131072, - max_output_tokens: 16384, + max_output_tokens: 117964, pricing: { text: { input: { - normal: 0.05, - cached: 0, + normal: 0.04, + cached: 0.02, }, output: { - normal: 0.1, + normal: 0.05, }, }, image: 0, @@ -4512,11 +4498,11 @@ const GOOGLE_GEMMA_4_31B_IT = { pricing: { text: { input: { - normal: 0.09, - cached: 0.05, + normal: 0.2, + cached: 0, }, output: { - normal: 0.34, + normal: 0.4, }, }, image: 0, @@ -4783,47 +4769,39 @@ const INCEPTION_MERCURY_2_5 = { }, reasoning: EFFORT_NONE_LOW_TO_HIGH, } as const -const INCLUSIONAI_LING_3_0_FLASH = { - id: 'inclusionai/ling-3.0-flash', - name: 'inclusionAI: Ling 3.0 Flash', +const INCEPTION_MERCURY_3 = { + id: 'inception/mercury-3', + name: 'Inception: Mercury 3', supports: { input: ['text'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', 'reasoning', 'responseFormat', - 'seed', 'stop', 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 262144, - max_output_tokens: 32768, + context_window: 1000000, + max_output_tokens: 131072, pricing: { text: { input: { - normal: 0.021, - cached: 0.0042, + normal: 0.1, + cached: 0.01, }, output: { - normal: 0.063, + normal: 0.35, }, }, image: 0, }, - reasoning: EFFORT_OFF_HIGH, } as const -const INCLUSIONAI_LING_3_0_FLASH_FIN = { - id: 'inclusionai/ling-3.0-flash-fin', - name: 'inclusionAI: Ling 3.0 Flash Fin', +const INCLUSIONAI_LING_3_0_FLASH = { + id: 'inclusionai/ling-3.0-flash', + name: 'inclusionAI: Ling 3.0 Flash', supports: { input: ['text'], output: ['text'], @@ -4834,6 +4812,7 @@ const INCLUSIONAI_LING_3_0_FLASH_FIN = { 'maxCompletionTokens', 'presencePenalty', 'reasoning', + 'responseFormat', 'seed', 'stop', 'temperature', @@ -4847,47 +4826,11 @@ const INCLUSIONAI_LING_3_0_FLASH_FIN = { pricing: { text: { input: { - normal: 0.042, - cached: 0.0084, - }, - output: { - normal: 0.1232, - }, - }, - image: 0, - }, - reasoning: EFFORT_OFF_HIGH, -} as const -const INCLUSIONAI_LING_3_0_FLASH_SANTE_FREE = { - id: 'inclusionai/ling-3.0-flash-sante:free', - name: 'inclusionAI: Ling 3.0 Flash Sante (free)', - supports: { - input: ['text'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'logprobs', - 'maxCompletionTokens', - 'presencePenalty', - 'reasoning', - 'seed', - 'stop', - 'temperature', - 'toolChoice', - 'topLogprobs', - 'topP', - ], - }, - context_window: 262144, - max_output_tokens: 32768, - pricing: { - text: { - input: { - normal: 0, - cached: 0, + normal: 0.021, + cached: 0.0042, }, output: { - normal: 0, + normal: 0.063, }, }, image: 0, @@ -4903,7 +4846,6 @@ const INCLUSIONAI_LING_3_0_FLASH_VL = { supports: [ 'frequencyPenalty', 'logitBias', - 'logprobs', 'maxCompletionTokens', 'presencePenalty', 'reasoning', @@ -4912,20 +4854,19 @@ const INCLUSIONAI_LING_3_0_FLASH_VL = { 'stop', 'temperature', 'toolChoice', - 'topLogprobs', 'topP', ], }, - context_window: 262144, + context_window: 131072, max_output_tokens: 32768, pricing: { text: { input: { - normal: 0.021, - cached: 0.0042, + normal: 0.06, + cached: 0.012, }, output: { - normal: 0.0616, + normal: 0.18, }, }, image: 0, @@ -4940,10 +4881,12 @@ const INCLUSIONAI_LING_3_1_FLASH = { output: ['text'], supports: [ 'frequencyPenalty', + 'logitBias', 'logprobs', 'maxCompletionTokens', 'presencePenalty', 'reasoning', + 'responseFormat', 'seed', 'stop', 'temperature', @@ -4953,15 +4896,15 @@ const INCLUSIONAI_LING_3_1_FLASH = { ], }, context_window: 262144, - max_output_tokens: 32768, + max_output_tokens: 235929, pricing: { text: { input: { - normal: 0, - cached: 0, + normal: 0.075, + cached: 0.015, }, output: { - normal: 0, + normal: 0.225, }, }, image: 0, @@ -5052,7 +4995,6 @@ const LIQUID_LFM_2_5_2_6B_FREE = { 'temperature', 'toolChoice', 'topLogprobs', - 'topP', ], }, context_window: 65536, @@ -5071,6 +5013,42 @@ const LIQUID_LFM_2_5_2_6B_FREE = { }, reasoning: EFFORT_MINIMAL_TO_HIGH, } as const +const LIQUID_LFM_2_5_24B_A2B = { + id: 'liquid/lfm-2.5-24b-a2b', + name: 'LiquidAI: LFM2.5-24B-A2B', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logprobs', + 'maxCompletionTokens', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + ], + }, + context_window: 128000, + max_output_tokens: 8192, + pricing: { + text: { + input: { + normal: 0.05, + cached: 0.025, + }, + output: { + normal: 0.7, + }, + }, + image: 0, + }, +} as const const MANCER_WEAVER = { id: 'mancer/weaver', name: 'Mancer: Weaver (alpha)', @@ -5263,15 +5241,15 @@ const META_LLAMA_LLAMA_3_2_3B_INSTRUCT = { ], }, context_window: 131072, - max_output_tokens: 117964, + max_output_tokens: 72000, pricing: { text: { input: { - normal: 0.05, + normal: 0.0509, cached: 0, }, output: { - normal: 0.33, + normal: 0.335, }, }, image: 0, @@ -5303,11 +5281,11 @@ const META_LLAMA_LLAMA_3_3_70B_INSTRUCT = { pricing: { text: { input: { - normal: 0.22, - cached: 0.11, + normal: 0.1, + cached: 0, }, output: { - normal: 0.5, + normal: 0.32, }, }, image: 0, @@ -5334,7 +5312,7 @@ const META_LLAMA_LLAMA_4_MAVERICK = { 'topP', ], }, - context_window: 1048576, + context_window: 524288, max_output_tokens: 16384, pricing: { text: { @@ -5606,47 +5584,82 @@ const META_MUSE_SPARK_1_3_CONTRIBUTOR = { }, reasoning: EFFORT_MINIMAL_TO_MAX, } as const -const MICROSOFT_PHI_4 = { - id: 'microsoft/phi-4', - name: 'Microsoft: Phi 4', +const META_MUSE_SPARK_OPEN = { + id: 'meta/muse-spark-open', + name: 'Meta: Muse Spark Open', supports: { - input: ['text'], + input: ['text', 'image', 'video', 'document', 'audio'], output: ['text'], supports: [ 'frequencyPenalty', 'logitBias', + 'logprobs', 'maxCompletionTokens', 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', 'stop', 'temperature', + 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 16384, - max_output_tokens: 14745, + context_window: 1048576, + max_output_tokens: 943718, pricing: { text: { input: { - normal: 0.07, - cached: 0, + normal: 1.25, + cached: 0.15, }, output: { - normal: 0.14, + normal: 4.25, + }, + }, + image: 0, + }, +} as const +const META_MUSE_WONDER = { + id: 'meta/muse-wonder', + name: 'Meta: Muse Wonder', + supports: { + input: ['text', 'image', 'video', 'document', 'audio'], + output: ['text'], + supports: [ + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'temperature', + 'toolChoice', + 'topP', + ], + }, + context_window: 1048576, + max_output_tokens: 943718, + pricing: { + text: { + input: { + normal: 4, + cached: 0.2, + }, + output: { + normal: 20, }, }, image: 0, }, } as const -const MICROSOFT_WIZARDLM_2_8X22B = { - id: 'microsoft/wizardlm-2-8x22b', - name: 'WizardLM-2 8x22B', +const MICROSOFT_PHI_4 = { + id: 'microsoft/phi-4', + name: 'Microsoft: Phi 4', supports: { input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', + 'logitBias', 'maxCompletionTokens', 'presencePenalty', 'responseFormat', @@ -5656,16 +5669,16 @@ const MICROSOFT_WIZARDLM_2_8X22B = { 'topP', ], }, - context_window: 65535, - max_output_tokens: 8000, + context_window: 16384, + max_output_tokens: 14745, pricing: { text: { input: { - normal: 0.62, + normal: 0.07, cached: 0, }, output: { - normal: 0.62, + normal: 0.14, }, }, image: 0, @@ -5750,15 +5763,15 @@ const MINIMAX_MINIMAX_M2 = { ], }, context_window: 204800, - max_output_tokens: 176947, + max_output_tokens: 131072, pricing: { text: { input: { - normal: 0.3, + normal: 0.255, cached: 0, }, output: { - normal: 1.2, + normal: 1.02, }, }, image: 0, @@ -5795,13 +5808,9 @@ const MINIMAX_MINIMAX_M2_1 = { input: ['text'], output: ['text'], supports: [ - 'frequencyPenalty', 'maxCompletionTokens', - 'presencePenalty', 'reasoning', 'responseFormat', - 'seed', - 'stop', 'temperature', 'toolChoice', 'topP', @@ -5846,15 +5855,15 @@ const MINIMAX_MINIMAX_M2_5 = { ], }, context_window: 204800, - max_output_tokens: 128000, + max_output_tokens: 32768, pricing: { text: { input: { normal: 0.27, - cached: 0.027, + cached: 0.03, }, output: { - normal: 1.08, + normal: 0.95, }, }, image: 0, @@ -5882,15 +5891,15 @@ const MINIMAX_MINIMAX_M2_7 = { ], }, context_window: 204800, - max_output_tokens: 176947, + max_output_tokens: 131072, pricing: { text: { input: { - normal: 0.21, - cached: 0.042, + normal: 0.3, + cached: 0.06, }, output: { - normal: 0.84, + normal: 1.2, }, }, image: 0, @@ -5935,6 +5944,36 @@ const MINIMAX_MINIMAX_M3 = { }, reasoning: EFFORT_OFF_HIGH, } as const +const MINIMAX_MINIMAX_M3_1_FLASH_FREE = { + id: 'minimax/minimax-m3.1-flash:free', + name: 'MiniMax: MiniMax M3.1 Flash (free)', + supports: { + input: ['text', 'image', 'video'], + output: ['text'], + supports: [ + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'temperature', + 'toolChoice', + 'topP', + ], + }, + context_window: 1000000, + max_output_tokens: 524288, + pricing: { + text: { + input: { + normal: 0, + cached: 0, + }, + output: { + normal: 0, + }, + }, + image: 0, + }, +} as const const MISTRALAI_CODESTRAL_2508 = { id: 'mistralai/codestral-2508', name: 'Mistral: Codestral 2508', @@ -6319,16 +6358,16 @@ const MISTRALAI_MISTRAL_LARGE_4_0 = { 'topP', ], }, - context_window: 524288, + context_window: 1048576, max_output_tokens: 262144, pricing: { text: { input: { - normal: 0.68, - cached: 0.07, + normal: 1.36, + cached: 0.14, }, output: { - normal: 2.09, + normal: 4.18, }, }, image: 0, @@ -6529,7 +6568,7 @@ const MISTRALAI_MISTRAL_NEMO = { pricing: { text: { input: { - normal: 0.019, + normal: 0.029, cached: 0, }, output: { @@ -6812,62 +6851,55 @@ const MISTRALAI_VOXTRAL_SMALL_24B_2507 = { image: 0, }, } as const -const MOONSHOTAI_KIMI_K2 = { - id: 'moonshotai/kimi-k2', - name: 'MoonshotAI: Kimi K2 0711', +const MOONDREAM_MOONDREAM3_PREVIEW = { + id: 'moondream/moondream3-preview', + name: 'Moondream: Moondream 3 Preview', supports: { - input: ['text'], + input: ['text', 'image'], output: ['text'], supports: [ - 'frequencyPenalty', 'maxCompletionTokens', - 'presencePenalty', - 'seed', - 'stop', + 'maxCompletionTokens', + 'reasoning', 'temperature', - 'toolChoice', 'topP', ], }, - context_window: 131072, - max_output_tokens: 98304, + context_window: 32000, + max_output_tokens: 4096, pricing: { text: { input: { - normal: 0.57, + normal: 0.3, cached: 0, }, output: { - normal: 2.3, + normal: 2.5, }, }, image: 0, }, } as const -const MOONSHOTAI_KIMI_K2_0905 = { - id: 'moonshotai/kimi-k2-0905', - name: 'MoonshotAI: Kimi K2 0905', +const MOONDREAM_MOONDREAM3_1_9B_A2B = { + id: 'moondream/moondream3.1-9b-a2b', + name: 'Moondream: Moondream 3.1', supports: { - input: ['text'], + input: ['text', 'image'], output: ['text'], supports: [ - 'frequencyPenalty', 'maxCompletionTokens', - 'presencePenalty', - 'responseFormat', - 'seed', - 'stop', + 'maxCompletionTokens', + 'reasoning', 'temperature', - 'toolChoice', 'topP', ], }, - context_window: 262144, - max_output_tokens: 98304, + context_window: 32000, + max_output_tokens: 4096, pricing: { text: { input: { - normal: 0.6, + normal: 0.3, cached: 0, }, output: { @@ -6877,29 +6909,58 @@ const MOONSHOTAI_KIMI_K2_0905 = { image: 0, }, } as const -const MOONSHOTAI_KIMI_K2_THINKING = { - id: 'moonshotai/kimi-k2-thinking', - name: 'MoonshotAI: Kimi K2 Thinking', +const MOONSHOTAI_KIMI_K2 = { + id: 'moonshotai/kimi-k2', + name: 'MoonshotAI: Kimi K2 0711', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'maxCompletionTokens', + 'presencePenalty', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topP', + ], + }, + context_window: 131072, + max_output_tokens: 98304, + pricing: { + text: { + input: { + normal: 0.57, + cached: 0, + }, + output: { + normal: 2.3, + }, + }, + image: 0, + }, +} as const +const MOONSHOTAI_KIMI_K2_0905 = { + id: 'moonshotai/kimi-k2-0905', + name: 'MoonshotAI: Kimi K2 0905', supports: { input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', - 'logprobs', 'maxCompletionTokens', 'presencePenalty', - 'reasoning', 'responseFormat', 'seed', 'stop', 'temperature', 'toolChoice', - 'topLogprobs', 'topP', ], }, context_window: 262144, - max_output_tokens: 235929, + max_output_tokens: 98304, pricing: { text: { input: { @@ -6912,6 +6973,42 @@ const MOONSHOTAI_KIMI_K2_THINKING = { }, image: 0, }, +} as const +const MOONSHOTAI_KIMI_K2_THINKING = { + id: 'moonshotai/kimi-k2-thinking', + name: 'MoonshotAI: Kimi K2 Thinking', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 262144, + max_output_tokens: 98304, + pricing: { + text: { + input: { + normal: 0.6, + cached: 0.15, + }, + output: { + normal: 2.5, + }, + }, + image: 0, + }, reasoning: EFFORT_MINIMAL_TO_HIGH, } as const const MOONSHOTAI_KIMI_K2_5 = { @@ -6941,11 +7038,11 @@ const MOONSHOTAI_KIMI_K2_5 = { pricing: { text: { input: { - normal: 0.45, - cached: 0.07, + normal: 0.5, + cached: 0.15, }, output: { - normal: 2.25, + normal: 2.5, }, }, image: 0, @@ -6980,11 +7077,11 @@ const MOONSHOTAI_KIMI_K2_6 = { pricing: { text: { input: { - normal: 0.465, - cached: 0.0975, + normal: 0.65, + cached: 0.15, }, output: { - normal: 2.45, + normal: 3.41, }, }, image: 0, @@ -7057,11 +7154,11 @@ const MOONSHOTAI_KIMI_K3 = { pricing: { text: { input: { - normal: 0.62, - cached: 0.43, + normal: 0.239, + cached: 0.21, }, output: { - normal: 15, + normal: 11.936, }, }, image: 0, @@ -7110,10 +7207,17 @@ const MORPH_MORPH_V3_FAST = { supports: { input: ['text'], output: ['text'], - supports: ['maxCompletionTokens', 'stop', 'temperature'], + supports: [ + 'logprobs', + 'maxCompletionTokens', + 'responseFormat', + 'stop', + 'temperature', + 'topLogprobs', + ], }, - context_window: 81920, - max_output_tokens: 38000, + context_window: 262144, + max_output_tokens: 131072, pricing: { text: { input: { @@ -7293,11 +7397,13 @@ const NOUSRESEARCH_HERMES_4_405B = { output: ['text'], supports: [ 'frequencyPenalty', + 'logprobs', 'maxCompletionTokens', 'presencePenalty', 'reasoning', 'responseFormat', 'temperature', + 'topLogprobs', 'topP', ], }, @@ -7344,11 +7450,11 @@ const NVIDIA_NEMOTRON_3_NANO_30B_A3B = { pricing: { text: { input: { - normal: 0.05, - cached: 0.03, + normal: 0.06, + cached: 0, }, output: { - normal: 0.2, + normal: 0.24, }, }, image: 0, @@ -7413,11 +7519,11 @@ const NVIDIA_NEMOTRON_3_SUPER_120B_A12B = { pricing: { text: { input: { - normal: 0.08, - cached: 0, + normal: 0.3, + cached: 0.15, }, output: { - normal: 0.45, + normal: 2.4, }, }, image: 0, @@ -7477,15 +7583,15 @@ const NVIDIA_NEMOTRON_3_ULTRA_550B_A55B = { ], }, context_window: 262144, - max_output_tokens: 16384, + max_output_tokens: 182520, pricing: { text: { input: { - normal: 0.5, - cached: 0.1, + normal: 0.6, + cached: 0.12, }, output: { - normal: 2.2, + normal: 2.4, }, }, image: 0, @@ -7610,15 +7716,15 @@ const NVIDIA_NEMOTRON_3_5_LIGHTNING = { ], }, context_window: 262144, - max_output_tokens: 32768, + max_output_tokens: 235929, pricing: { text: { input: { - normal: 0.06, - cached: 0.03, + normal: 0.07, + cached: 0.04, }, output: { - normal: 0.16, + normal: 0.2, }, }, image: 0, @@ -7656,6 +7762,74 @@ const NVIDIA_NEMOTRON_3_5_LIGHTNING_FREE = { }, reasoning: EFFORT_OFF_HIGH, } as const +const NVIDIA_NEMOTRON_3_5_SUPER_VL = { + id: 'nvidia/nemotron-3.5-super-vl', + name: 'NVIDIA: Nemotron 3.5 Super VL', + supports: { + input: ['text', 'image', 'video'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 1048576, + max_output_tokens: 235929, + pricing: { + text: { + input: { + normal: 0.15, + cached: 0.02, + }, + output: { + normal: 0.5, + }, + }, + image: 0, + }, +} as const +const NVIDIA_NEMOTRON_3_5_SUPER_VL_FREE = { + id: 'nvidia/nemotron-3.5-super-vl:free', + name: 'NVIDIA: Nemotron 3.5 Super VL (free)', + supports: { + input: ['text', 'image', 'video'], + output: ['text'], + supports: [ + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'seed', + 'temperature', + 'toolChoice', + 'topP', + ], + }, + context_window: 1000000, + max_output_tokens: 131072, + pricing: { + text: { + input: { + normal: 0, + cached: 0, + }, + output: { + normal: 0, + }, + }, + image: 0, + }, +} as const const OPENAI_GPT_3_5_TURBO = { id: 'openai/gpt-3.5-turbo', name: 'OpenAI: GPT-3.5 Turbo', @@ -9623,11 +9797,11 @@ const OPENAI_GPT_5_6_SOL = { pricing: { text: { input: { - normal: 2, - cached: 2.7, + normal: 4, + cached: 5.4, }, output: { - normal: 10, + normal: 20, }, }, image: 0, @@ -9654,11 +9828,11 @@ const OPENAI_GPT_5_6_SOL_PRO = { pricing: { text: { input: { - normal: 2, - cached: 2.7, + normal: 4, + cached: 5.4, }, output: { - normal: 10, + normal: 20, }, }, image: 0, @@ -9684,11 +9858,11 @@ const OPENAI_GPT_5_6_SOL_PRO_BATCH = { pricing: { text: { input: { - normal: 1, - cached: 1.35, + normal: 2, + cached: 2.7, }, output: { - normal: 5, + normal: 10, }, }, image: 0, @@ -9714,11 +9888,11 @@ const OPENAI_GPT_5_6_SOL_BATCH = { pricing: { text: { input: { - normal: 1, - cached: 1.35, + normal: 2, + cached: 2.7, }, output: { - normal: 5, + normal: 10, }, }, image: 0, @@ -10275,6 +10449,64 @@ const OPENAI_GPT_6_1_SOL_PRO = { }, reasoning: EFFORT_LOW_TO_MAX, } as const +const OPENAI_GPT_6_1_SOL_PRO_BATCH = { + id: 'openai/gpt-6.1-sol-pro:batch', + name: 'OpenAI: GPT-6.1 Sol Pro (batch)', + supports: { + input: ['document', 'image', 'text'], + output: ['text'], + supports: [ + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'seed', + 'toolChoice', + ], + }, + context_window: 1050000, + max_output_tokens: 128000, + pricing: { + text: { + input: { + normal: 1, + cached: 1.3, + }, + output: { + normal: 5, + }, + }, + image: 0, + }, +} as const +const OPENAI_GPT_6_1_SOL_BATCH = { + id: 'openai/gpt-6.1-sol:batch', + name: 'OpenAI: GPT-6.1 Sol (batch)', + supports: { + input: ['document', 'image', 'text'], + output: ['text'], + supports: [ + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'seed', + 'toolChoice', + ], + }, + context_window: 1050000, + max_output_tokens: 128000, + pricing: { + text: { + input: { + normal: 1, + cached: 1.3, + }, + output: { + normal: 5, + }, + }, + image: 0, + }, +} as const const OPENAI_GPT_AUDIO = { id: 'openai/gpt-audio', name: 'OpenAI: GPT Audio', @@ -10393,15 +10625,15 @@ const OPENAI_GPT_OSS_120B = { ], }, context_window: 131072, - max_output_tokens: 117964, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0.037, - cached: 0, - }, + normal: 0.15, + cached: 0.075, + }, output: { - normal: 0.17, + normal: 0.6, }, }, image: 0, @@ -11357,41 +11589,6 @@ const QWEN_QWEN_PLUS = { image: 0, }, } as const -const QWEN_QWEN_PLUS_2025_07_28 = { - id: 'qwen/qwen-plus-2025-07-28', - name: 'Qwen: Qwen Plus 0728', - supports: { - input: ['text'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'logprobs', - 'maxCompletionTokens', - 'presencePenalty', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'toolChoice', - 'topLogprobs', - 'topP', - ], - }, - context_window: 1000000, - max_output_tokens: 32768, - pricing: { - text: { - input: { - normal: 0.26, - cached: 0, - }, - output: { - normal: 0.78, - }, - }, - image: 0, - }, -} as const const QWEN_QWEN2_5_VL_72B_INSTRUCT = { id: 'qwen/qwen2.5-vl-72b-instruct', name: 'Qwen: Qwen2.5 VL 72B Instruct', @@ -11449,7 +11646,7 @@ const QWEN_QWEN3_14B = { 'topP', ], }, - context_window: 131072, + context_window: 40960, max_output_tokens: 16384, pricing: { text: { @@ -11465,41 +11662,6 @@ const QWEN_QWEN3_14B = { }, reasoning: EFFORT_OFF_HIGH, } as const -const QWEN_QWEN3_235B_A22B = { - id: 'qwen/qwen3-235b-a22b', - name: 'Qwen: Qwen3 235B A22B', - supports: { - input: ['text'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'maxCompletionTokens', - 'presencePenalty', - 'reasoning', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'toolChoice', - 'topP', - ], - }, - context_window: 131072, - max_output_tokens: 8192, - pricing: { - text: { - input: { - normal: 0.455, - cached: 0, - }, - output: { - normal: 1.82, - }, - }, - image: 0, - }, - reasoning: EFFORT_OFF_HIGH, -} as const const QWEN_QWEN3_235B_A22B_2507 = { id: 'qwen/qwen3-235b-a22b-2507', name: 'Qwen: Qwen3 235B A22B Instruct 2507', @@ -11544,29 +11706,25 @@ const QWEN_QWEN3_235B_A22B_THINKING_2507 = { output: ['text'], supports: [ 'frequencyPenalty', - 'logprobs', 'maxCompletionTokens', 'presencePenalty', 'reasoning', - 'responseFormat', - 'seed', 'stop', 'temperature', 'toolChoice', - 'topLogprobs', 'topP', ], }, - context_window: 131072, - max_output_tokens: 117964, + context_window: 128000, + max_output_tokens: 16384, pricing: { text: { input: { - normal: 0.23, + normal: 0.45, cached: 0, }, output: { - normal: 2.3, + normal: 3.5, }, }, image: 0, @@ -11593,7 +11751,7 @@ const QWEN_QWEN3_30B_A3B = { 'topP', ], }, - context_window: 131072, + context_window: 40960, max_output_tokens: 16384, pricing: { text: { @@ -11631,54 +11789,19 @@ const QWEN_QWEN3_30B_A3B_INSTRUCT_2507 = { ], }, context_window: 262144, - max_output_tokens: 32000, - pricing: { - text: { - input: { - normal: 0.04815, - cached: 0, - }, - output: { - normal: 0.19305, - }, - }, - image: 0, - }, -} as const -const QWEN_QWEN3_30B_A3B_THINKING_2507 = { - id: 'qwen/qwen3-30b-a3b-thinking-2507', - name: 'Qwen: Qwen3 30B A3B Thinking 2507', - supports: { - input: ['text'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'maxCompletionTokens', - 'presencePenalty', - 'reasoning', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'toolChoice', - 'topP', - ], - }, - context_window: 81920, - max_output_tokens: 32768, + max_output_tokens: 235929, pricing: { text: { input: { - normal: 0.2, + normal: 0.09, cached: 0, }, output: { - normal: 2.4, + normal: 0.3, }, }, image: 0, }, - reasoning: EFFORT_MINIMAL_TO_HIGH, } as const const QWEN_QWEN3_32B = { id: 'qwen/qwen3-32b', @@ -11718,41 +11841,6 @@ const QWEN_QWEN3_32B = { }, reasoning: EFFORT_OFF_HIGH, } as const -const QWEN_QWEN3_8B = { - id: 'qwen/qwen3-8b', - name: 'Qwen: Qwen3 8B', - supports: { - input: ['text'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'maxCompletionTokens', - 'presencePenalty', - 'reasoning', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'toolChoice', - 'topP', - ], - }, - context_window: 131072, - max_output_tokens: 8192, - pricing: { - text: { - input: { - normal: 0.117, - cached: 0, - }, - output: { - normal: 0.455, - }, - }, - image: 0, - }, - reasoning: EFFORT_OFF_HIGH, -} as const const QWEN_QWEN3_CODER = { id: 'qwen/qwen3-coder', name: 'Qwen: Qwen3 Coder 480B A35B', @@ -11797,15 +11885,11 @@ const QWEN_QWEN3_CODER_30B_A3B_INSTRUCT = { output: ['text'], supports: [ 'frequencyPenalty', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', 'responseFormat', - 'seed', 'stop', 'temperature', 'toolChoice', - 'topLogprobs', 'topP', ], }, @@ -11895,113 +11979,6 @@ const QWEN_QWEN3_CODER_NEXT = { image: 0, }, } as const -const QWEN_QWEN3_CODER_PLUS = { - id: 'qwen/qwen3-coder-plus', - name: 'Qwen: Qwen3 Coder Plus', - supports: { - input: ['text'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'logprobs', - 'maxCompletionTokens', - 'presencePenalty', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'toolChoice', - 'topLogprobs', - 'topP', - ], - }, - context_window: 1000000, - max_output_tokens: 65536, - pricing: { - text: { - input: { - normal: 0.65, - cached: 0.9425, - }, - output: { - normal: 3.25, - }, - }, - image: 0, - }, -} as const -const QWEN_QWEN3_MAX = { - id: 'qwen/qwen3-max', - name: 'Qwen: Qwen3 Max', - supports: { - input: ['text'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'logprobs', - 'maxCompletionTokens', - 'presencePenalty', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'toolChoice', - 'topLogprobs', - 'topP', - ], - }, - context_window: 262144, - max_output_tokens: 65536, - pricing: { - text: { - input: { - normal: 0.78, - cached: 1.131, - }, - output: { - normal: 3.9, - }, - }, - image: 0, - }, -} as const -const QWEN_QWEN3_MAX_THINKING = { - id: 'qwen/qwen3-max-thinking', - name: 'Qwen: Qwen3 Max Thinking', - supports: { - input: ['text'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'logprobs', - 'maxCompletionTokens', - 'presencePenalty', - 'reasoning', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'toolChoice', - 'topLogprobs', - 'topP', - ], - }, - context_window: 262144, - max_output_tokens: 65536, - pricing: { - text: { - input: { - normal: 0.78, - cached: 0, - }, - output: { - normal: 3.9, - }, - }, - image: 0, - }, - reasoning: EFFORT_OFF_HIGH, -} as const const QWEN_QWEN3_NEXT_80B_A3B_INSTRUCT = { id: 'qwen/qwen3-next-80b-a3b-instruct', name: 'Qwen: Qwen3 Next 80B A3B Instruct', @@ -12024,12 +12001,12 @@ const QWEN_QWEN3_NEXT_80B_A3B_INSTRUCT = { ], }, context_window: 262144, - max_output_tokens: 235929, + max_output_tokens: 16384, pricing: { text: { input: { - normal: 0.1, - cached: 0.07, + normal: 0.09, + cached: 0, }, output: { normal: 1.1, @@ -12060,7 +12037,7 @@ const QWEN_QWEN3_NEXT_80B_A3B_THINKING = { ], }, context_window: 262144, - max_output_tokens: 32768, + max_output_tokens: 235929, pricing: { text: { input: { @@ -12111,43 +12088,6 @@ const QWEN_QWEN3_VL_235B_A22B_INSTRUCT = { image: 0, }, } as const -const QWEN_QWEN3_VL_235B_A22B_THINKING = { - id: 'qwen/qwen3-vl-235b-a22b-thinking', - name: 'Qwen: Qwen3 VL 235B A22B Thinking', - supports: { - input: ['text', 'image'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'logprobs', - 'maxCompletionTokens', - 'presencePenalty', - 'reasoning', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'toolChoice', - 'topLogprobs', - 'topP', - ], - }, - context_window: 131072, - max_output_tokens: 32768, - pricing: { - text: { - input: { - normal: 0.4, - cached: 0, - }, - output: { - normal: 4, - }, - }, - image: 0, - }, - reasoning: EFFORT_MINIMAL_TO_HIGH, -} as const const QWEN_QWEN3_VL_30B_A3B_INSTRUCT = { id: 'qwen/qwen3-vl-30b-a3b-instruct', name: 'Qwen: Qwen3 VL 30B A3B Instruct', @@ -12192,70 +12132,30 @@ const QWEN_QWEN3_VL_30B_A3B_THINKING = { output: ['text'], supports: [ 'frequencyPenalty', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', 'reasoning', 'responseFormat', - 'seed', - 'stop', 'temperature', 'toolChoice', - 'topLogprobs', 'topP', ], }, context_window: 262144, - max_output_tokens: 32768, + max_output_tokens: 235929, pricing: { text: { input: { - normal: 0.2, + normal: 0.29, cached: 0, }, output: { - normal: 2.4, + normal: 1, }, }, image: 0, }, reasoning: EFFORT_MINIMAL_TO_HIGH, } as const -const QWEN_QWEN3_VL_32B_INSTRUCT = { - id: 'qwen/qwen3-vl-32b-instruct', - name: 'Qwen: Qwen3 VL 32B Instruct', - supports: { - input: ['text', 'image'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'logprobs', - 'maxCompletionTokens', - 'presencePenalty', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'toolChoice', - 'topLogprobs', - 'topP', - ], - }, - context_window: 131072, - max_output_tokens: 32768, - pricing: { - text: { - input: { - normal: 0.104, - cached: 0, - }, - output: { - normal: 0.416, - }, - }, - image: 0, - }, -} as const const QWEN_QWEN3_VL_8B_INSTRUCT = { id: 'qwen/qwen3-vl-8b-instruct', name: 'Qwen: Qwen3 VL 8B Instruct', @@ -12278,56 +12178,19 @@ const QWEN_QWEN3_VL_8B_INSTRUCT = { ], }, context_window: 262144, - max_output_tokens: 32768, - pricing: { - text: { - input: { - normal: 0.117, - cached: 0, - }, - output: { - normal: 0.455, - }, - }, - image: 0, - }, -} as const -const QWEN_QWEN3_VL_8B_THINKING = { - id: 'qwen/qwen3-vl-8b-thinking', - name: 'Qwen: Qwen3 VL 8B Thinking', - supports: { - input: ['image', 'text'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'logprobs', - 'maxCompletionTokens', - 'presencePenalty', - 'reasoning', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'toolChoice', - 'topLogprobs', - 'topP', - ], - }, - context_window: 131072, - max_output_tokens: 32768, + max_output_tokens: 235929, pricing: { text: { input: { - normal: 0.18, - cached: 0, + normal: 0.25, + cached: 0.12, }, output: { - normal: 2.1, + normal: 0.75, }, }, image: 0, }, - reasoning: EFFORT_MINIMAL_TO_HIGH, } as const const QWEN_QWEN3_5_122B_A10B = { id: 'qwen/qwen3.5-122b-a10b', @@ -12356,11 +12219,11 @@ const QWEN_QWEN3_5_122B_A10B = { pricing: { text: { input: { - normal: 0.26, + normal: 0.4, cached: 0, }, output: { - normal: 2.08, + normal: 3.2, }, }, image: 0, @@ -12394,11 +12257,11 @@ const QWEN_QWEN3_5_27B = { pricing: { text: { input: { - normal: 0.195, - cached: 0, + normal: 0.27, + cached: 0.27, }, output: { - normal: 1.56, + normal: 2.16, }, }, image: 0, @@ -12428,11 +12291,11 @@ const QWEN_QWEN3_5_35B_A3B = { ], }, context_window: 262144, - max_output_tokens: 235929, + max_output_tokens: 81920, pricing: { text: { input: { - normal: 0.15, + normal: 0.14, cached: 0.05, }, output: { @@ -12466,15 +12329,15 @@ const QWEN_QWEN3_5_397B_A17B = { ], }, context_window: 262144, - max_output_tokens: 81920, + max_output_tokens: 235929, pricing: { text: { input: { - normal: 0.45, - cached: 0.22, + normal: 0.5, + cached: 0.3, }, output: { - normal: 3, + normal: 3.6, }, }, image: 0, @@ -12504,15 +12367,15 @@ const QWEN_QWEN3_5_9B = { ], }, context_window: 262144, - max_output_tokens: 32768, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0.1, - cached: 0, + normal: 0.08, + cached: 0.04, }, output: { - normal: 0.15, + normal: 0.13, }, }, image: 0, @@ -12655,8 +12518,8 @@ const QWEN_QWEN3_6_27B = { pricing: { text: { input: { - normal: 0.3, - cached: 0.03, + normal: 0.25, + cached: 0.025, }, output: { normal: 2, @@ -12693,11 +12556,11 @@ const QWEN_QWEN3_6_35B_A3B = { pricing: { text: { input: { - normal: 0.15, + normal: 0.1, cached: 0.05, }, output: { - normal: 1, + normal: 0.95, }, }, image: 0, @@ -12741,11 +12604,11 @@ const QWEN_QWEN3_6_FLASH = { }, reasoning: EFFORT_OFF_HIGH, } as const -const QWEN_QWEN3_6_MAX_PREVIEW = { - id: 'qwen/qwen3.6-max-preview', - name: 'Qwen: Qwen3.6 Max Preview', +const QWEN_QWEN3_6_PLUS = { + id: 'qwen/qwen3.6-plus', + name: 'Qwen: Qwen3.6 Plus', supports: { - input: ['text'], + input: ['text', 'image', 'video'], output: ['text'], supports: [ 'frequencyPenalty', @@ -12762,37 +12625,35 @@ const QWEN_QWEN3_6_MAX_PREVIEW = { 'topP', ], }, - context_window: 262144, + context_window: 1000000, max_output_tokens: 65536, pricing: { text: { input: { - normal: 1.027, - cached: 1.28375, + normal: 0.325, + cached: 0.40625, }, output: { - normal: 6.162, + normal: 1.95, }, }, image: 0, }, reasoning: EFFORT_OFF_HIGH, } as const -const QWEN_QWEN3_6_PLUS = { - id: 'qwen/qwen3.6-plus', - name: 'Qwen: Qwen3.6 Plus', +const QWEN_QWEN3_7_FLASH = { + id: 'qwen/qwen3.7-flash', + name: 'Qwen: Qwen3.7 Flash', supports: { input: ['text', 'image', 'video'], output: ['text'], supports: [ - 'frequencyPenalty', 'logprobs', 'maxCompletionTokens', 'presencePenalty', 'reasoning', 'responseFormat', 'seed', - 'stop', 'temperature', 'toolChoice', 'topLogprobs', @@ -12804,30 +12665,32 @@ const QWEN_QWEN3_6_PLUS = { pricing: { text: { input: { - normal: 0.325, - cached: 0.40625, + normal: 0.03, + cached: 0.044, }, output: { - normal: 1.95, + normal: 0.13, }, }, image: 0, }, - reasoning: EFFORT_OFF_HIGH, + reasoning: BUDGET_OFF_HIGH, } as const -const QWEN_QWEN3_7_FLASH = { - id: 'qwen/qwen3.7-flash', - name: 'Qwen: Qwen3.7 Flash', +const QWEN_QWEN3_7_MAX = { + id: 'qwen/qwen3.7-max', + name: 'Qwen: Qwen3.7 Max', supports: { - input: ['text', 'image', 'video'], + input: ['text'], output: ['text'], supports: [ + 'frequencyPenalty', 'logprobs', 'maxCompletionTokens', 'presencePenalty', 'reasoning', 'responseFormat', 'seed', + 'stop', 'temperature', 'toolChoice', 'topLogprobs', @@ -12835,26 +12698,26 @@ const QWEN_QWEN3_7_FLASH = { ], }, context_window: 1000000, - max_output_tokens: 65536, + max_output_tokens: 131072, pricing: { text: { input: { - normal: 0.03, - cached: 0.044, + normal: 1.475, + cached: 2.13875, }, output: { - normal: 0.13, + normal: 4.425, }, }, image: 0, }, - reasoning: BUDGET_OFF_HIGH, + reasoning: EFFORT_OFF_HIGH, } as const -const QWEN_QWEN3_7_MAX = { - id: 'qwen/qwen3.7-max', - name: 'Qwen: Qwen3.7 Max', +const QWEN_QWEN3_7_PLUS = { + id: 'qwen/qwen3.7-plus', + name: 'Qwen: Qwen3.7 Plus', supports: { - input: ['text'], + input: ['text', 'image'], output: ['text'], supports: [ 'frequencyPenalty', @@ -12876,20 +12739,20 @@ const QWEN_QWEN3_7_MAX = { pricing: { text: { input: { - normal: 1.475, - cached: 2.13875, + normal: 0.32, + cached: 0.464, }, output: { - normal: 4.425, + normal: 1.28, }, }, image: 0, }, reasoning: EFFORT_OFF_HIGH, } as const -const QWEN_QWEN3_7_PLUS = { - id: 'qwen/qwen3.7-plus', - name: 'Qwen: Qwen3.7 Plus', +const QWEN_QWEN3_7_PLUS_BATCH = { + id: 'qwen/qwen3.7-plus:batch', + name: 'Qwen: Qwen3.7 Plus (batch)', supports: { input: ['text', 'image'], output: ['text'], @@ -12908,21 +12771,20 @@ const QWEN_QWEN3_7_PLUS = { 'topP', ], }, - context_window: 1000000, + context_window: 262144, max_output_tokens: 131072, pricing: { text: { input: { - normal: 0.32, - cached: 0.464, + normal: 0.23, + cached: 0, }, output: { - normal: 1.28, + normal: 0.92, }, }, image: 0, }, - reasoning: EFFORT_OFF_HIGH, } as const const QWEN_QWEN3_8_2_4T_A95B = { id: 'qwen/qwen3.8-2.4t-a95b', @@ -12947,7 +12809,7 @@ const QWEN_QWEN3_8_2_4T_A95B = { ], }, context_window: 1048576, - max_output_tokens: 131072, + max_output_tokens: 909000, pricing: { text: { input: { @@ -12985,15 +12847,15 @@ const QWEN_QWEN3_8_27B = { ], }, context_window: 1000000, - max_output_tokens: 131072, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0.425, - cached: 0.61625, + normal: 0.04, + cached: 0.018, }, output: { - normal: 2.55, + normal: 1.35, }, }, image: 0, @@ -13027,7 +12889,7 @@ const QWEN_QWEN3_8_FLASH = { text: { input: { normal: 0.15, - cached: 0.21600000000000003, + cached: 0.016, }, output: { normal: 0.47, @@ -13064,7 +12926,7 @@ const QWEN_QWEN3_8_MAX_0902 = { text: { input: { normal: 2, - cached: 2.75, + cached: 0.25, }, output: { normal: 6, @@ -13148,6 +13010,76 @@ const QWEN_QWEN3_8_OMNI_FLASH = { }, reasoning: BUDGET_OFF_HIGH, } as const +const RECURSIVE_FLINT_V1_0_FREE = { + id: 'recursive/flint-v1.0:free', + name: 'Recursive: Flint (free)', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'logprobs', + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'topLogprobs', + 'topP', + ], + }, + context_window: 262144, + max_output_tokens: 235929, + pricing: { + text: { + input: { + normal: 0, + cached: 0, + }, + output: { + normal: 0, + }, + }, + image: 0, + }, +} as const +const REFLECTION_BEAM_1_0_501B_A23B = { + id: 'reflection/beam-1.0-501b-a23b', + name: 'Reflection: Beam 1.0 501B A23B', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 1048576, + max_output_tokens: 943718, + pricing: { + text: { + input: { + normal: 0.3, + cached: 0.04, + }, + output: { + normal: 1, + }, + }, + image: 0, + }, +} as const const REKAAI_REKA_EDGE = { id: 'rekaai/reka-edge', name: 'Reka Edge', @@ -13416,7 +13348,6 @@ const SAO10K_L3_1_EURYALE_70B = { 'seed', 'stop', 'temperature', - 'toolChoice', 'topP', ], }, @@ -13435,35 +13366,47 @@ const SAO10K_L3_1_EURYALE_70B = { image: 0, }, } as const -const SAO10K_L3_3_EURYALE_70B = { - id: 'sao10k/l3.3-euryale-70b', - name: 'Sao10K: Llama 3.3 Euryale 70B', +const SCALEDOWN_EXTRACT = { + id: 'scaledown/extract', + name: 'ScaleDown: Extract', supports: { - input: ['text'], + input: ['text', 'image', 'document'], output: ['text'], - supports: [ - 'frequencyPenalty', - 'logprobs', - 'maxCompletionTokens', - 'presencePenalty', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'topLogprobs', - 'topP', - ], + supports: ['maxCompletionTokens'], }, - context_window: 131072, - max_output_tokens: 16384, + context_window: 1000000, + max_output_tokens: 900000, pricing: { text: { input: { - normal: 0.65, + normal: 0.04, cached: 0, }, output: { - normal: 0.75, + normal: 0, + }, + }, + image: 0, + }, +} as const +const SCALEDOWN_SUMMARIZE = { + id: 'scaledown/summarize', + name: 'ScaleDown: Summarize', + supports: { + input: ['text', 'image', 'document'], + output: ['text'], + supports: ['maxCompletionTokens'], + }, + context_window: 1000000, + max_output_tokens: 4000, + pricing: { + text: { + input: { + normal: 0.04, + cached: 0, + }, + output: { + normal: 0, }, }, image: 0, @@ -13537,6 +13480,43 @@ const STEPFUN_STEP_3_7_FLASH = { }, reasoning: EFFORT_LOW_TO_HIGH, } as const +const STEPFUN_STEP_5_PREVIEW = { + id: 'stepfun/step-5-preview', + name: 'StepFun: Step 5 Preview', + supports: { + input: ['text', 'image', 'video'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 1048576, + max_output_tokens: 64000, + pricing: { + text: { + input: { + normal: 1, + cached: 0.1, + }, + output: { + normal: 2.7, + }, + }, + image: 0, + }, +} as const const TENCENT_HUNYUAN_A13B_INSTRUCT = { id: 'tencent/hunyuan-a13b-instruct', name: 'Tencent: Hunyuan A13B Instruct', @@ -13999,53 +13979,53 @@ const THINKINGMACHINES_INKLING_FREE = { }, reasoning: EFFORT_NONE_MINIMAL_TO_HIGH_MAX, } as const -const UNBIASED_PARETO = { - id: 'unbiased/pareto', - name: 'Pareto', +const UNBIASED_PARETO_26_10 = { + id: 'unbiased/pareto-26.10', + name: 'Pareto 26.10', supports: { input: ['text', 'image'], output: ['text'], - supports: [ - 'maxCompletionTokens', - 'responseFormat', - 'temperature', - 'toolChoice', - 'topP', - ], + supports: ['maxCompletionTokens', 'temperature', 'toolChoice', 'topP'], }, - context_window: 262144, + context_window: 1048576, max_output_tokens: 131072, pricing: { text: { input: { - normal: 2.5, - cached: 0.25, + normal: 0.8, + cached: 0.03, }, output: { - normal: 7.5, + normal: 3.2, }, }, image: 0, }, } as const -const UNBIASED_PARETO_26_10_PREVIEW = { - id: 'unbiased/pareto-26.10-preview', - name: 'Pareto 26.10 Preview', +const UNBIASED_PARETO_26_9 = { + id: 'unbiased/pareto-26.9', + name: 'Pareto 26.9', supports: { input: ['text', 'image'], output: ['text'], - supports: ['maxCompletionTokens', 'temperature', 'toolChoice', 'topP'], + supports: [ + 'maxCompletionTokens', + 'responseFormat', + 'temperature', + 'toolChoice', + 'topP', + ], }, - context_window: 1048576, + context_window: 262144, max_output_tokens: 131072, pricing: { text: { input: { - normal: 0.8, - cached: 0.03, + normal: 2.5, + cached: 0.25, }, output: { - normal: 3.2, + normal: 7.5, }, }, image: 0, @@ -14177,11 +14157,11 @@ const UPSTAGE_SOLAR_PRO4 = { pricing: { text: { input: { - normal: 0.09, - cached: 0.018, + normal: 0.15, + cached: 0.03, }, output: { - normal: 0.36, + normal: 0.6, }, }, image: 0, @@ -14503,15 +14483,15 @@ const XIAOMI_MIMO_V2_5 = { ], }, context_window: 1050000, - max_output_tokens: 131072, + max_output_tokens: 945000, pricing: { text: { input: { - normal: 0.14, - cached: 0.0028, + normal: 0.119, + cached: 0.00255, }, output: { - normal: 0.28, + normal: 0.238, }, }, image: 0, @@ -14540,15 +14520,15 @@ const XIAOMI_MIMO_V2_5_PRO = { ], }, context_window: 1050000, - max_output_tokens: 131072, + max_output_tokens: 945000, pricing: { text: { input: { - normal: 0.435, - cached: 0.0036, + normal: 0.3045, + cached: 0.0028, }, output: { - normal: 0.87, + normal: 0.609, }, }, image: 0, @@ -14663,6 +14643,40 @@ const XIAOMI_MIMO_V2_6_PRO_ULTRASPEED = { }, reasoning: EFFORT_OFF_HIGH, } as const +const XINGCHEN_AGI_XING4_0_29B_A4B_FREE = { + id: 'xingchen-agi/xing4.0-29b-a4b:free', + name: 'XingChen: Xing4.0 29B A4B (free)', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topP', + ], + }, + context_window: 262144, + max_output_tokens: 235929, + pricing: { + text: { + input: { + normal: 0, + cached: 0, + }, + output: { + normal: 0, + }, + }, + image: 0, + }, +} as const const Z_AI_GLM_4_5 = { id: 'z-ai/glm-4.5', name: 'Z.ai: GLM 4.5', @@ -14784,15 +14798,15 @@ const Z_AI_GLM_4_6 = { ], }, context_window: 204800, - max_output_tokens: 16384, + max_output_tokens: 131072, pricing: { text: { input: { - normal: 0.43, - cached: 0.08, + normal: 0.55, + cached: 0.11, }, output: { - normal: 1.75, + normal: 2.2, }, }, image: 0, @@ -14824,7 +14838,7 @@ const Z_AI_GLM_4_6V = { text: { input: { normal: 0.3, - cached: 0.05, + cached: 0.055, }, output: { normal: 0.9, @@ -14859,11 +14873,11 @@ const Z_AI_GLM_4_7 = { pricing: { text: { input: { - normal: 0.6, - cached: 0.11, + normal: 0.54, + cached: 0.099, }, output: { - normal: 2.2, + normal: 1.98, }, }, image: 0, @@ -14930,15 +14944,15 @@ const Z_AI_GLM_5 = { ], }, context_window: 204800, - max_output_tokens: 128000, + max_output_tokens: 131072, pricing: { text: { input: { - normal: 0.6, - cached: 0.12, + normal: 1, + cached: 0.2, }, output: { - normal: 1.92, + normal: 3.2, }, }, image: 0, @@ -14999,15 +15013,15 @@ const Z_AI_GLM_5_1 = { ], }, context_window: 204800, - max_output_tokens: 128000, + max_output_tokens: 131072, pricing: { text: { input: { - normal: 0.966, - cached: 0.1794, + normal: 1.4, + cached: 0.26, }, output: { - normal: 3.036, + normal: 4.4, }, }, image: 0, @@ -15038,15 +15052,15 @@ const Z_AI_GLM_5_2 = { ], }, context_window: 1048576, - max_output_tokens: 131072, + max_output_tokens: 943718, pricing: { text: { input: { - normal: 0.171, - cached: 0.162, + normal: 0.0341, + cached: 0.033, }, output: { - normal: 7.2, + normal: 7, }, }, image: 0, @@ -15081,11 +15095,11 @@ const Z_AI_GLM_5_3 = { pricing: { text: { input: { - normal: 0.07, - cached: 0.065, + normal: 0.079, + cached: 0.078, }, output: { - normal: 7, + normal: 1.4, }, }, image: 0, @@ -15116,15 +15130,15 @@ const Z_AI_GLM_5_3_FLASH = { ], }, context_window: 1048576, - max_output_tokens: 943717, + max_output_tokens: 943718, pricing: { text: { input: { - normal: 0.15, - cached: 0.03, + normal: 0.0052, + cached: 0.0052, }, output: { - normal: 0.5, + normal: 0.1985, }, }, image: 0, @@ -15140,6 +15154,7 @@ const Z_AI_GLM_5_3_FLASH_BATCH = { supports: [ 'frequencyPenalty', 'logitBias', + 'logprobs', 'maxCompletionTokens', 'presencePenalty', 'reasoning', @@ -15148,6 +15163,7 @@ const Z_AI_GLM_5_3_FLASH_BATCH = { 'stop', 'temperature', 'toolChoice', + 'topLogprobs', 'topP', ], }, @@ -15156,11 +15172,11 @@ const Z_AI_GLM_5_3_FLASH_BATCH = { pricing: { text: { input: { - normal: 0.06, - cached: 0.012, + normal: 0.05, + cached: 0.01, }, output: { - normal: 0.2, + normal: 0.18, }, }, image: 0, @@ -15320,9 +15336,7 @@ export type OpenRouterModelOptionsByName = { | 'maxCompletionTokens' | 'responseFormat' | 'stop' - | 'temperature' | 'toolChoice' - | 'topP' > [_ANTHROPIC_CLAUDE_OPUS_LATEST.id]: OpenRouterCommonOptions & Pick< @@ -15331,7 +15345,6 @@ export type OpenRouterModelOptionsByName = { | 'maxCompletionTokens' | 'responseFormat' | 'stop' - | 'temperature' | 'toolChoice' > [_ANTHROPIC_CLAUDE_SONNET_LATEST.id]: OpenRouterCommonOptions & @@ -15341,7 +15354,6 @@ export type OpenRouterModelOptionsByName = { | 'maxCompletionTokens' | 'responseFormat' | 'stop' - | 'temperature' | 'toolChoice' > [_DEEPSEEK_DEEPSEEK_FLASH_LATEST.id]: OpenRouterCommonOptions & @@ -15351,6 +15363,8 @@ export type OpenRouterModelOptionsByName = { | 'logitBias' | 'logprobs' | 'maxCompletionTokens' + | 'maxCompletionTokens' + | 'parallelToolCalls' | 'presencePenalty' | 'responseFormat' | 'seed' @@ -15476,6 +15490,11 @@ export type OpenRouterModelOptionsByName = { | 'seed' | 'toolChoice' > + [_UNBIASED_PARETO_LATEST.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + 'maxCompletionTokens' | 'temperature' | 'toolChoice' | 'topP' + > [_X_AI_GROK_LATEST.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -15658,6 +15677,20 @@ export type OpenRouterModelOptionsByName = { | 'toolChoice' | 'topP' > + [ANTHROPIC_CLAUDE_HAIKU_5_5.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'maxCompletionTokens' + | 'responseFormat' + | 'stop' + | 'toolChoice' + > + [ANTHROPIC_CLAUDE_HAIKU_5_5_BATCH.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + 'maxCompletionTokens' | 'responseFormat' | 'stop' | 'toolChoice' + > [ANTHROPIC_CLAUDE_OPUS_4_1.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -15733,7 +15766,6 @@ export type OpenRouterModelOptionsByName = { | 'maxCompletionTokens' | 'responseFormat' | 'stop' - | 'temperature' | 'toolChoice' > [ANTHROPIC_CLAUDE_OPUS_4_8_BATCH.id]: OpenRouterCommonOptions & @@ -15748,7 +15780,6 @@ export type OpenRouterModelOptionsByName = { | 'maxCompletionTokens' | 'responseFormat' | 'stop' - | 'temperature' | 'toolChoice' > [ANTHROPIC_CLAUDE_OPUS_5_BATCH.id]: OpenRouterCommonOptions & @@ -15763,7 +15794,6 @@ export type OpenRouterModelOptionsByName = { | 'maxCompletionTokens' | 'responseFormat' | 'stop' - | 'temperature' | 'toolChoice' > [ANTHROPIC_CLAUDE_OPUS_5_5_BATCH.id]: OpenRouterCommonOptions & @@ -15771,11 +15801,6 @@ export type OpenRouterModelOptionsByName = { OpenRouterBaseOptions, 'maxCompletionTokens' | 'responseFormat' | 'stop' | 'toolChoice' > - [ANTHROPIC_CLAUDE_SONNET_4.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - 'maxCompletionTokens' | 'stop' | 'temperature' | 'toolChoice' | 'topP' - > [ANTHROPIC_CLAUDE_SONNET_4_5.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -15839,7 +15864,6 @@ export type OpenRouterModelOptionsByName = { | 'maxCompletionTokens' | 'responseFormat' | 'stop' - | 'temperature' | 'toolChoice' > [ANTHROPIC_CLAUDE_SONNET_5_5_BATCH.id]: OpenRouterCommonOptions & @@ -15847,35 +15871,11 @@ export type OpenRouterModelOptionsByName = { OpenRouterBaseOptions, 'maxCompletionTokens' | 'responseFormat' | 'stop' | 'toolChoice' > - [APODEX_APODEX_1_1_MINI_FREE.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'responseFormat' - | 'seed' - | 'stop' - | 'temperature' - | 'toolChoice' - | 'topP' - > [ARCEE_AI_TRINITY_LARGE_THINKING.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, 'maxCompletionTokens' | 'temperature' | 'toolChoice' | 'topP' > - [BAIDU_ERNIE_4_5_VL_424B_A47B.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'seed' - | 'stop' - | 'temperature' - | 'topP' - > [BYTEDANCE_SEED_SEED_1_6.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -16084,19 +16084,6 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [DEEPSEEK_DEEPSEEK_R1.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'responseFormat' - | 'seed' - | 'stop' - | 'temperature' - | 'toolChoice' - | 'topP' - > [DEEPSEEK_DEEPSEEK_R1_0528.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -16249,30 +16236,25 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [DEEPSEEK_DEEPSEEK_V4_1_FLASH_BATCH.id]: OpenRouterCommonOptions & + [DEEPSEEK_DEEPSEEK_V4_1_FLASH_1017.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' + | 'maxCompletionTokens' + | 'parallelToolCalls' | 'presencePenalty' | 'responseFormat' | 'seed' | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > - [DOTS_STUDIO_DOTS_3_NOTE_PREVIEW_FREE.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'maxCompletionTokens' - | 'responseFormat' - | 'temperature' - | 'toolChoice' - | 'topP' - > - [FIREWORKS_EMBER_1.id]: OpenRouterCommonOptions & + [DEEPSEEK_DEEPSEEK_V4_1_FLASH_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -16281,45 +16263,53 @@ export type OpenRouterModelOptionsByName = { | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' + | 'seed' | 'stop' | 'temperature' | 'toolChoice' | 'topLogprobs' | 'topP' > - [GOOGLE_GEMINI_2_5_FLASH.id]: OpenRouterCommonOptions & + [DOTS_STUDIO_DOTS_3_NOTE_PREVIEW_FREE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' | 'responseFormat' - | 'seed' - | 'stop' | 'temperature' | 'toolChoice' | 'topP' > - [GOOGLE_GEMINI_2_5_FLASH_IMAGE.id]: OpenRouterCommonOptions & + [ELORIAN_GLIMPSE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' + | 'presencePenalty' | 'responseFormat' - | 'seed' | 'stop' | 'temperature' + | 'toolChoice' + | 'topLogprobs' | 'topP' > - [GOOGLE_GEMINI_2_5_FLASH_LITE.id]: OpenRouterCommonOptions & + [FIREWORKS_EMBER_1.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' + | 'presencePenalty' | 'responseFormat' - | 'seed' | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > - [GOOGLE_GEMINI_2_5_FLASH_LITE_BATCH.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_2_5_FLASH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' @@ -16330,7 +16320,7 @@ export type OpenRouterModelOptionsByName = { | 'toolChoice' | 'topP' > - [GOOGLE_GEMINI_2_5_FLASH_BATCH.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_2_5_FLASH_IMAGE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' @@ -16338,10 +16328,9 @@ export type OpenRouterModelOptionsByName = { | 'seed' | 'stop' | 'temperature' - | 'toolChoice' | 'topP' > - [GOOGLE_GEMINI_2_5_PRO.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_2_5_FLASH_LITE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' @@ -16352,18 +16341,17 @@ export type OpenRouterModelOptionsByName = { | 'toolChoice' | 'topP' > - [GOOGLE_GEMINI_2_5_PRO_PREVIEW.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_2_5_PRO.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' | 'responseFormat' | 'seed' - | 'stop' | 'temperature' | 'toolChoice' | 'topP' > - [GOOGLE_GEMINI_2_5_PRO_BATCH.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_2_5_PRO_PREVIEW.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' @@ -16582,6 +16570,28 @@ export type OpenRouterModelOptionsByName = { OpenRouterBaseOptions, 'maxCompletionTokens' | 'responseFormat' | 'seed' | 'stop' | 'toolChoice' > + [GOOGLE_GEMINI_4_ARGON.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'responseFormat' + | 'seed' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topP' + > + [GOOGLE_GEMINI_4_ARGON_BATCH.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'responseFormat' + | 'seed' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topP' + > [GOOGLE_GEMINI_NANO_BANANA_2_1.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -16639,12 +16649,14 @@ export type OpenRouterModelOptionsByName = { OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' | 'seed' | 'stop' | 'temperature' + | 'topLogprobs' | 'topP' > [GOOGLE_GEMMA_4_26B_A4B_IT.id]: OpenRouterCommonOptions & @@ -16773,23 +16785,16 @@ export type OpenRouterModelOptionsByName = { | 'temperature' | 'toolChoice' > - [INCLUSIONAI_LING_3_0_FLASH.id]: OpenRouterCommonOptions & + [INCEPTION_MERCURY_3.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' - | 'presencePenalty' | 'responseFormat' - | 'seed' | 'stop' | 'temperature' | 'toolChoice' - | 'topLogprobs' - | 'topP' > - [INCLUSIONAI_LING_3_0_FLASH_FIN.id]: OpenRouterCommonOptions & + [INCLUSIONAI_LING_3_0_FLASH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -16797,6 +16802,7 @@ export type OpenRouterModelOptionsByName = { | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' + | 'responseFormat' | 'seed' | 'stop' | 'temperature' @@ -16804,21 +16810,21 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [INCLUSIONAI_LING_3_0_FLASH_SANTE_FREE.id]: OpenRouterCommonOptions & + [INCLUSIONAI_LING_3_0_FLASH_VL.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logprobs' + | 'logitBias' | 'maxCompletionTokens' | 'presencePenalty' + | 'responseFormat' | 'seed' | 'stop' | 'temperature' | 'toolChoice' - | 'topLogprobs' | 'topP' > - [INCLUSIONAI_LING_3_0_FLASH_VL.id]: OpenRouterCommonOptions & + [INCLUSIONAI_LING_3_1_FLASH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -16834,21 +16840,20 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [INCLUSIONAI_LING_3_1_FLASH.id]: OpenRouterCommonOptions & + [INFERENCE_NET_SCHEMATRON_V2_SMALL.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logprobs' + | 'logitBias' | 'maxCompletionTokens' | 'presencePenalty' + | 'responseFormat' | 'seed' | 'stop' | 'temperature' - | 'toolChoice' - | 'topLogprobs' | 'topP' > - [INFERENCE_NET_SCHEMATRON_V2_SMALL.id]: OpenRouterCommonOptions & + [INFERENCE_NET_SCHEMATRON_V2_TURBO.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -16861,20 +16866,22 @@ export type OpenRouterModelOptionsByName = { | 'temperature' | 'topP' > - [INFERENCE_NET_SCHEMATRON_V2_TURBO.id]: OpenRouterCommonOptions & + [LIQUID_LFM_2_5_2_6B_FREE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logitBias' + | 'logprobs' + | 'maxCompletionTokens' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' | 'seed' | 'stop' | 'temperature' - | 'topP' + | 'toolChoice' + | 'topLogprobs' > - [LIQUID_LFM_2_5_2_6B_FREE.id]: OpenRouterCommonOptions & + [LIQUID_LFM_2_5_24B_A2B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -16888,7 +16895,6 @@ export type OpenRouterModelOptionsByName = { | 'temperature' | 'toolChoice' | 'topLogprobs' - | 'topP' > [MANCER_WEAVER.id]: OpenRouterCommonOptions & Pick< @@ -17091,23 +17097,36 @@ export type OpenRouterModelOptionsByName = { | 'toolChoice' | 'topP' > - [MICROSOFT_PHI_4.id]: OpenRouterCommonOptions & + [META_MUSE_SPARK_OPEN.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' | 'seed' | 'stop' | 'temperature' + | 'toolChoice' + | 'topLogprobs' + | 'topP' + > + [META_MUSE_WONDER.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'responseFormat' + | 'temperature' + | 'toolChoice' | 'topP' > - [MICROSOFT_WIZARDLM_2_8X22B.id]: OpenRouterCommonOptions & + [MICROSOFT_PHI_4.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' + | 'logitBias' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' @@ -17150,12 +17169,8 @@ export type OpenRouterModelOptionsByName = { [MINIMAX_MINIMAX_M2_1.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' | 'maxCompletionTokens' - | 'presencePenalty' | 'responseFormat' - | 'seed' - | 'stop' | 'temperature' | 'toolChoice' | 'topP' @@ -17206,6 +17221,15 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > + [MINIMAX_MINIMAX_M3_1_FLASH_FREE.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'responseFormat' + | 'temperature' + | 'toolChoice' + | 'topP' + > [MISTRALAI_CODESTRAL_2508.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -17554,6 +17578,16 @@ export type OpenRouterModelOptionsByName = { | 'toolChoice' | 'topP' > + [MOONDREAM_MOONDREAM3_PREVIEW.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + 'maxCompletionTokens' | 'maxCompletionTokens' | 'temperature' | 'topP' + > + [MOONDREAM_MOONDREAM3_1_9B_A2B.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + 'maxCompletionTokens' | 'maxCompletionTokens' | 'temperature' | 'topP' + > [MOONSHOTAI_KIMI_K2.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -17675,7 +17709,15 @@ export type OpenRouterModelOptionsByName = { | 'topP' > [MORPH_MORPH_V3_FAST.id]: OpenRouterCommonOptions & - Pick + Pick< + OpenRouterBaseOptions, + | 'logprobs' + | 'maxCompletionTokens' + | 'responseFormat' + | 'stop' + | 'temperature' + | 'topLogprobs' + > [MORPH_MORPH_V3_LARGE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -17734,10 +17776,12 @@ export type OpenRouterModelOptionsByName = { Pick< OpenRouterBaseOptions, | 'frequencyPenalty' + | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' | 'temperature' + | 'topLogprobs' | 'topP' > [NVIDIA_NEMOTRON_3_NANO_30B_A3B.id]: OpenRouterCommonOptions & @@ -17844,6 +17888,32 @@ export type OpenRouterModelOptionsByName = { OpenRouterBaseOptions, 'maxCompletionTokens' | 'seed' | 'temperature' | 'toolChoice' | 'topP' > + [NVIDIA_NEMOTRON_3_5_SUPER_VL.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' + | 'maxCompletionTokens' + | 'presencePenalty' + | 'responseFormat' + | 'seed' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topLogprobs' + | 'topP' + > + [NVIDIA_NEMOTRON_3_5_SUPER_VL_FREE.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'responseFormat' + | 'seed' + | 'temperature' + | 'toolChoice' + | 'topP' + > [OPENAI_GPT_3_5_TURBO.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -18589,6 +18659,16 @@ export type OpenRouterModelOptionsByName = { | 'seed' | 'toolChoice' > + [OPENAI_GPT_6_1_SOL_PRO_BATCH.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + 'maxCompletionTokens' | 'responseFormat' | 'seed' | 'toolChoice' + > + [OPENAI_GPT_6_1_SOL_BATCH.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + 'maxCompletionTokens' | 'responseFormat' | 'seed' | 'toolChoice' + > [OPENAI_GPT_AUDIO.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -18906,21 +18986,6 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [QWEN_QWEN_PLUS_2025_07_28.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logprobs' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'responseFormat' - | 'seed' - | 'stop' - | 'temperature' - | 'toolChoice' - | 'topLogprobs' - | 'topP' - > [QWEN_QWEN2_5_VL_72B_INSTRUCT.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -18952,19 +19017,6 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_235B_A22B.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'responseFormat' - | 'seed' - | 'stop' - | 'temperature' - | 'toolChoice' - | 'topP' - > [QWEN_QWEN3_235B_A22B_2507.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -18985,15 +19037,11 @@ export type OpenRouterModelOptionsByName = { Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' - | 'responseFormat' - | 'seed' | 'stop' | 'temperature' | 'toolChoice' - | 'topLogprobs' | 'topP' > [QWEN_QWEN3_30B_A3B.id]: OpenRouterCommonOptions & @@ -19026,19 +19074,6 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_30B_A3B_THINKING_2507.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'responseFormat' - | 'seed' - | 'stop' - | 'temperature' - | 'toolChoice' - | 'topP' - > [QWEN_QWEN3_32B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -19055,19 +19090,6 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_8B.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'responseFormat' - | 'seed' - | 'stop' - | 'temperature' - | 'toolChoice' - | 'topP' - > [QWEN_QWEN3_CODER.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -19088,15 +19110,11 @@ export type OpenRouterModelOptionsByName = { Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logprobs' | 'maxCompletionTokens' - | 'presencePenalty' | 'responseFormat' - | 'seed' | 'stop' | 'temperature' | 'toolChoice' - | 'topLogprobs' | 'topP' > [QWEN_QWEN3_CODER_FLASH.id]: OpenRouterCommonOptions & @@ -19130,51 +19148,6 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_CODER_PLUS.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logprobs' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'responseFormat' - | 'seed' - | 'stop' - | 'temperature' - | 'toolChoice' - | 'topLogprobs' - | 'topP' - > - [QWEN_QWEN3_MAX.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logprobs' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'responseFormat' - | 'seed' - | 'stop' - | 'temperature' - | 'toolChoice' - | 'topLogprobs' - | 'topP' - > - [QWEN_QWEN3_MAX_THINKING.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logprobs' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'responseFormat' - | 'seed' - | 'stop' - | 'temperature' - | 'toolChoice' - | 'topLogprobs' - | 'topP' - > [QWEN_QWEN3_NEXT_80B_A3B_INSTRUCT.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -19222,21 +19195,6 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_VL_235B_A22B_THINKING.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logprobs' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'responseFormat' - | 'seed' - | 'stop' - | 'temperature' - | 'toolChoice' - | 'topLogprobs' - | 'topP' - > [QWEN_QWEN3_VL_30B_A3B_INSTRUCT.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -19257,30 +19215,10 @@ export type OpenRouterModelOptionsByName = { Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logprobs' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'responseFormat' - | 'seed' - | 'stop' - | 'temperature' - | 'toolChoice' - | 'topLogprobs' - | 'topP' - > - [QWEN_QWEN3_VL_32B_INSTRUCT.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logprobs' | 'maxCompletionTokens' - | 'presencePenalty' | 'responseFormat' - | 'seed' - | 'stop' | 'temperature' | 'toolChoice' - | 'topLogprobs' | 'topP' > [QWEN_QWEN3_VL_8B_INSTRUCT.id]: OpenRouterCommonOptions & @@ -19299,21 +19237,6 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_VL_8B_THINKING.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logprobs' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'responseFormat' - | 'seed' - | 'stop' - | 'temperature' - | 'toolChoice' - | 'topLogprobs' - | 'topP' - > [QWEN_QWEN3_5_122B_A10B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -19484,7 +19407,7 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_6_MAX_PREVIEW.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_6_PLUS.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -19499,35 +19422,35 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_6_PLUS.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_7_FLASH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' | 'seed' - | 'stop' | 'temperature' | 'toolChoice' | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_7_FLASH.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_7_MAX.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' | 'seed' + | 'stop' | 'temperature' | 'toolChoice' | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_7_MAX.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_7_PLUS.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -19542,7 +19465,7 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_7_PLUS.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_7_PLUS_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -19649,6 +19572,34 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > + [RECURSIVE_FLINT_V1_0_FREE.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'logprobs' + | 'maxCompletionTokens' + | 'responseFormat' + | 'seed' + | 'stop' + | 'temperature' + | 'topLogprobs' + | 'topP' + > + [REFLECTION_BEAM_1_0_501B_A23B.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' + | 'maxCompletionTokens' + | 'presencePenalty' + | 'responseFormat' + | 'seed' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topLogprobs' + | 'topP' + > [REKAAI_REKA_EDGE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -19722,36 +19673,41 @@ export type OpenRouterModelOptionsByName = { | 'seed' | 'stop' | 'temperature' - | 'toolChoice' | 'topP' > - [SAO10K_L3_3_EURYALE_70B.id]: OpenRouterCommonOptions & + [SCALEDOWN_EXTRACT.id]: OpenRouterCommonOptions & + Pick + [SCALEDOWN_SUMMARIZE.id]: OpenRouterCommonOptions & + Pick + [STEPFUN_STEP_3_5_FLASH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logprobs' | 'maxCompletionTokens' - | 'presencePenalty' - | 'responseFormat' - | 'seed' - | 'stop' | 'temperature' - | 'topLogprobs' + | 'toolChoice' | 'topP' > - [STEPFUN_STEP_3_5_FLASH.id]: OpenRouterCommonOptions & + [STEPFUN_STEP_3_7_FLASH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' + | 'logprobs' | 'maxCompletionTokens' + | 'presencePenalty' + | 'responseFormat' + | 'seed' + | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > - [STEPFUN_STEP_3_7_FLASH.id]: OpenRouterCommonOptions & + [STEPFUN_STEP_5_PREVIEW.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' + | 'logitBias' | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' @@ -19922,7 +19878,12 @@ export type OpenRouterModelOptionsByName = { | 'temperature' | 'topP' > - [UNBIASED_PARETO.id]: OpenRouterCommonOptions & + [UNBIASED_PARETO_26_10.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + 'maxCompletionTokens' | 'temperature' | 'toolChoice' | 'topP' + > + [UNBIASED_PARETO_26_9.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' @@ -19931,11 +19892,6 @@ export type OpenRouterModelOptionsByName = { | 'toolChoice' | 'topP' > - [UNBIASED_PARETO_26_10_PREVIEW.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - 'maxCompletionTokens' | 'temperature' | 'toolChoice' | 'topP' - > [UNDI95_REMM_SLERP_L2_13B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -20158,6 +20114,19 @@ export type OpenRouterModelOptionsByName = { | 'toolChoice' | 'topP' > + [XINGCHEN_AGI_XING4_0_29B_A4B_FREE.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'maxCompletionTokens' + | 'presencePenalty' + | 'responseFormat' + | 'seed' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topP' + > [Z_AI_GLM_4_5.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -20345,6 +20314,7 @@ export type OpenRouterModelOptionsByName = { OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' @@ -20352,6 +20322,7 @@ export type OpenRouterModelOptionsByName = { | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > [Z_AI_GLM_5_3_FLASHX.id]: OpenRouterCommonOptions & @@ -20432,6 +20403,7 @@ export type OpenRouterModelInputModalitiesByName = { [_OPENAI_GPT_MINI_LATEST.id]: ReadonlyArray<'document' | 'image' | 'text'> [_OPENAI_GPT_SOL_LATEST.id]: ReadonlyArray<'document' | 'image' | 'text'> [_OPENAI_GPT_TERRA_LATEST.id]: ReadonlyArray<'document' | 'image' | 'text'> + [_UNBIASED_PARETO_LATEST.id]: ReadonlyArray<'text' | 'image'> [_X_AI_GROK_LATEST.id]: ReadonlyArray<'text' | 'image' | 'document'> [_Z_AI_GLM_FLASH_LATEST.id]: ReadonlyArray<'text' | 'image' | 'video'> [_Z_AI_GLM_LATEST.id]: ReadonlyArray<'text'> @@ -20461,6 +20433,10 @@ export type OpenRouterModelInputModalitiesByName = { [ANTHROPIC_CLAUDE_HAIKU_4_5_BATCH.id]: ReadonlyArray< 'text' | 'image' | 'document' > + [ANTHROPIC_CLAUDE_HAIKU_5_5.id]: ReadonlyArray<'text' | 'image' | 'document'> + [ANTHROPIC_CLAUDE_HAIKU_5_5_BATCH.id]: ReadonlyArray< + 'text' | 'image' | 'document' + > [ANTHROPIC_CLAUDE_OPUS_4_1.id]: ReadonlyArray<'image' | 'text' | 'document'> [ANTHROPIC_CLAUDE_OPUS_4_1_BATCH.id]: ReadonlyArray< 'image' | 'text' | 'document' @@ -20489,7 +20465,6 @@ export type OpenRouterModelInputModalitiesByName = { [ANTHROPIC_CLAUDE_OPUS_5_5_BATCH.id]: ReadonlyArray< 'text' | 'image' | 'document' > - [ANTHROPIC_CLAUDE_SONNET_4.id]: ReadonlyArray<'image' | 'text' | 'document'> [ANTHROPIC_CLAUDE_SONNET_4_5.id]: ReadonlyArray<'text' | 'image' | 'document'> [ANTHROPIC_CLAUDE_SONNET_4_5_BATCH.id]: ReadonlyArray< 'text' | 'image' | 'document' @@ -20506,9 +20481,7 @@ export type OpenRouterModelInputModalitiesByName = { [ANTHROPIC_CLAUDE_SONNET_5_5_BATCH.id]: ReadonlyArray< 'text' | 'image' | 'document' > - [APODEX_APODEX_1_1_MINI_FREE.id]: ReadonlyArray<'text'> [ARCEE_AI_TRINITY_LARGE_THINKING.id]: ReadonlyArray<'text'> - [BAIDU_ERNIE_4_5_VL_424B_A47B.id]: ReadonlyArray<'image' | 'text'> [BYTEDANCE_SEED_SEED_1_6.id]: ReadonlyArray<'image' | 'text' | 'video'> [BYTEDANCE_SEED_SEED_1_6_FLASH.id]: ReadonlyArray<'image' | 'text' | 'video'> [BYTEDANCE_SEED_SEED_2_1_TURBO.id]: ReadonlyArray<'text' | 'image' | 'video'> @@ -20526,7 +20499,6 @@ export type OpenRouterModelInputModalitiesByName = { [DEEPSEEK_DEEPSEEK_CHAT.id]: ReadonlyArray<'text'> [DEEPSEEK_DEEPSEEK_CHAT_V3_0324.id]: ReadonlyArray<'text'> [DEEPSEEK_DEEPSEEK_CHAT_V3_1.id]: ReadonlyArray<'text'> - [DEEPSEEK_DEEPSEEK_R1.id]: ReadonlyArray<'text'> [DEEPSEEK_DEEPSEEK_R1_0528.id]: ReadonlyArray<'text'> [DEEPSEEK_DEEPSEEK_V3_1_TERMINUS.id]: ReadonlyArray<'text'> [DEEPSEEK_DEEPSEEK_V3_2.id]: ReadonlyArray<'text'> @@ -20537,8 +20509,10 @@ export type OpenRouterModelInputModalitiesByName = { [DEEPSEEK_DEEPSEEK_V4_PRO.id]: ReadonlyArray<'text'> [DEEPSEEK_DEEPSEEK_V4_PRO_0813.id]: ReadonlyArray<'text'> [DEEPSEEK_DEEPSEEK_V4_1_FLASH.id]: ReadonlyArray<'text' | 'image'> + [DEEPSEEK_DEEPSEEK_V4_1_FLASH_1017.id]: ReadonlyArray<'text' | 'image'> [DEEPSEEK_DEEPSEEK_V4_1_FLASH_BATCH.id]: ReadonlyArray<'text' | 'image'> [DOTS_STUDIO_DOTS_3_NOTE_PREVIEW_FREE.id]: ReadonlyArray<'text' | 'image'> + [ELORIAN_GLIMPSE.id]: ReadonlyArray<'text' | 'image' | 'video'> [FIREWORKS_EMBER_1.id]: ReadonlyArray<'text' | 'image'> [GOOGLE_GEMINI_2_5_FLASH.id]: ReadonlyArray< 'document' | 'image' | 'text' | 'audio' | 'video' @@ -20547,21 +20521,12 @@ export type OpenRouterModelInputModalitiesByName = { [GOOGLE_GEMINI_2_5_FLASH_LITE.id]: ReadonlyArray< 'text' | 'image' | 'document' | 'audio' | 'video' > - [GOOGLE_GEMINI_2_5_FLASH_LITE_BATCH.id]: ReadonlyArray< - 'text' | 'image' | 'document' | 'audio' | 'video' - > - [GOOGLE_GEMINI_2_5_FLASH_BATCH.id]: ReadonlyArray< - 'document' | 'image' | 'text' | 'audio' | 'video' - > [GOOGLE_GEMINI_2_5_PRO.id]: ReadonlyArray< 'text' | 'image' | 'document' | 'audio' | 'video' > [GOOGLE_GEMINI_2_5_PRO_PREVIEW.id]: ReadonlyArray< 'document' | 'image' | 'text' | 'audio' > - [GOOGLE_GEMINI_2_5_PRO_BATCH.id]: ReadonlyArray< - 'text' | 'image' | 'document' | 'audio' | 'video' - > [GOOGLE_GEMINI_3_FLASH_PREVIEW.id]: ReadonlyArray< 'text' | 'image' | 'document' | 'audio' | 'video' > @@ -20621,6 +20586,12 @@ export type OpenRouterModelInputModalitiesByName = { [GOOGLE_GEMINI_3_8_FLASH_BATCH.id]: ReadonlyArray< 'text' | 'image' | 'video' | 'document' | 'audio' > + [GOOGLE_GEMINI_4_ARGON.id]: ReadonlyArray< + 'audio' | 'document' | 'image' | 'text' | 'video' + > + [GOOGLE_GEMINI_4_ARGON_BATCH.id]: ReadonlyArray< + 'audio' | 'document' | 'image' | 'text' | 'video' + > [GOOGLE_GEMINI_NANO_BANANA_2_1.id]: ReadonlyArray<'image' | 'text'> [GOOGLE_GEMMA_2_27B_IT.id]: ReadonlyArray<'text'> [GOOGLE_GEMMA_3_12B_IT.id]: ReadonlyArray<'text' | 'image'> @@ -20637,14 +20608,14 @@ export type OpenRouterModelInputModalitiesByName = { [IBM_GRANITE_GRANITE_4_2_8B.id]: ReadonlyArray<'text'> [INCEPTION_MERCURY_2.id]: ReadonlyArray<'text'> [INCEPTION_MERCURY_2_5.id]: ReadonlyArray<'text'> + [INCEPTION_MERCURY_3.id]: ReadonlyArray<'text'> [INCLUSIONAI_LING_3_0_FLASH.id]: ReadonlyArray<'text'> - [INCLUSIONAI_LING_3_0_FLASH_FIN.id]: ReadonlyArray<'text'> - [INCLUSIONAI_LING_3_0_FLASH_SANTE_FREE.id]: ReadonlyArray<'text'> [INCLUSIONAI_LING_3_0_FLASH_VL.id]: ReadonlyArray<'text' | 'image' | 'video'> [INCLUSIONAI_LING_3_1_FLASH.id]: ReadonlyArray<'text'> [INFERENCE_NET_SCHEMATRON_V2_SMALL.id]: ReadonlyArray<'text'> [INFERENCE_NET_SCHEMATRON_V2_TURBO.id]: ReadonlyArray<'text'> [LIQUID_LFM_2_5_2_6B_FREE.id]: ReadonlyArray<'text'> + [LIQUID_LFM_2_5_24B_A2B.id]: ReadonlyArray<'text'> [MANCER_WEAVER.id]: ReadonlyArray<'text'> [MEITUAN_LONGCAT_2_0.id]: ReadonlyArray<'text'> [META_LLAMA_LLAMA_3_1_70B_INSTRUCT.id]: ReadonlyArray<'text'> @@ -20671,8 +20642,13 @@ export type OpenRouterModelInputModalitiesByName = { [META_MUSE_SPARK_1_3_CONTRIBUTOR.id]: ReadonlyArray< 'text' | 'image' | 'video' | 'document' > + [META_MUSE_SPARK_OPEN.id]: ReadonlyArray< + 'text' | 'image' | 'video' | 'document' | 'audio' + > + [META_MUSE_WONDER.id]: ReadonlyArray< + 'text' | 'image' | 'video' | 'document' | 'audio' + > [MICROSOFT_PHI_4.id]: ReadonlyArray<'text'> - [MICROSOFT_WIZARDLM_2_8X22B.id]: ReadonlyArray<'text'> [MINIMAX_MINIMAX_01.id]: ReadonlyArray<'text' | 'image'> [MINIMAX_MINIMAX_M1.id]: ReadonlyArray<'text'> [MINIMAX_MINIMAX_M2.id]: ReadonlyArray<'text'> @@ -20681,6 +20657,9 @@ export type OpenRouterModelInputModalitiesByName = { [MINIMAX_MINIMAX_M2_5.id]: ReadonlyArray<'text'> [MINIMAX_MINIMAX_M2_7.id]: ReadonlyArray<'text'> [MINIMAX_MINIMAX_M3.id]: ReadonlyArray<'text' | 'image' | 'video'> + [MINIMAX_MINIMAX_M3_1_FLASH_FREE.id]: ReadonlyArray< + 'text' | 'image' | 'video' + > [MISTRALAI_CODESTRAL_2508.id]: ReadonlyArray<'text' | 'document'> [MISTRALAI_CODESTRAL_2508_BATCH.id]: ReadonlyArray<'text' | 'document'> [MISTRALAI_DEVSTRAL_2512.id]: ReadonlyArray<'text' | 'document'> @@ -20721,6 +20700,8 @@ export type OpenRouterModelInputModalitiesByName = { [MISTRALAI_VOXTRAL_SMALL_24B_2507.id]: ReadonlyArray< 'text' | 'audio' | 'document' > + [MOONDREAM_MOONDREAM3_PREVIEW.id]: ReadonlyArray<'text' | 'image'> + [MOONDREAM_MOONDREAM3_1_9B_A2B.id]: ReadonlyArray<'text' | 'image'> [MOONSHOTAI_KIMI_K2.id]: ReadonlyArray<'text'> [MOONSHOTAI_KIMI_K2_0905.id]: ReadonlyArray<'text'> [MOONSHOTAI_KIMI_K2_THINKING.id]: ReadonlyArray<'text'> @@ -20748,6 +20729,10 @@ export type OpenRouterModelInputModalitiesByName = { [NVIDIA_NEMOTRON_3_5_CONTENT_SAFETY_FREE.id]: ReadonlyArray<'text' | 'image'> [NVIDIA_NEMOTRON_3_5_LIGHTNING.id]: ReadonlyArray<'text'> [NVIDIA_NEMOTRON_3_5_LIGHTNING_FREE.id]: ReadonlyArray<'text'> + [NVIDIA_NEMOTRON_3_5_SUPER_VL.id]: ReadonlyArray<'text' | 'image' | 'video'> + [NVIDIA_NEMOTRON_3_5_SUPER_VL_FREE.id]: ReadonlyArray< + 'text' | 'image' | 'video' + > [OPENAI_GPT_3_5_TURBO.id]: ReadonlyArray<'text'> [OPENAI_GPT_3_5_TURBO_0613.id]: ReadonlyArray<'text'> [OPENAI_GPT_3_5_TURBO_16K.id]: ReadonlyArray<'text'> @@ -20841,6 +20826,10 @@ export type OpenRouterModelInputModalitiesByName = { [OPENAI_GPT_6_SOL_BATCH.id]: ReadonlyArray<'document' | 'image' | 'text'> [OPENAI_GPT_6_1_SOL.id]: ReadonlyArray<'document' | 'image' | 'text'> [OPENAI_GPT_6_1_SOL_PRO.id]: ReadonlyArray<'document' | 'image' | 'text'> + [OPENAI_GPT_6_1_SOL_PRO_BATCH.id]: ReadonlyArray< + 'document' | 'image' | 'text' + > + [OPENAI_GPT_6_1_SOL_BATCH.id]: ReadonlyArray<'document' | 'image' | 'text'> [OPENAI_GPT_AUDIO.id]: ReadonlyArray<'text' | 'audio'> [OPENAI_GPT_AUDIO_MINI.id]: ReadonlyArray<'text' | 'audio'> [OPENAI_GPT_CHAT_LATEST.id]: ReadonlyArray<'text' | 'image' | 'document'> @@ -20878,33 +20867,23 @@ export type OpenRouterModelInputModalitiesByName = { [QWEN_QWEN_2_5_7B_INSTRUCT.id]: ReadonlyArray<'text'> [QWEN_QWEN_2_5_CODER_32B_INSTRUCT.id]: ReadonlyArray<'text'> [QWEN_QWEN_PLUS.id]: ReadonlyArray<'text'> - [QWEN_QWEN_PLUS_2025_07_28.id]: ReadonlyArray<'text'> [QWEN_QWEN2_5_VL_72B_INSTRUCT.id]: ReadonlyArray<'text' | 'image'> [QWEN_QWEN3_14B.id]: ReadonlyArray<'text'> - [QWEN_QWEN3_235B_A22B.id]: ReadonlyArray<'text'> [QWEN_QWEN3_235B_A22B_2507.id]: ReadonlyArray<'text'> [QWEN_QWEN3_235B_A22B_THINKING_2507.id]: ReadonlyArray<'text'> [QWEN_QWEN3_30B_A3B.id]: ReadonlyArray<'text'> [QWEN_QWEN3_30B_A3B_INSTRUCT_2507.id]: ReadonlyArray<'text'> - [QWEN_QWEN3_30B_A3B_THINKING_2507.id]: ReadonlyArray<'text'> [QWEN_QWEN3_32B.id]: ReadonlyArray<'text'> - [QWEN_QWEN3_8B.id]: ReadonlyArray<'text'> [QWEN_QWEN3_CODER.id]: ReadonlyArray<'text'> [QWEN_QWEN3_CODER_30B_A3B_INSTRUCT.id]: ReadonlyArray<'text'> [QWEN_QWEN3_CODER_FLASH.id]: ReadonlyArray<'text'> [QWEN_QWEN3_CODER_NEXT.id]: ReadonlyArray<'text'> - [QWEN_QWEN3_CODER_PLUS.id]: ReadonlyArray<'text'> - [QWEN_QWEN3_MAX.id]: ReadonlyArray<'text'> - [QWEN_QWEN3_MAX_THINKING.id]: ReadonlyArray<'text'> [QWEN_QWEN3_NEXT_80B_A3B_INSTRUCT.id]: ReadonlyArray<'text'> [QWEN_QWEN3_NEXT_80B_A3B_THINKING.id]: ReadonlyArray<'text'> [QWEN_QWEN3_VL_235B_A22B_INSTRUCT.id]: ReadonlyArray<'text' | 'image'> - [QWEN_QWEN3_VL_235B_A22B_THINKING.id]: ReadonlyArray<'text' | 'image'> [QWEN_QWEN3_VL_30B_A3B_INSTRUCT.id]: ReadonlyArray<'text' | 'image'> [QWEN_QWEN3_VL_30B_A3B_THINKING.id]: ReadonlyArray<'text' | 'image'> - [QWEN_QWEN3_VL_32B_INSTRUCT.id]: ReadonlyArray<'text' | 'image'> [QWEN_QWEN3_VL_8B_INSTRUCT.id]: ReadonlyArray<'image' | 'text'> - [QWEN_QWEN3_VL_8B_THINKING.id]: ReadonlyArray<'image' | 'text'> [QWEN_QWEN3_5_122B_A10B.id]: ReadonlyArray<'text' | 'image' | 'video'> [QWEN_QWEN3_5_27B.id]: ReadonlyArray<'text' | 'image' | 'video'> [QWEN_QWEN3_5_35B_A3B.id]: ReadonlyArray<'text' | 'image' | 'video'> @@ -20916,11 +20895,11 @@ export type OpenRouterModelInputModalitiesByName = { [QWEN_QWEN3_6_27B.id]: ReadonlyArray<'text' | 'image' | 'video'> [QWEN_QWEN3_6_35B_A3B.id]: ReadonlyArray<'text' | 'image' | 'video'> [QWEN_QWEN3_6_FLASH.id]: ReadonlyArray<'text' | 'image' | 'video'> - [QWEN_QWEN3_6_MAX_PREVIEW.id]: ReadonlyArray<'text'> [QWEN_QWEN3_6_PLUS.id]: ReadonlyArray<'text' | 'image' | 'video'> [QWEN_QWEN3_7_FLASH.id]: ReadonlyArray<'text' | 'image' | 'video'> [QWEN_QWEN3_7_MAX.id]: ReadonlyArray<'text'> [QWEN_QWEN3_7_PLUS.id]: ReadonlyArray<'text' | 'image'> + [QWEN_QWEN3_7_PLUS_BATCH.id]: ReadonlyArray<'text' | 'image'> [QWEN_QWEN3_8_2_4T_A95B.id]: ReadonlyArray<'text'> [QWEN_QWEN3_8_27B.id]: ReadonlyArray<'text' | 'image' | 'video'> [QWEN_QWEN3_8_FLASH.id]: ReadonlyArray<'text' | 'image' | 'video'> @@ -20929,6 +20908,8 @@ export type OpenRouterModelInputModalitiesByName = { [QWEN_QWEN3_8_OMNI_FLASH.id]: ReadonlyArray< 'text' | 'image' | 'audio' | 'video' > + [RECURSIVE_FLINT_V1_0_FREE.id]: ReadonlyArray<'text'> + [REFLECTION_BEAM_1_0_501B_A23B.id]: ReadonlyArray<'text'> [REKAAI_REKA_EDGE.id]: ReadonlyArray<'image' | 'text' | 'video'> [REKAAI_REKA_FLASH_3.id]: ReadonlyArray<'text'> [RELACE_RELACE_APPLY_3.id]: ReadonlyArray<'text'> @@ -20939,9 +20920,11 @@ export type OpenRouterModelInputModalitiesByName = { [SAKANA_SAKANA_NAMAZU.id]: ReadonlyArray<'text' | 'image' | 'document'> [SAO10K_L3_LUNARIS_8B.id]: ReadonlyArray<'text'> [SAO10K_L3_1_EURYALE_70B.id]: ReadonlyArray<'text'> - [SAO10K_L3_3_EURYALE_70B.id]: ReadonlyArray<'text'> + [SCALEDOWN_EXTRACT.id]: ReadonlyArray<'text' | 'image' | 'document'> + [SCALEDOWN_SUMMARIZE.id]: ReadonlyArray<'text' | 'image' | 'document'> [STEPFUN_STEP_3_5_FLASH.id]: ReadonlyArray<'text'> [STEPFUN_STEP_3_7_FLASH.id]: ReadonlyArray<'text' | 'image' | 'video'> + [STEPFUN_STEP_5_PREVIEW.id]: ReadonlyArray<'text' | 'image' | 'video'> [TENCENT_HUNYUAN_A13B_INSTRUCT.id]: ReadonlyArray<'text'> [TENCENT_HY_MT2_1_8B.id]: ReadonlyArray<'text'> [TENCENT_HY_MT2_30B_A3B.id]: ReadonlyArray<'text'> @@ -20958,8 +20941,8 @@ export type OpenRouterModelInputModalitiesByName = { 'text' | 'image' | 'audio' > [THINKINGMACHINES_INKLING_FREE.id]: ReadonlyArray<'text' | 'image' | 'audio'> - [UNBIASED_PARETO.id]: ReadonlyArray<'text' | 'image'> - [UNBIASED_PARETO_26_10_PREVIEW.id]: ReadonlyArray<'text' | 'image'> + [UNBIASED_PARETO_26_10.id]: ReadonlyArray<'text' | 'image'> + [UNBIASED_PARETO_26_9.id]: ReadonlyArray<'text' | 'image'> [UNDI95_REMM_SLERP_L2_13B.id]: ReadonlyArray<'text'> [UPSTAGE_SOLAR_MINI4.id]: ReadonlyArray<'text'> [UPSTAGE_SOLAR_PRO_3.id]: ReadonlyArray<'text'> @@ -20982,6 +20965,7 @@ export type OpenRouterModelInputModalitiesByName = { [XIAOMI_MIMO_V2_6_PRO_ULTRASPEED.id]: ReadonlyArray< 'text' | 'image' | 'video' | 'audio' > + [XINGCHEN_AGI_XING4_0_29B_A4B_FREE.id]: ReadonlyArray<'text'> [Z_AI_GLM_4_5.id]: ReadonlyArray<'text'> [Z_AI_GLM_4_5_AIR.id]: ReadonlyArray<'text'> [Z_AI_GLM_4_5V.id]: ReadonlyArray<'text' | 'image'> @@ -21021,6 +21005,7 @@ export const OPENROUTER_CHAT_MODELS = [ _OPENAI_GPT_MINI_LATEST.id, _OPENAI_GPT_SOL_LATEST.id, _OPENAI_GPT_TERRA_LATEST.id, + _UNBIASED_PARETO_LATEST.id, _X_AI_GROK_LATEST.id, _Z_AI_GLM_FLASH_LATEST.id, _Z_AI_GLM_LATEST.id, @@ -21042,6 +21027,8 @@ export const OPENROUTER_CHAT_MODELS = [ ANTHROPIC_CLAUDE_FABLE_5_1_BATCH.id, ANTHROPIC_CLAUDE_HAIKU_4_5.id, ANTHROPIC_CLAUDE_HAIKU_4_5_BATCH.id, + ANTHROPIC_CLAUDE_HAIKU_5_5.id, + ANTHROPIC_CLAUDE_HAIKU_5_5_BATCH.id, ANTHROPIC_CLAUDE_OPUS_4_1.id, ANTHROPIC_CLAUDE_OPUS_4_1_BATCH.id, ANTHROPIC_CLAUDE_OPUS_4_5.id, @@ -21056,7 +21043,6 @@ export const OPENROUTER_CHAT_MODELS = [ ANTHROPIC_CLAUDE_OPUS_5_BATCH.id, ANTHROPIC_CLAUDE_OPUS_5_5.id, ANTHROPIC_CLAUDE_OPUS_5_5_BATCH.id, - ANTHROPIC_CLAUDE_SONNET_4.id, ANTHROPIC_CLAUDE_SONNET_4_5.id, ANTHROPIC_CLAUDE_SONNET_4_5_BATCH.id, ANTHROPIC_CLAUDE_SONNET_4_6.id, @@ -21065,9 +21051,7 @@ export const OPENROUTER_CHAT_MODELS = [ ANTHROPIC_CLAUDE_SONNET_5_BATCH.id, ANTHROPIC_CLAUDE_SONNET_5_5.id, ANTHROPIC_CLAUDE_SONNET_5_5_BATCH.id, - APODEX_APODEX_1_1_MINI_FREE.id, ARCEE_AI_TRINITY_LARGE_THINKING.id, - BAIDU_ERNIE_4_5_VL_424B_A47B.id, BYTEDANCE_SEED_SEED_1_6.id, BYTEDANCE_SEED_SEED_1_6_FLASH.id, BYTEDANCE_SEED_SEED_2_1_TURBO.id, @@ -21085,7 +21069,6 @@ export const OPENROUTER_CHAT_MODELS = [ DEEPSEEK_DEEPSEEK_CHAT.id, DEEPSEEK_DEEPSEEK_CHAT_V3_0324.id, DEEPSEEK_DEEPSEEK_CHAT_V3_1.id, - DEEPSEEK_DEEPSEEK_R1.id, DEEPSEEK_DEEPSEEK_R1_0528.id, DEEPSEEK_DEEPSEEK_V3_1_TERMINUS.id, DEEPSEEK_DEEPSEEK_V3_2.id, @@ -21096,17 +21079,16 @@ export const OPENROUTER_CHAT_MODELS = [ DEEPSEEK_DEEPSEEK_V4_PRO.id, DEEPSEEK_DEEPSEEK_V4_PRO_0813.id, DEEPSEEK_DEEPSEEK_V4_1_FLASH.id, + DEEPSEEK_DEEPSEEK_V4_1_FLASH_1017.id, DEEPSEEK_DEEPSEEK_V4_1_FLASH_BATCH.id, DOTS_STUDIO_DOTS_3_NOTE_PREVIEW_FREE.id, + ELORIAN_GLIMPSE.id, FIREWORKS_EMBER_1.id, GOOGLE_GEMINI_2_5_FLASH.id, GOOGLE_GEMINI_2_5_FLASH_IMAGE.id, GOOGLE_GEMINI_2_5_FLASH_LITE.id, - GOOGLE_GEMINI_2_5_FLASH_LITE_BATCH.id, - GOOGLE_GEMINI_2_5_FLASH_BATCH.id, GOOGLE_GEMINI_2_5_PRO.id, GOOGLE_GEMINI_2_5_PRO_PREVIEW.id, - GOOGLE_GEMINI_2_5_PRO_BATCH.id, GOOGLE_GEMINI_3_FLASH_PREVIEW.id, GOOGLE_GEMINI_3_FLASH_PREVIEW_BATCH.id, GOOGLE_GEMINI_3_PRO_IMAGE.id, @@ -21130,6 +21112,8 @@ export const OPENROUTER_CHAT_MODELS = [ GOOGLE_GEMINI_3_7_FLASH_BATCH.id, GOOGLE_GEMINI_3_8_FLASH.id, GOOGLE_GEMINI_3_8_FLASH_BATCH.id, + GOOGLE_GEMINI_4_ARGON.id, + GOOGLE_GEMINI_4_ARGON_BATCH.id, GOOGLE_GEMINI_NANO_BANANA_2_1.id, GOOGLE_GEMMA_2_27B_IT.id, GOOGLE_GEMMA_3_12B_IT.id, @@ -21144,14 +21128,14 @@ export const OPENROUTER_CHAT_MODELS = [ IBM_GRANITE_GRANITE_4_2_8B.id, INCEPTION_MERCURY_2.id, INCEPTION_MERCURY_2_5.id, + INCEPTION_MERCURY_3.id, INCLUSIONAI_LING_3_0_FLASH.id, - INCLUSIONAI_LING_3_0_FLASH_FIN.id, - INCLUSIONAI_LING_3_0_FLASH_SANTE_FREE.id, INCLUSIONAI_LING_3_0_FLASH_VL.id, INCLUSIONAI_LING_3_1_FLASH.id, INFERENCE_NET_SCHEMATRON_V2_SMALL.id, INFERENCE_NET_SCHEMATRON_V2_TURBO.id, LIQUID_LFM_2_5_2_6B_FREE.id, + LIQUID_LFM_2_5_24B_A2B.id, MANCER_WEAVER.id, MEITUAN_LONGCAT_2_0.id, META_LLAMA_LLAMA_3_1_70B_INSTRUCT.id, @@ -21168,8 +21152,9 @@ export const OPENROUTER_CHAT_MODELS = [ META_MUSE_SPARK_1_2_CONTRIBUTOR.id, META_MUSE_SPARK_1_3.id, META_MUSE_SPARK_1_3_CONTRIBUTOR.id, + META_MUSE_SPARK_OPEN.id, + META_MUSE_WONDER.id, MICROSOFT_PHI_4.id, - MICROSOFT_WIZARDLM_2_8X22B.id, MINIMAX_MINIMAX_01.id, MINIMAX_MINIMAX_M1.id, MINIMAX_MINIMAX_M2.id, @@ -21178,6 +21163,7 @@ export const OPENROUTER_CHAT_MODELS = [ MINIMAX_MINIMAX_M2_5.id, MINIMAX_MINIMAX_M2_7.id, MINIMAX_MINIMAX_M3.id, + MINIMAX_MINIMAX_M3_1_FLASH_FREE.id, MISTRALAI_CODESTRAL_2508.id, MISTRALAI_CODESTRAL_2508_BATCH.id, MISTRALAI_DEVSTRAL_2512.id, @@ -21204,6 +21190,8 @@ export const OPENROUTER_CHAT_MODELS = [ MISTRALAI_MISTRAL_SMALL_3_2_24B_INSTRUCT.id, MISTRALAI_MIXTRAL_8X22B_INSTRUCT.id, MISTRALAI_VOXTRAL_SMALL_24B_2507.id, + MOONDREAM_MOONDREAM3_PREVIEW.id, + MOONDREAM_MOONDREAM3_1_9B_A2B.id, MOONSHOTAI_KIMI_K2.id, MOONSHOTAI_KIMI_K2_0905.id, MOONSHOTAI_KIMI_K2_THINKING.id, @@ -21229,6 +21217,8 @@ export const OPENROUTER_CHAT_MODELS = [ NVIDIA_NEMOTRON_3_5_CONTENT_SAFETY_FREE.id, NVIDIA_NEMOTRON_3_5_LIGHTNING.id, NVIDIA_NEMOTRON_3_5_LIGHTNING_FREE.id, + NVIDIA_NEMOTRON_3_5_SUPER_VL.id, + NVIDIA_NEMOTRON_3_5_SUPER_VL_FREE.id, OPENAI_GPT_3_5_TURBO.id, OPENAI_GPT_3_5_TURBO_0613.id, OPENAI_GPT_3_5_TURBO_16K.id, @@ -21312,6 +21302,8 @@ export const OPENROUTER_CHAT_MODELS = [ OPENAI_GPT_6_SOL_BATCH.id, OPENAI_GPT_6_1_SOL.id, OPENAI_GPT_6_1_SOL_PRO.id, + OPENAI_GPT_6_1_SOL_PRO_BATCH.id, + OPENAI_GPT_6_1_SOL_BATCH.id, OPENAI_GPT_AUDIO.id, OPENAI_GPT_AUDIO_MINI.id, OPENAI_GPT_CHAT_LATEST.id, @@ -21347,33 +21339,23 @@ export const OPENROUTER_CHAT_MODELS = [ QWEN_QWEN_2_5_7B_INSTRUCT.id, QWEN_QWEN_2_5_CODER_32B_INSTRUCT.id, QWEN_QWEN_PLUS.id, - QWEN_QWEN_PLUS_2025_07_28.id, QWEN_QWEN2_5_VL_72B_INSTRUCT.id, QWEN_QWEN3_14B.id, - QWEN_QWEN3_235B_A22B.id, QWEN_QWEN3_235B_A22B_2507.id, QWEN_QWEN3_235B_A22B_THINKING_2507.id, QWEN_QWEN3_30B_A3B.id, QWEN_QWEN3_30B_A3B_INSTRUCT_2507.id, - QWEN_QWEN3_30B_A3B_THINKING_2507.id, QWEN_QWEN3_32B.id, - QWEN_QWEN3_8B.id, QWEN_QWEN3_CODER.id, QWEN_QWEN3_CODER_30B_A3B_INSTRUCT.id, QWEN_QWEN3_CODER_FLASH.id, QWEN_QWEN3_CODER_NEXT.id, - QWEN_QWEN3_CODER_PLUS.id, - QWEN_QWEN3_MAX.id, - QWEN_QWEN3_MAX_THINKING.id, QWEN_QWEN3_NEXT_80B_A3B_INSTRUCT.id, QWEN_QWEN3_NEXT_80B_A3B_THINKING.id, QWEN_QWEN3_VL_235B_A22B_INSTRUCT.id, - QWEN_QWEN3_VL_235B_A22B_THINKING.id, QWEN_QWEN3_VL_30B_A3B_INSTRUCT.id, QWEN_QWEN3_VL_30B_A3B_THINKING.id, - QWEN_QWEN3_VL_32B_INSTRUCT.id, QWEN_QWEN3_VL_8B_INSTRUCT.id, - QWEN_QWEN3_VL_8B_THINKING.id, QWEN_QWEN3_5_122B_A10B.id, QWEN_QWEN3_5_27B.id, QWEN_QWEN3_5_35B_A3B.id, @@ -21385,17 +21367,19 @@ export const OPENROUTER_CHAT_MODELS = [ QWEN_QWEN3_6_27B.id, QWEN_QWEN3_6_35B_A3B.id, QWEN_QWEN3_6_FLASH.id, - QWEN_QWEN3_6_MAX_PREVIEW.id, QWEN_QWEN3_6_PLUS.id, QWEN_QWEN3_7_FLASH.id, QWEN_QWEN3_7_MAX.id, QWEN_QWEN3_7_PLUS.id, + QWEN_QWEN3_7_PLUS_BATCH.id, QWEN_QWEN3_8_2_4T_A95B.id, QWEN_QWEN3_8_27B.id, QWEN_QWEN3_8_FLASH.id, QWEN_QWEN3_8_MAX_0902.id, QWEN_QWEN3_8_MAX_PRIME.id, QWEN_QWEN3_8_OMNI_FLASH.id, + RECURSIVE_FLINT_V1_0_FREE.id, + REFLECTION_BEAM_1_0_501B_A23B.id, REKAAI_REKA_EDGE.id, REKAAI_REKA_FLASH_3.id, RELACE_RELACE_APPLY_3.id, @@ -21406,9 +21390,11 @@ export const OPENROUTER_CHAT_MODELS = [ SAKANA_SAKANA_NAMAZU.id, SAO10K_L3_LUNARIS_8B.id, SAO10K_L3_1_EURYALE_70B.id, - SAO10K_L3_3_EURYALE_70B.id, + SCALEDOWN_EXTRACT.id, + SCALEDOWN_SUMMARIZE.id, STEPFUN_STEP_3_5_FLASH.id, STEPFUN_STEP_3_7_FLASH.id, + STEPFUN_STEP_5_PREVIEW.id, TENCENT_HUNYUAN_A13B_INSTRUCT.id, TENCENT_HY_MT2_1_8B.id, TENCENT_HY_MT2_30B_A3B.id, @@ -21423,8 +21409,8 @@ export const OPENROUTER_CHAT_MODELS = [ THINKINGMACHINES_INKLING_SMALL.id, THINKINGMACHINES_INKLING_SMALL_FREE.id, THINKINGMACHINES_INKLING_FREE.id, - UNBIASED_PARETO.id, - UNBIASED_PARETO_26_10_PREVIEW.id, + UNBIASED_PARETO_26_10.id, + UNBIASED_PARETO_26_9.id, UNDI95_REMM_SLERP_L2_13B.id, UPSTAGE_SOLAR_MINI4.id, UPSTAGE_SOLAR_PRO_3.id, @@ -21443,6 +21429,7 @@ export const OPENROUTER_CHAT_MODELS = [ XIAOMI_MIMO_V2_6_FLASH.id, XIAOMI_MIMO_V2_6_PRO.id, XIAOMI_MIMO_V2_6_PRO_ULTRASPEED.id, + XINGCHEN_AGI_XING4_0_29B_A4B_FREE.id, Z_AI_GLM_4_5.id, Z_AI_GLM_4_5_AIR.id, Z_AI_GLM_4_5V.id, @@ -21494,6 +21481,7 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< [_OPENAI_GPT_MINI_LATEST.id]: _OPENAI_GPT_MINI_LATEST.supports.input, [_OPENAI_GPT_SOL_LATEST.id]: _OPENAI_GPT_SOL_LATEST.supports.input, [_OPENAI_GPT_TERRA_LATEST.id]: _OPENAI_GPT_TERRA_LATEST.supports.input, + [_UNBIASED_PARETO_LATEST.id]: _UNBIASED_PARETO_LATEST.supports.input, [_X_AI_GROK_LATEST.id]: _X_AI_GROK_LATEST.supports.input, [_Z_AI_GLM_FLASH_LATEST.id]: _Z_AI_GLM_FLASH_LATEST.supports.input, [_Z_AI_GLM_LATEST.id]: _Z_AI_GLM_LATEST.supports.input, @@ -21520,6 +21508,9 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< [ANTHROPIC_CLAUDE_HAIKU_4_5.id]: ANTHROPIC_CLAUDE_HAIKU_4_5.supports.input, [ANTHROPIC_CLAUDE_HAIKU_4_5_BATCH.id]: ANTHROPIC_CLAUDE_HAIKU_4_5_BATCH.supports.input, + [ANTHROPIC_CLAUDE_HAIKU_5_5.id]: ANTHROPIC_CLAUDE_HAIKU_5_5.supports.input, + [ANTHROPIC_CLAUDE_HAIKU_5_5_BATCH.id]: + ANTHROPIC_CLAUDE_HAIKU_5_5_BATCH.supports.input, [ANTHROPIC_CLAUDE_OPUS_4_1.id]: ANTHROPIC_CLAUDE_OPUS_4_1.supports.input, [ANTHROPIC_CLAUDE_OPUS_4_1_BATCH.id]: ANTHROPIC_CLAUDE_OPUS_4_1_BATCH.supports.input, @@ -21541,7 +21532,6 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< [ANTHROPIC_CLAUDE_OPUS_5_5.id]: ANTHROPIC_CLAUDE_OPUS_5_5.supports.input, [ANTHROPIC_CLAUDE_OPUS_5_5_BATCH.id]: ANTHROPIC_CLAUDE_OPUS_5_5_BATCH.supports.input, - [ANTHROPIC_CLAUDE_SONNET_4.id]: ANTHROPIC_CLAUDE_SONNET_4.supports.input, [ANTHROPIC_CLAUDE_SONNET_4_5.id]: ANTHROPIC_CLAUDE_SONNET_4_5.supports.input, [ANTHROPIC_CLAUDE_SONNET_4_5_BATCH.id]: ANTHROPIC_CLAUDE_SONNET_4_5_BATCH.supports.input, @@ -21554,11 +21544,8 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< [ANTHROPIC_CLAUDE_SONNET_5_5.id]: ANTHROPIC_CLAUDE_SONNET_5_5.supports.input, [ANTHROPIC_CLAUDE_SONNET_5_5_BATCH.id]: ANTHROPIC_CLAUDE_SONNET_5_5_BATCH.supports.input, - [APODEX_APODEX_1_1_MINI_FREE.id]: APODEX_APODEX_1_1_MINI_FREE.supports.input, [ARCEE_AI_TRINITY_LARGE_THINKING.id]: ARCEE_AI_TRINITY_LARGE_THINKING.supports.input, - [BAIDU_ERNIE_4_5_VL_424B_A47B.id]: - BAIDU_ERNIE_4_5_VL_424B_A47B.supports.input, [BYTEDANCE_SEED_SEED_1_6.id]: BYTEDANCE_SEED_SEED_1_6.supports.input, [BYTEDANCE_SEED_SEED_1_6_FLASH.id]: BYTEDANCE_SEED_SEED_1_6_FLASH.supports.input, @@ -21584,7 +21571,6 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< [DEEPSEEK_DEEPSEEK_CHAT_V3_0324.id]: DEEPSEEK_DEEPSEEK_CHAT_V3_0324.supports.input, [DEEPSEEK_DEEPSEEK_CHAT_V3_1.id]: DEEPSEEK_DEEPSEEK_CHAT_V3_1.supports.input, - [DEEPSEEK_DEEPSEEK_R1.id]: DEEPSEEK_DEEPSEEK_R1.supports.input, [DEEPSEEK_DEEPSEEK_R1_0528.id]: DEEPSEEK_DEEPSEEK_R1_0528.supports.input, [DEEPSEEK_DEEPSEEK_V3_1_TERMINUS.id]: DEEPSEEK_DEEPSEEK_V3_1_TERMINUS.supports.input, @@ -21600,24 +21586,22 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< DEEPSEEK_DEEPSEEK_V4_PRO_0813.supports.input, [DEEPSEEK_DEEPSEEK_V4_1_FLASH.id]: DEEPSEEK_DEEPSEEK_V4_1_FLASH.supports.input, + [DEEPSEEK_DEEPSEEK_V4_1_FLASH_1017.id]: + DEEPSEEK_DEEPSEEK_V4_1_FLASH_1017.supports.input, [DEEPSEEK_DEEPSEEK_V4_1_FLASH_BATCH.id]: DEEPSEEK_DEEPSEEK_V4_1_FLASH_BATCH.supports.input, [DOTS_STUDIO_DOTS_3_NOTE_PREVIEW_FREE.id]: DOTS_STUDIO_DOTS_3_NOTE_PREVIEW_FREE.supports.input, + [ELORIAN_GLIMPSE.id]: ELORIAN_GLIMPSE.supports.input, [FIREWORKS_EMBER_1.id]: FIREWORKS_EMBER_1.supports.input, [GOOGLE_GEMINI_2_5_FLASH.id]: GOOGLE_GEMINI_2_5_FLASH.supports.input, [GOOGLE_GEMINI_2_5_FLASH_IMAGE.id]: GOOGLE_GEMINI_2_5_FLASH_IMAGE.supports.input, [GOOGLE_GEMINI_2_5_FLASH_LITE.id]: GOOGLE_GEMINI_2_5_FLASH_LITE.supports.input, - [GOOGLE_GEMINI_2_5_FLASH_LITE_BATCH.id]: - GOOGLE_GEMINI_2_5_FLASH_LITE_BATCH.supports.input, - [GOOGLE_GEMINI_2_5_FLASH_BATCH.id]: - GOOGLE_GEMINI_2_5_FLASH_BATCH.supports.input, [GOOGLE_GEMINI_2_5_PRO.id]: GOOGLE_GEMINI_2_5_PRO.supports.input, [GOOGLE_GEMINI_2_5_PRO_PREVIEW.id]: GOOGLE_GEMINI_2_5_PRO_PREVIEW.supports.input, - [GOOGLE_GEMINI_2_5_PRO_BATCH.id]: GOOGLE_GEMINI_2_5_PRO_BATCH.supports.input, [GOOGLE_GEMINI_3_FLASH_PREVIEW.id]: GOOGLE_GEMINI_3_FLASH_PREVIEW.supports.input, [GOOGLE_GEMINI_3_FLASH_PREVIEW_BATCH.id]: @@ -21659,6 +21643,8 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< [GOOGLE_GEMINI_3_8_FLASH.id]: GOOGLE_GEMINI_3_8_FLASH.supports.input, [GOOGLE_GEMINI_3_8_FLASH_BATCH.id]: GOOGLE_GEMINI_3_8_FLASH_BATCH.supports.input, + [GOOGLE_GEMINI_4_ARGON.id]: GOOGLE_GEMINI_4_ARGON.supports.input, + [GOOGLE_GEMINI_4_ARGON_BATCH.id]: GOOGLE_GEMINI_4_ARGON_BATCH.supports.input, [GOOGLE_GEMINI_NANO_BANANA_2_1.id]: GOOGLE_GEMINI_NANO_BANANA_2_1.supports.input, [GOOGLE_GEMMA_2_27B_IT.id]: GOOGLE_GEMMA_2_27B_IT.supports.input, @@ -21676,11 +21662,8 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< [IBM_GRANITE_GRANITE_4_2_8B.id]: IBM_GRANITE_GRANITE_4_2_8B.supports.input, [INCEPTION_MERCURY_2.id]: INCEPTION_MERCURY_2.supports.input, [INCEPTION_MERCURY_2_5.id]: INCEPTION_MERCURY_2_5.supports.input, + [INCEPTION_MERCURY_3.id]: INCEPTION_MERCURY_3.supports.input, [INCLUSIONAI_LING_3_0_FLASH.id]: INCLUSIONAI_LING_3_0_FLASH.supports.input, - [INCLUSIONAI_LING_3_0_FLASH_FIN.id]: - INCLUSIONAI_LING_3_0_FLASH_FIN.supports.input, - [INCLUSIONAI_LING_3_0_FLASH_SANTE_FREE.id]: - INCLUSIONAI_LING_3_0_FLASH_SANTE_FREE.supports.input, [INCLUSIONAI_LING_3_0_FLASH_VL.id]: INCLUSIONAI_LING_3_0_FLASH_VL.supports.input, [INCLUSIONAI_LING_3_1_FLASH.id]: INCLUSIONAI_LING_3_1_FLASH.supports.input, @@ -21689,6 +21672,7 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< [INFERENCE_NET_SCHEMATRON_V2_TURBO.id]: INFERENCE_NET_SCHEMATRON_V2_TURBO.supports.input, [LIQUID_LFM_2_5_2_6B_FREE.id]: LIQUID_LFM_2_5_2_6B_FREE.supports.input, + [LIQUID_LFM_2_5_24B_A2B.id]: LIQUID_LFM_2_5_24B_A2B.supports.input, [MANCER_WEAVER.id]: MANCER_WEAVER.supports.input, [MEITUAN_LONGCAT_2_0.id]: MEITUAN_LONGCAT_2_0.supports.input, [META_LLAMA_LLAMA_3_1_70B_INSTRUCT.id]: @@ -21713,8 +21697,9 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< [META_MUSE_SPARK_1_3.id]: META_MUSE_SPARK_1_3.supports.input, [META_MUSE_SPARK_1_3_CONTRIBUTOR.id]: META_MUSE_SPARK_1_3_CONTRIBUTOR.supports.input, + [META_MUSE_SPARK_OPEN.id]: META_MUSE_SPARK_OPEN.supports.input, + [META_MUSE_WONDER.id]: META_MUSE_WONDER.supports.input, [MICROSOFT_PHI_4.id]: MICROSOFT_PHI_4.supports.input, - [MICROSOFT_WIZARDLM_2_8X22B.id]: MICROSOFT_WIZARDLM_2_8X22B.supports.input, [MINIMAX_MINIMAX_01.id]: MINIMAX_MINIMAX_01.supports.input, [MINIMAX_MINIMAX_M1.id]: MINIMAX_MINIMAX_M1.supports.input, [MINIMAX_MINIMAX_M2.id]: MINIMAX_MINIMAX_M2.supports.input, @@ -21723,6 +21708,8 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< [MINIMAX_MINIMAX_M2_5.id]: MINIMAX_MINIMAX_M2_5.supports.input, [MINIMAX_MINIMAX_M2_7.id]: MINIMAX_MINIMAX_M2_7.supports.input, [MINIMAX_MINIMAX_M3.id]: MINIMAX_MINIMAX_M3.supports.input, + [MINIMAX_MINIMAX_M3_1_FLASH_FREE.id]: + MINIMAX_MINIMAX_M3_1_FLASH_FREE.supports.input, [MISTRALAI_CODESTRAL_2508.id]: MISTRALAI_CODESTRAL_2508.supports.input, [MISTRALAI_CODESTRAL_2508_BATCH.id]: MISTRALAI_CODESTRAL_2508_BATCH.supports.input, @@ -21766,6 +21753,10 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< MISTRALAI_MIXTRAL_8X22B_INSTRUCT.supports.input, [MISTRALAI_VOXTRAL_SMALL_24B_2507.id]: MISTRALAI_VOXTRAL_SMALL_24B_2507.supports.input, + [MOONDREAM_MOONDREAM3_PREVIEW.id]: + MOONDREAM_MOONDREAM3_PREVIEW.supports.input, + [MOONDREAM_MOONDREAM3_1_9B_A2B.id]: + MOONDREAM_MOONDREAM3_1_9B_A2B.supports.input, [MOONSHOTAI_KIMI_K2.id]: MOONSHOTAI_KIMI_K2.supports.input, [MOONSHOTAI_KIMI_K2_0905.id]: MOONSHOTAI_KIMI_K2_0905.supports.input, [MOONSHOTAI_KIMI_K2_THINKING.id]: MOONSHOTAI_KIMI_K2_THINKING.supports.input, @@ -21803,6 +21794,10 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< NVIDIA_NEMOTRON_3_5_LIGHTNING.supports.input, [NVIDIA_NEMOTRON_3_5_LIGHTNING_FREE.id]: NVIDIA_NEMOTRON_3_5_LIGHTNING_FREE.supports.input, + [NVIDIA_NEMOTRON_3_5_SUPER_VL.id]: + NVIDIA_NEMOTRON_3_5_SUPER_VL.supports.input, + [NVIDIA_NEMOTRON_3_5_SUPER_VL_FREE.id]: + NVIDIA_NEMOTRON_3_5_SUPER_VL_FREE.supports.input, [OPENAI_GPT_3_5_TURBO.id]: OPENAI_GPT_3_5_TURBO.supports.input, [OPENAI_GPT_3_5_TURBO_0613.id]: OPENAI_GPT_3_5_TURBO_0613.supports.input, [OPENAI_GPT_3_5_TURBO_16K.id]: OPENAI_GPT_3_5_TURBO_16K.supports.input, @@ -21892,6 +21887,9 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< [OPENAI_GPT_6_SOL_BATCH.id]: OPENAI_GPT_6_SOL_BATCH.supports.input, [OPENAI_GPT_6_1_SOL.id]: OPENAI_GPT_6_1_SOL.supports.input, [OPENAI_GPT_6_1_SOL_PRO.id]: OPENAI_GPT_6_1_SOL_PRO.supports.input, + [OPENAI_GPT_6_1_SOL_PRO_BATCH.id]: + OPENAI_GPT_6_1_SOL_PRO_BATCH.supports.input, + [OPENAI_GPT_6_1_SOL_BATCH.id]: OPENAI_GPT_6_1_SOL_BATCH.supports.input, [OPENAI_GPT_AUDIO.id]: OPENAI_GPT_AUDIO.supports.input, [OPENAI_GPT_AUDIO_MINI.id]: OPENAI_GPT_AUDIO_MINI.supports.input, [OPENAI_GPT_CHAT_LATEST.id]: OPENAI_GPT_CHAT_LATEST.supports.input, @@ -21932,44 +21930,32 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< [QWEN_QWEN_2_5_CODER_32B_INSTRUCT.id]: QWEN_QWEN_2_5_CODER_32B_INSTRUCT.supports.input, [QWEN_QWEN_PLUS.id]: QWEN_QWEN_PLUS.supports.input, - [QWEN_QWEN_PLUS_2025_07_28.id]: QWEN_QWEN_PLUS_2025_07_28.supports.input, [QWEN_QWEN2_5_VL_72B_INSTRUCT.id]: QWEN_QWEN2_5_VL_72B_INSTRUCT.supports.input, [QWEN_QWEN3_14B.id]: QWEN_QWEN3_14B.supports.input, - [QWEN_QWEN3_235B_A22B.id]: QWEN_QWEN3_235B_A22B.supports.input, [QWEN_QWEN3_235B_A22B_2507.id]: QWEN_QWEN3_235B_A22B_2507.supports.input, [QWEN_QWEN3_235B_A22B_THINKING_2507.id]: QWEN_QWEN3_235B_A22B_THINKING_2507.supports.input, [QWEN_QWEN3_30B_A3B.id]: QWEN_QWEN3_30B_A3B.supports.input, [QWEN_QWEN3_30B_A3B_INSTRUCT_2507.id]: QWEN_QWEN3_30B_A3B_INSTRUCT_2507.supports.input, - [QWEN_QWEN3_30B_A3B_THINKING_2507.id]: - QWEN_QWEN3_30B_A3B_THINKING_2507.supports.input, [QWEN_QWEN3_32B.id]: QWEN_QWEN3_32B.supports.input, - [QWEN_QWEN3_8B.id]: QWEN_QWEN3_8B.supports.input, [QWEN_QWEN3_CODER.id]: QWEN_QWEN3_CODER.supports.input, [QWEN_QWEN3_CODER_30B_A3B_INSTRUCT.id]: QWEN_QWEN3_CODER_30B_A3B_INSTRUCT.supports.input, [QWEN_QWEN3_CODER_FLASH.id]: QWEN_QWEN3_CODER_FLASH.supports.input, [QWEN_QWEN3_CODER_NEXT.id]: QWEN_QWEN3_CODER_NEXT.supports.input, - [QWEN_QWEN3_CODER_PLUS.id]: QWEN_QWEN3_CODER_PLUS.supports.input, - [QWEN_QWEN3_MAX.id]: QWEN_QWEN3_MAX.supports.input, - [QWEN_QWEN3_MAX_THINKING.id]: QWEN_QWEN3_MAX_THINKING.supports.input, [QWEN_QWEN3_NEXT_80B_A3B_INSTRUCT.id]: QWEN_QWEN3_NEXT_80B_A3B_INSTRUCT.supports.input, [QWEN_QWEN3_NEXT_80B_A3B_THINKING.id]: QWEN_QWEN3_NEXT_80B_A3B_THINKING.supports.input, [QWEN_QWEN3_VL_235B_A22B_INSTRUCT.id]: QWEN_QWEN3_VL_235B_A22B_INSTRUCT.supports.input, - [QWEN_QWEN3_VL_235B_A22B_THINKING.id]: - QWEN_QWEN3_VL_235B_A22B_THINKING.supports.input, [QWEN_QWEN3_VL_30B_A3B_INSTRUCT.id]: QWEN_QWEN3_VL_30B_A3B_INSTRUCT.supports.input, [QWEN_QWEN3_VL_30B_A3B_THINKING.id]: QWEN_QWEN3_VL_30B_A3B_THINKING.supports.input, - [QWEN_QWEN3_VL_32B_INSTRUCT.id]: QWEN_QWEN3_VL_32B_INSTRUCT.supports.input, [QWEN_QWEN3_VL_8B_INSTRUCT.id]: QWEN_QWEN3_VL_8B_INSTRUCT.supports.input, - [QWEN_QWEN3_VL_8B_THINKING.id]: QWEN_QWEN3_VL_8B_THINKING.supports.input, [QWEN_QWEN3_5_122B_A10B.id]: QWEN_QWEN3_5_122B_A10B.supports.input, [QWEN_QWEN3_5_27B.id]: QWEN_QWEN3_5_27B.supports.input, [QWEN_QWEN3_5_35B_A3B.id]: QWEN_QWEN3_5_35B_A3B.supports.input, @@ -21981,17 +21967,20 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< [QWEN_QWEN3_6_27B.id]: QWEN_QWEN3_6_27B.supports.input, [QWEN_QWEN3_6_35B_A3B.id]: QWEN_QWEN3_6_35B_A3B.supports.input, [QWEN_QWEN3_6_FLASH.id]: QWEN_QWEN3_6_FLASH.supports.input, - [QWEN_QWEN3_6_MAX_PREVIEW.id]: QWEN_QWEN3_6_MAX_PREVIEW.supports.input, [QWEN_QWEN3_6_PLUS.id]: QWEN_QWEN3_6_PLUS.supports.input, [QWEN_QWEN3_7_FLASH.id]: QWEN_QWEN3_7_FLASH.supports.input, [QWEN_QWEN3_7_MAX.id]: QWEN_QWEN3_7_MAX.supports.input, [QWEN_QWEN3_7_PLUS.id]: QWEN_QWEN3_7_PLUS.supports.input, + [QWEN_QWEN3_7_PLUS_BATCH.id]: QWEN_QWEN3_7_PLUS_BATCH.supports.input, [QWEN_QWEN3_8_2_4T_A95B.id]: QWEN_QWEN3_8_2_4T_A95B.supports.input, [QWEN_QWEN3_8_27B.id]: QWEN_QWEN3_8_27B.supports.input, [QWEN_QWEN3_8_FLASH.id]: QWEN_QWEN3_8_FLASH.supports.input, [QWEN_QWEN3_8_MAX_0902.id]: QWEN_QWEN3_8_MAX_0902.supports.input, [QWEN_QWEN3_8_MAX_PRIME.id]: QWEN_QWEN3_8_MAX_PRIME.supports.input, [QWEN_QWEN3_8_OMNI_FLASH.id]: QWEN_QWEN3_8_OMNI_FLASH.supports.input, + [RECURSIVE_FLINT_V1_0_FREE.id]: RECURSIVE_FLINT_V1_0_FREE.supports.input, + [REFLECTION_BEAM_1_0_501B_A23B.id]: + REFLECTION_BEAM_1_0_501B_A23B.supports.input, [REKAAI_REKA_EDGE.id]: REKAAI_REKA_EDGE.supports.input, [REKAAI_REKA_FLASH_3.id]: REKAAI_REKA_FLASH_3.supports.input, [RELACE_RELACE_APPLY_3.id]: RELACE_RELACE_APPLY_3.supports.input, @@ -22002,9 +21991,11 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< [SAKANA_SAKANA_NAMAZU.id]: SAKANA_SAKANA_NAMAZU.supports.input, [SAO10K_L3_LUNARIS_8B.id]: SAO10K_L3_LUNARIS_8B.supports.input, [SAO10K_L3_1_EURYALE_70B.id]: SAO10K_L3_1_EURYALE_70B.supports.input, - [SAO10K_L3_3_EURYALE_70B.id]: SAO10K_L3_3_EURYALE_70B.supports.input, + [SCALEDOWN_EXTRACT.id]: SCALEDOWN_EXTRACT.supports.input, + [SCALEDOWN_SUMMARIZE.id]: SCALEDOWN_SUMMARIZE.supports.input, [STEPFUN_STEP_3_5_FLASH.id]: STEPFUN_STEP_3_5_FLASH.supports.input, [STEPFUN_STEP_3_7_FLASH.id]: STEPFUN_STEP_3_7_FLASH.supports.input, + [STEPFUN_STEP_5_PREVIEW.id]: STEPFUN_STEP_5_PREVIEW.supports.input, [TENCENT_HUNYUAN_A13B_INSTRUCT.id]: TENCENT_HUNYUAN_A13B_INSTRUCT.supports.input, [TENCENT_HY_MT2_1_8B.id]: TENCENT_HY_MT2_1_8B.supports.input, @@ -22023,9 +22014,8 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< THINKINGMACHINES_INKLING_SMALL_FREE.supports.input, [THINKINGMACHINES_INKLING_FREE.id]: THINKINGMACHINES_INKLING_FREE.supports.input, - [UNBIASED_PARETO.id]: UNBIASED_PARETO.supports.input, - [UNBIASED_PARETO_26_10_PREVIEW.id]: - UNBIASED_PARETO_26_10_PREVIEW.supports.input, + [UNBIASED_PARETO_26_10.id]: UNBIASED_PARETO_26_10.supports.input, + [UNBIASED_PARETO_26_9.id]: UNBIASED_PARETO_26_9.supports.input, [UNDI95_REMM_SLERP_L2_13B.id]: UNDI95_REMM_SLERP_L2_13B.supports.input, [UPSTAGE_SOLAR_MINI4.id]: UPSTAGE_SOLAR_MINI4.supports.input, [UPSTAGE_SOLAR_PRO_3.id]: UPSTAGE_SOLAR_PRO_3.supports.input, @@ -22045,6 +22035,8 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< [XIAOMI_MIMO_V2_6_PRO.id]: XIAOMI_MIMO_V2_6_PRO.supports.input, [XIAOMI_MIMO_V2_6_PRO_ULTRASPEED.id]: XIAOMI_MIMO_V2_6_PRO_ULTRASPEED.supports.input, + [XINGCHEN_AGI_XING4_0_29B_A4B_FREE.id]: + XINGCHEN_AGI_XING4_0_29B_A4B_FREE.supports.input, [Z_AI_GLM_4_5.id]: Z_AI_GLM_4_5.supports.input, [Z_AI_GLM_4_5_AIR.id]: Z_AI_GLM_4_5_AIR.supports.input, [Z_AI_GLM_4_5V.id]: Z_AI_GLM_4_5V.supports.input, @@ -22132,7 +22124,6 @@ const OPENROUTER_REASONING = { [ANTHROPIC_CLAUDE_OPUS_5_5.id]: ANTHROPIC_CLAUDE_OPUS_5_5.reasoning, [ANTHROPIC_CLAUDE_OPUS_5_5_BATCH.id]: ANTHROPIC_CLAUDE_OPUS_5_5_BATCH.reasoning, - [ANTHROPIC_CLAUDE_SONNET_4.id]: ANTHROPIC_CLAUDE_SONNET_4.reasoning, [ANTHROPIC_CLAUDE_SONNET_4_5.id]: ANTHROPIC_CLAUDE_SONNET_4_5.reasoning, [ANTHROPIC_CLAUDE_SONNET_4_5_BATCH.id]: ANTHROPIC_CLAUDE_SONNET_4_5_BATCH.reasoning, @@ -22147,7 +22138,6 @@ const OPENROUTER_REASONING = { ANTHROPIC_CLAUDE_SONNET_5_5_BATCH.reasoning, [ARCEE_AI_TRINITY_LARGE_THINKING.id]: ARCEE_AI_TRINITY_LARGE_THINKING.reasoning, - [BAIDU_ERNIE_4_5_VL_424B_A47B.id]: BAIDU_ERNIE_4_5_VL_424B_A47B.reasoning, [BYTEDANCE_SEED_SEED_1_6.id]: BYTEDANCE_SEED_SEED_1_6.reasoning, [BYTEDANCE_SEED_SEED_1_6_FLASH.id]: BYTEDANCE_SEED_SEED_1_6_FLASH.reasoning, [BYTEDANCE_SEED_SEED_2_1_TURBO.id]: BYTEDANCE_SEED_SEED_2_1_TURBO.reasoning, @@ -22157,7 +22147,6 @@ const OPENROUTER_REASONING = { [COHERE_COMMAND_A_PLUS.id]: COHERE_COMMAND_A_PLUS.reasoning, [COHERE_NORTH_MINI_CODE_FREE.id]: COHERE_NORTH_MINI_CODE_FREE.reasoning, [DEEPSEEK_DEEPSEEK_CHAT_V3_1.id]: DEEPSEEK_DEEPSEEK_CHAT_V3_1.reasoning, - [DEEPSEEK_DEEPSEEK_R1.id]: DEEPSEEK_DEEPSEEK_R1.reasoning, [DEEPSEEK_DEEPSEEK_R1_0528.id]: DEEPSEEK_DEEPSEEK_R1_0528.reasoning, [DEEPSEEK_DEEPSEEK_V3_1_TERMINUS.id]: DEEPSEEK_DEEPSEEK_V3_1_TERMINUS.reasoning, @@ -22178,12 +22167,8 @@ const OPENROUTER_REASONING = { [FIREWORKS_EMBER_1.id]: FIREWORKS_EMBER_1.reasoning, [GOOGLE_GEMINI_2_5_FLASH.id]: GOOGLE_GEMINI_2_5_FLASH.reasoning, [GOOGLE_GEMINI_2_5_FLASH_LITE.id]: GOOGLE_GEMINI_2_5_FLASH_LITE.reasoning, - [GOOGLE_GEMINI_2_5_FLASH_LITE_BATCH.id]: - GOOGLE_GEMINI_2_5_FLASH_LITE_BATCH.reasoning, - [GOOGLE_GEMINI_2_5_FLASH_BATCH.id]: GOOGLE_GEMINI_2_5_FLASH_BATCH.reasoning, [GOOGLE_GEMINI_2_5_PRO.id]: GOOGLE_GEMINI_2_5_PRO.reasoning, [GOOGLE_GEMINI_2_5_PRO_PREVIEW.id]: GOOGLE_GEMINI_2_5_PRO_PREVIEW.reasoning, - [GOOGLE_GEMINI_2_5_PRO_BATCH.id]: GOOGLE_GEMINI_2_5_PRO_BATCH.reasoning, [GOOGLE_GEMINI_3_FLASH_PREVIEW.id]: GOOGLE_GEMINI_3_FLASH_PREVIEW.reasoning, [GOOGLE_GEMINI_3_FLASH_PREVIEW_BATCH.id]: GOOGLE_GEMINI_3_FLASH_PREVIEW_BATCH.reasoning, @@ -22224,9 +22209,6 @@ const OPENROUTER_REASONING = { [INCEPTION_MERCURY_2.id]: INCEPTION_MERCURY_2.reasoning, [INCEPTION_MERCURY_2_5.id]: INCEPTION_MERCURY_2_5.reasoning, [INCLUSIONAI_LING_3_0_FLASH.id]: INCLUSIONAI_LING_3_0_FLASH.reasoning, - [INCLUSIONAI_LING_3_0_FLASH_FIN.id]: INCLUSIONAI_LING_3_0_FLASH_FIN.reasoning, - [INCLUSIONAI_LING_3_0_FLASH_SANTE_FREE.id]: - INCLUSIONAI_LING_3_0_FLASH_SANTE_FREE.reasoning, [INCLUSIONAI_LING_3_0_FLASH_VL.id]: INCLUSIONAI_LING_3_0_FLASH_VL.reasoning, [LIQUID_LFM_2_5_2_6B_FREE.id]: LIQUID_LFM_2_5_2_6B_FREE.reasoning, [MEITUAN_LONGCAT_2_0.id]: MEITUAN_LONGCAT_2_0.reasoning, @@ -22364,21 +22346,13 @@ const OPENROUTER_REASONING = { [POOLSIDE_LAGUNA_XS_2_1_FREE.id]: POOLSIDE_LAGUNA_XS_2_1_FREE.reasoning, [PRISM_ML_TERNARY_BONSAI_2_27B.id]: PRISM_ML_TERNARY_BONSAI_2_27B.reasoning, [QWEN_QWEN3_14B.id]: QWEN_QWEN3_14B.reasoning, - [QWEN_QWEN3_235B_A22B.id]: QWEN_QWEN3_235B_A22B.reasoning, [QWEN_QWEN3_235B_A22B_THINKING_2507.id]: QWEN_QWEN3_235B_A22B_THINKING_2507.reasoning, [QWEN_QWEN3_30B_A3B.id]: QWEN_QWEN3_30B_A3B.reasoning, - [QWEN_QWEN3_30B_A3B_THINKING_2507.id]: - QWEN_QWEN3_30B_A3B_THINKING_2507.reasoning, [QWEN_QWEN3_32B.id]: QWEN_QWEN3_32B.reasoning, - [QWEN_QWEN3_8B.id]: QWEN_QWEN3_8B.reasoning, - [QWEN_QWEN3_MAX_THINKING.id]: QWEN_QWEN3_MAX_THINKING.reasoning, [QWEN_QWEN3_NEXT_80B_A3B_THINKING.id]: QWEN_QWEN3_NEXT_80B_A3B_THINKING.reasoning, - [QWEN_QWEN3_VL_235B_A22B_THINKING.id]: - QWEN_QWEN3_VL_235B_A22B_THINKING.reasoning, [QWEN_QWEN3_VL_30B_A3B_THINKING.id]: QWEN_QWEN3_VL_30B_A3B_THINKING.reasoning, - [QWEN_QWEN3_VL_8B_THINKING.id]: QWEN_QWEN3_VL_8B_THINKING.reasoning, [QWEN_QWEN3_5_122B_A10B.id]: QWEN_QWEN3_5_122B_A10B.reasoning, [QWEN_QWEN3_5_27B.id]: QWEN_QWEN3_5_27B.reasoning, [QWEN_QWEN3_5_35B_A3B.id]: QWEN_QWEN3_5_35B_A3B.reasoning, @@ -22390,7 +22364,6 @@ const OPENROUTER_REASONING = { [QWEN_QWEN3_6_27B.id]: QWEN_QWEN3_6_27B.reasoning, [QWEN_QWEN3_6_35B_A3B.id]: QWEN_QWEN3_6_35B_A3B.reasoning, [QWEN_QWEN3_6_FLASH.id]: QWEN_QWEN3_6_FLASH.reasoning, - [QWEN_QWEN3_6_MAX_PREVIEW.id]: QWEN_QWEN3_6_MAX_PREVIEW.reasoning, [QWEN_QWEN3_6_PLUS.id]: QWEN_QWEN3_6_PLUS.reasoning, [QWEN_QWEN3_7_FLASH.id]: QWEN_QWEN3_7_FLASH.reasoning, [QWEN_QWEN3_7_MAX.id]: QWEN_QWEN3_7_MAX.reasoning, @@ -22601,7 +22574,7 @@ export const OPENROUTER_VIDEO_MODEL_META = { ], resolutions: ['480p', '720p', '1080p'], aspectRatios: ['16:9', '4:3', '1:1', '3:4', '9:16'], - frameImages: ['first_frame'], + frameImages: ['first_frame', 'last_frame'], sizes: null, generateAudio: true, seed: true, @@ -22614,15 +22587,15 @@ export const OPENROUTER_VIDEO_MODEL_META = { ], resolutions: ['480p', '720p', '1080p'], aspectRatios: ['16:9', '4:3', '1:1', '3:4', '9:16'], - frameImages: ['first_frame'], + frameImages: ['first_frame', 'last_frame'], sizes: null, generateAudio: true, seed: true, }, 'black-forest-labs/flux-3-video': { - name: 'Black Forest Labs: FLUX.3 Video', + name: 'Black Forest Labs: FLUX 3 Video', durations: [5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20], - resolutions: ['720p', '1080p'], + resolutions: ['720p', '1080p', '2K', '4K'], aspectRatios: ['21:9', '16:9', '4:3', '1:1', '3:4', '9:16'], frameImages: ['first_frame', 'last_frame'], sizes: null, @@ -23024,6 +22997,8 @@ export const OPENROUTER_COMBINED_TOOLS_AND_SCHEMA_MODELS: ReadonlySet = ANTHROPIC_CLAUDE_FABLE_5_1_BATCH.id, ANTHROPIC_CLAUDE_HAIKU_4_5.id, ANTHROPIC_CLAUDE_HAIKU_4_5_BATCH.id, + ANTHROPIC_CLAUDE_HAIKU_5_5.id, + ANTHROPIC_CLAUDE_HAIKU_5_5_BATCH.id, ANTHROPIC_CLAUDE_OPUS_4_1_BATCH.id, ANTHROPIC_CLAUDE_OPUS_4_5.id, ANTHROPIC_CLAUDE_OPUS_4_5_BATCH.id, @@ -23045,7 +23020,6 @@ export const OPENROUTER_COMBINED_TOOLS_AND_SCHEMA_MODELS: ReadonlySet = ANTHROPIC_CLAUDE_SONNET_5_BATCH.id, ANTHROPIC_CLAUDE_SONNET_5_5.id, ANTHROPIC_CLAUDE_SONNET_5_5_BATCH.id, - APODEX_APODEX_1_1_MINI_FREE.id, BYTEDANCE_SEED_SEED_1_6.id, BYTEDANCE_SEED_SEED_1_6_FLASH.id, BYTEDANCE_SEED_SEED_2_1_TURBO.id, @@ -23067,16 +23041,15 @@ export const OPENROUTER_COMBINED_TOOLS_AND_SCHEMA_MODELS: ReadonlySet = DEEPSEEK_DEEPSEEK_V4_PRO.id, DEEPSEEK_DEEPSEEK_V4_PRO_0813.id, DEEPSEEK_DEEPSEEK_V4_1_FLASH.id, + DEEPSEEK_DEEPSEEK_V4_1_FLASH_1017.id, DEEPSEEK_DEEPSEEK_V4_1_FLASH_BATCH.id, DOTS_STUDIO_DOTS_3_NOTE_PREVIEW_FREE.id, + ELORIAN_GLIMPSE.id, FIREWORKS_EMBER_1.id, GOOGLE_GEMINI_2_5_FLASH.id, GOOGLE_GEMINI_2_5_FLASH_LITE.id, - GOOGLE_GEMINI_2_5_FLASH_LITE_BATCH.id, - GOOGLE_GEMINI_2_5_FLASH_BATCH.id, GOOGLE_GEMINI_2_5_PRO.id, GOOGLE_GEMINI_2_5_PRO_PREVIEW.id, - GOOGLE_GEMINI_2_5_PRO_BATCH.id, GOOGLE_GEMINI_3_FLASH_PREVIEW.id, GOOGLE_GEMINI_3_FLASH_PREVIEW_BATCH.id, GOOGLE_GEMINI_3_PRO_IMAGE.id, @@ -23096,6 +23069,8 @@ export const OPENROUTER_COMBINED_TOOLS_AND_SCHEMA_MODELS: ReadonlySet = GOOGLE_GEMINI_3_7_FLASH_BATCH.id, GOOGLE_GEMINI_3_8_FLASH.id, GOOGLE_GEMINI_3_8_FLASH_BATCH.id, + GOOGLE_GEMINI_4_ARGON.id, + GOOGLE_GEMINI_4_ARGON_BATCH.id, GOOGLE_GEMINI_NANO_BANANA_2_1.id, GOOGLE_GEMMA_3_12B_IT.id, GOOGLE_GEMMA_3_27B_IT.id, @@ -23104,9 +23079,11 @@ export const OPENROUTER_COMBINED_TOOLS_AND_SCHEMA_MODELS: ReadonlySet = IBM_GRANITE_GRANITE_4_2_8B.id, INCEPTION_MERCURY_2.id, INCEPTION_MERCURY_2_5.id, - INCLUSIONAI_LING_3_0_FLASH_FIN.id, + INCEPTION_MERCURY_3.id, INCLUSIONAI_LING_3_0_FLASH_VL.id, + INCLUSIONAI_LING_3_1_FLASH.id, LIQUID_LFM_2_5_2_6B_FREE.id, + LIQUID_LFM_2_5_24B_A2B.id, META_LLAMA_LLAMA_3_1_70B_INSTRUCT.id, META_LLAMA_LLAMA_3_1_8B_INSTRUCT.id, META_LLAMA_LLAMA_3_3_70B_INSTRUCT.id, @@ -23118,6 +23095,8 @@ export const OPENROUTER_COMBINED_TOOLS_AND_SCHEMA_MODELS: ReadonlySet = META_MUSE_SPARK_1_2_CONTRIBUTOR.id, META_MUSE_SPARK_1_3.id, META_MUSE_SPARK_1_3_CONTRIBUTOR.id, + META_MUSE_SPARK_OPEN.id, + META_MUSE_WONDER.id, MINIMAX_MINIMAX_M2.id, MINIMAX_MINIMAX_M2_5.id, MINIMAX_MINIMAX_M3.id, @@ -23159,6 +23138,8 @@ export const OPENROUTER_COMBINED_TOOLS_AND_SCHEMA_MODELS: ReadonlySet = NVIDIA_NEMOTRON_3_SUPER_120B_A12B_FREE.id, NVIDIA_NEMOTRON_3_ULTRA_550B_A55B.id, NVIDIA_NEMOTRON_3_5_LIGHTNING.id, + NVIDIA_NEMOTRON_3_5_SUPER_VL.id, + NVIDIA_NEMOTRON_3_5_SUPER_VL_FREE.id, OPENAI_GPT_3_5_TURBO.id, OPENAI_GPT_3_5_TURBO_0613.id, OPENAI_GPT_3_5_TURBO_16K.id, @@ -23238,6 +23219,8 @@ export const OPENROUTER_COMBINED_TOOLS_AND_SCHEMA_MODELS: ReadonlySet = OPENAI_GPT_6_SOL_BATCH.id, OPENAI_GPT_6_1_SOL.id, OPENAI_GPT_6_1_SOL_PRO.id, + OPENAI_GPT_6_1_SOL_PRO_BATCH.id, + OPENAI_GPT_6_1_SOL_BATCH.id, OPENAI_GPT_AUDIO.id, OPENAI_GPT_AUDIO_MINI.id, OPENAI_GPT_CHAT_LATEST.id, @@ -23261,7 +23244,6 @@ export const OPENROUTER_COMBINED_TOOLS_AND_SCHEMA_MODELS: ReadonlySet = QWEN_QWEN_2_5_72B_INSTRUCT.id, QWEN_QWEN_2_5_7B_INSTRUCT.id, QWEN_QWEN_PLUS.id, - QWEN_QWEN_PLUS_2025_07_28.id, QWEN_QWEN3_14B.id, QWEN_QWEN3_235B_A22B_2507.id, QWEN_QWEN3_30B_A3B.id, @@ -23270,18 +23252,12 @@ export const OPENROUTER_COMBINED_TOOLS_AND_SCHEMA_MODELS: ReadonlySet = QWEN_QWEN3_CODER.id, QWEN_QWEN3_CODER_30B_A3B_INSTRUCT.id, QWEN_QWEN3_CODER_NEXT.id, - QWEN_QWEN3_CODER_PLUS.id, - QWEN_QWEN3_MAX.id, - QWEN_QWEN3_MAX_THINKING.id, QWEN_QWEN3_NEXT_80B_A3B_INSTRUCT.id, QWEN_QWEN3_NEXT_80B_A3B_THINKING.id, QWEN_QWEN3_VL_235B_A22B_INSTRUCT.id, - QWEN_QWEN3_VL_235B_A22B_THINKING.id, QWEN_QWEN3_VL_30B_A3B_INSTRUCT.id, QWEN_QWEN3_VL_30B_A3B_THINKING.id, - QWEN_QWEN3_VL_32B_INSTRUCT.id, QWEN_QWEN3_VL_8B_INSTRUCT.id, - QWEN_QWEN3_VL_8B_THINKING.id, QWEN_QWEN3_5_122B_A10B.id, QWEN_QWEN3_5_27B.id, QWEN_QWEN3_5_35B_A3B.id, @@ -23293,23 +23269,24 @@ export const OPENROUTER_COMBINED_TOOLS_AND_SCHEMA_MODELS: ReadonlySet = QWEN_QWEN3_6_27B.id, QWEN_QWEN3_6_35B_A3B.id, QWEN_QWEN3_6_FLASH.id, - QWEN_QWEN3_6_MAX_PREVIEW.id, QWEN_QWEN3_6_PLUS.id, QWEN_QWEN3_7_MAX.id, QWEN_QWEN3_7_PLUS.id, + QWEN_QWEN3_7_PLUS_BATCH.id, QWEN_QWEN3_8_2_4T_A95B.id, QWEN_QWEN3_8_27B.id, QWEN_QWEN3_8_FLASH.id, QWEN_QWEN3_8_MAX_0902.id, QWEN_QWEN3_8_MAX_PRIME.id, QWEN_QWEN3_8_OMNI_FLASH.id, + REFLECTION_BEAM_1_0_501B_A23B.id, REKAAI_REKA_EDGE.id, SAKANA_FUGU_MAX.id, SAKANA_FUGU_ULTRA.id, SAKANA_FUGU_ULTRA_V2.id, SAKANA_SAKANA_NAMAZU.id, - SAO10K_L3_1_EURYALE_70B.id, STEPFUN_STEP_3_7_FLASH.id, + STEPFUN_STEP_5_PREVIEW.id, TENCENT_HY3.id, TENCENT_HY4_PREVIEW.id, UPSTAGE_SOLAR_MINI4.id, @@ -23327,6 +23304,7 @@ export const OPENROUTER_COMBINED_TOOLS_AND_SCHEMA_MODELS: ReadonlySet = XIAOMI_MIMO_V2_6_FLASH.id, XIAOMI_MIMO_V2_6_PRO.id, XIAOMI_MIMO_V2_6_PRO_ULTRASPEED.id, + XINGCHEN_AGI_XING4_0_29B_A4B_FREE.id, Z_AI_GLM_4_6.id, Z_AI_GLM_4_7.id, Z_AI_GLM_4_7_FLASH.id, @@ -23352,26 +23330,21 @@ export const OPENROUTER_JSON_OBJECT_ONLY_MODELS: ReadonlySet = AION_LABS_AION_3_5.id, AION_LABS_AION_3_5_MINI.id, COGNITIVECOMPUTATIONS_DOLPHIN_MISTRAL_24B_VENICE_EDITION.id, - DEEPSEEK_DEEPSEEK_R1.id, GOOGLE_GEMINI_3_1_FLASH_LITE_IMAGE.id, GOOGLE_GEMMA_4_26B_A4B_IT_FREE.id, GOOGLE_GEMMA_4_31B_IT_FREE.id, IBM_GRANITE_GRANITE_4_0_H_MICRO.id, INCLUSIONAI_LING_3_0_FLASH.id, MANCER_WEAVER.id, - MICROSOFT_WIZARDLM_2_8X22B.id, MINIMAX_MINIMAX_M2_1.id, MINIMAX_MINIMAX_M2_7.id, - NOUSRESEARCH_HERMES_4_405B.id, + MINIMAX_MINIMAX_M3_1_FLASH_FREE.id, QWEN_QWEN_2_5_CODER_32B_INSTRUCT.id, - QWEN_QWEN3_235B_A22B.id, - QWEN_QWEN3_235B_A22B_THINKING_2507.id, - QWEN_QWEN3_30B_A3B_THINKING_2507.id, - QWEN_QWEN3_8B.id, QWEN_QWEN3_CODER_FLASH.id, QWEN_QWEN3_7_FLASH.id, + RECURSIVE_FLINT_V1_0_FREE.id, RELACE_RELACE_SEARCH.id, - UNBIASED_PARETO.id, + UNBIASED_PARETO_26_9.id, Z_AI_GLM_4_5.id, Z_AI_GLM_4_5V.id, Z_AI_GLM_4_6V.id, diff --git a/packages/ai-vercel-gateway/src/model-meta.ts b/packages/ai-vercel-gateway/src/model-meta.ts index 603f12e0b6..9882909b1c 100644 --- a/packages/ai-vercel-gateway/src/model-meta.ts +++ b/packages/ai-vercel-gateway/src/model-meta.ts @@ -20,20 +20,13 @@ export const VERCEL_GATEWAY_CHAT_MODELS = [ 'alibaba/qwen-3-235b', 'alibaba/qwen-3-30b', 'alibaba/qwen-3-32b', - 'alibaba/qwen-3.6-max-preview', - 'alibaba/qwen3-235b-a22b-thinking', 'alibaba/qwen3-coder', 'alibaba/qwen3-coder-30b-a3b', 'alibaba/qwen3-coder-next', - 'alibaba/qwen3-coder-plus', - 'alibaba/qwen3-max', - 'alibaba/qwen3-max-preview', 'alibaba/qwen3-max-thinking', 'alibaba/qwen3-next-80b-a3b-instruct', 'alibaba/qwen3-next-80b-a3b-thinking', - 'alibaba/qwen3-vl-235b-a22b-instruct', 'alibaba/qwen3-vl-instruct', - 'alibaba/qwen3-vl-thinking', 'alibaba/qwen3.5-flash', 'alibaba/qwen3.5-plus', 'alibaba/qwen3.6-27b', @@ -52,35 +45,49 @@ export const VERCEL_GATEWAY_CHAT_MODELS = [ 'amazon/nova-lite', 'amazon/nova-micro', 'amazon/nova-pro', - 'anthropic/claude-3-haiku', 'anthropic/claude-fable-5', + 'anthropic/claude-fable-5-batch', 'anthropic/claude-fable-5.1', + 'anthropic/claude-fable-5.1-batch', 'anthropic/claude-haiku-4.5', - 'anthropic/claude-opus-4', + 'anthropic/claude-haiku-4.5-batch', + 'anthropic/claude-haiku-5.5', + 'anthropic/claude-haiku-5.5-batch', 'anthropic/claude-opus-4.5', + 'anthropic/claude-opus-4.5-batch', 'anthropic/claude-opus-4.6', + 'anthropic/claude-opus-4.6-batch', 'anthropic/claude-opus-4.7', + 'anthropic/claude-opus-4.7-batch', 'anthropic/claude-opus-4.8', + 'anthropic/claude-opus-4.8-batch', 'anthropic/claude-opus-4.8-fast', 'anthropic/claude-opus-5', + 'anthropic/claude-opus-5-batch', 'anthropic/claude-opus-5-fast', 'anthropic/claude-opus-5.5', + 'anthropic/claude-opus-5.5-batch', 'anthropic/claude-opus-5.5-fast', - 'anthropic/claude-sonnet-4', 'anthropic/claude-sonnet-4.5', + 'anthropic/claude-sonnet-4.5-batch', 'anthropic/claude-sonnet-4.6', + 'anthropic/claude-sonnet-4.6-batch', 'anthropic/claude-sonnet-5', + 'anthropic/claude-sonnet-5-batch', 'anthropic/claude-sonnet-5.5', + 'anthropic/claude-sonnet-5.5-batch', 'arcee-ai/trinity-large-thinking', + 'baseten/elephant-1', + 'baseten/mammoth-1', 'bytedance/seed-1.6', 'bytedance/seed-1.8', 'bytedance/seed-2.1-turbo', + 'callstack/apex', 'cohere/command-a', 'convaiinnovations/laya', 'convaiinnovations/laya-free', 'deepseek/deepseek-r1', 'deepseek/deepseek-v3.1', - 'deepseek/deepseek-v3.1-terminus', 'deepseek/deepseek-v3.2', 'deepseek/deepseek-v3.2-thinking', 'deepseek/deepseek-v4-flash', @@ -89,51 +96,68 @@ export const VERCEL_GATEWAY_CHAT_MODELS = [ 'deepseek/deepseek-v4-pro', 'deepseek/deepseek-v4-pro-0813', 'deepseek/deepseek-v4.1-flash', + 'deepseek/deepseek-v4.1-flash-1017', + 'deepseek/deepseek-v4.1-flash-1017-fast', 'deepseek/deepseek-v4.1-flash-fast', + 'elorian/glimpse', 'fireworks/ember-1', + 'fish-audio/drama-3', 'fish-audio/s1', 'fish-audio/s2-pro', 'fish-audio/s2.1-pro', 'fish-audio/transcribe-1', 'google/gemini-2.5-flash', + 'google/gemini-2.5-flash-batch', 'google/gemini-2.5-flash-image', 'google/gemini-2.5-flash-lite', + 'google/gemini-2.5-flash-lite-batch', 'google/gemini-2.5-pro', + 'google/gemini-2.5-pro-batch', 'google/gemini-3-flash', + 'google/gemini-3-flash-batch', 'google/gemini-3-pro-image', 'google/gemini-3.1-flash-image', 'google/gemini-3.1-flash-image-preview', 'google/gemini-3.1-flash-lite', + 'google/gemini-3.1-flash-lite-batch', 'google/gemini-3.1-flash-lite-image', 'google/gemini-3.1-pro-preview', + 'google/gemini-3.1-pro-preview-batch', 'google/gemini-3.5-flash', + 'google/gemini-3.5-flash-batch', 'google/gemini-3.5-flash-lite', + 'google/gemini-3.5-flash-lite-batch', 'google/gemini-3.5-transcribe', 'google/gemini-3.5-transcribe-live', 'google/gemini-3.6-flash', + 'google/gemini-3.6-flash-batch', 'google/gemini-3.7-flash', + 'google/gemini-3.7-flash-batch', 'google/gemini-3.8-flash', 'google/gemini-3.8-flash-lite-tts', 'google/gemini-3.8-flash-tts', 'google/gemini-3.8-live', 'google/gemini-3.8-live-extended-thinking', + 'google/gemini-4-argon', 'google/gemini-nano-banana-2.1', 'google/gemini-omni-flash-preview', 'google/gemma-4-26b-a4b-it', 'google/gemma-4-31b-it', 'inception/mercury-2', 'inception/mercury-2.5', + 'inception/mercury-3', 'inception/mercury-coder-small', 'inclusionai/ling-3.0-flash', 'inclusionai/ling-3.0-flash-fin', 'inclusionai/ling-3.0-flash-sante', 'inclusionai/ling-3.0-flash-vl', 'inclusionai/ling-3.1-flash', - 'inclusionai/ling-3.1-flash-free', 'inference-net/schematron-v2-small', 'inference-net/schematron-v2-turbo', 'interfaze/interfaze-beta', 'liquid/d1', + 'liquid/d1-ultra', + 'liquid/lfm2.5-24b-a2b', 'meituan/longcat-2.5-preview', 'meta/llama-3.1-70b', 'meta/llama-3.1-8b', @@ -146,12 +170,15 @@ export const VERCEL_GATEWAY_CHAT_MODELS = [ 'meta/muse-spark-1.2-contributor', 'meta/muse-spark-1.3', 'meta/muse-spark-1.3-contributor', + 'meta/muse-spark-open', + 'meta/muse-wonder-1.0', 'microsoft/mai-transcribe-2', 'microsoft/mai-transcribe-2-streaming', 'microsoft/mai-voice-2', 'microsoft/mai-voice-2-flash', 'microsoft/mai-voice-2.1', 'microsoft/mai-voice-2.1-flash', + 'microsoft/microsoft-decision-1', 'minimax/minimax-m2', 'minimax/minimax-m2.1', 'minimax/minimax-m2.1-lightning', @@ -160,6 +187,7 @@ export const VERCEL_GATEWAY_CHAT_MODELS = [ 'minimax/minimax-m2.7', 'minimax/minimax-m2.7-highspeed', 'minimax/minimax-m3', + 'minimax/minimax-m3.1-flash', 'mistral/codestral', 'mistral/ministral-14b', 'mistral/ministral-3b', @@ -169,9 +197,11 @@ export const VERCEL_GATEWAY_CHAT_MODELS = [ 'mistral/mistral-medium-3.5', 'mistral/mistral-nemo', 'mistral/mistral-small', + 'mistral/voxtral-mini-transcribe-3', + 'mistral/voxtral-mini-tts-3', + 'mistral/voxtral-small-transcribe-3', 'mixedbread/toast-1', 'moonshotai/kimi-k2', - 'moonshotai/kimi-k2-thinking', 'moonshotai/kimi-k2.5', 'moonshotai/kimi-k2.6', 'moonshotai/kimi-k2.7-code', @@ -184,63 +214,87 @@ export const VERCEL_GATEWAY_CHAT_MODELS = [ 'nvidia/nemotron-3-super-120b-a12b', 'nvidia/nemotron-3-ultra-550b-a55b', 'nvidia/nemotron-3.5-lightning', + 'nvidia/nemotron-3.5-lightning-free', + 'nvidia/nemotron-3.5-super-vl', 'nvidia/nemotron-nano-12b-v2-vl', 'nvidia/nemotron-nano-9b-v2', 'openai/gpt-3.5-turbo', 'openai/gpt-4-turbo', 'openai/gpt-4.1', + 'openai/gpt-4.1-batch', 'openai/gpt-4.1-fast', 'openai/gpt-4.1-mini', + 'openai/gpt-4.1-mini-batch', 'openai/gpt-4.1-mini-fast', 'openai/gpt-4.1-nano', + 'openai/gpt-4.1-nano-batch', 'openai/gpt-4.1-nano-fast', 'openai/gpt-4o', + 'openai/gpt-4o-batch', 'openai/gpt-4o-fast', 'openai/gpt-4o-mini', + 'openai/gpt-4o-mini-batch', 'openai/gpt-4o-mini-fast', 'openai/gpt-4o-mini-transcribe', 'openai/gpt-4o-transcribe', 'openai/gpt-5', + 'openai/gpt-5-batch', 'openai/gpt-5-codex', 'openai/gpt-5-fast', 'openai/gpt-5-mini', + 'openai/gpt-5-mini-batch', 'openai/gpt-5-mini-fast', 'openai/gpt-5-nano', + 'openai/gpt-5-nano-batch', 'openai/gpt-5-pro', + 'openai/gpt-5-pro-batch', 'openai/gpt-5.1-codex', 'openai/gpt-5.1-codex-max', 'openai/gpt-5.1-codex-mini', 'openai/gpt-5.1-thinking', 'openai/gpt-5.1-thinking-fast', 'openai/gpt-5.2', + 'openai/gpt-5.2-batch', 'openai/gpt-5.2-codex', 'openai/gpt-5.2-fast', 'openai/gpt-5.2-pro', 'openai/gpt-5.3-codex', 'openai/gpt-5.3-codex-fast', 'openai/gpt-5.4', + 'openai/gpt-5.4-batch', 'openai/gpt-5.4-fast', 'openai/gpt-5.4-mini', + 'openai/gpt-5.4-mini-batch', 'openai/gpt-5.4-mini-fast', 'openai/gpt-5.4-nano', + 'openai/gpt-5.4-nano-batch', 'openai/gpt-5.4-pro', 'openai/gpt-5.5', + 'openai/gpt-5.5-batch', 'openai/gpt-5.5-fast', 'openai/gpt-5.5-pro', + 'openai/gpt-5.5-pro-batch', 'openai/gpt-5.6-luna', + 'openai/gpt-5.6-luna-batch', 'openai/gpt-5.6-luna-fast', 'openai/gpt-5.6-sol', + 'openai/gpt-5.6-sol-batch', 'openai/gpt-5.6-sol-fast', 'openai/gpt-5.6-terra', + 'openai/gpt-5.6-terra-batch', 'openai/gpt-5.6-terra-fast', 'openai/gpt-6-astra', + 'openai/gpt-6-astra-batch', 'openai/gpt-6-astra-fast', 'openai/gpt-6-luna', + 'openai/gpt-6-luna-batch', 'openai/gpt-6-luna-decisions', 'openai/gpt-6-luna-fast', 'openai/gpt-6-sol', + 'openai/gpt-6-sol-batch', 'openai/gpt-6-sol-fast', 'openai/gpt-6.1-sol', + 'openai/gpt-6.1-sol-batch', 'openai/gpt-6.1-sol-fast', 'openai/gpt-live-1', 'openai/gpt-oss-120b', @@ -262,33 +316,44 @@ export const VERCEL_GATEWAY_CHAT_MODELS = [ 'openai/tts-1', 'openai/tts-1-hd', 'openai/whisper-1', + 'perplexity/pplx-decider-flash-v1.2', + 'perplexity/pplx-decider-v1.2', 'perplexity/sonar', 'poolside/laguna-s-2.1', 'poolside/laguna-s-2.1-free', 'quiverai/arrow-2', 'quiverai/arrow-2-telos', + 'reflection/beam', + 'reflection/beam-free', 'sakana/fugu-max', 'sakana/fugu-ultra', 'sakana/fugu-ultra-v2', 'sakana/namazu', + 'scaledown/scaledown-classify-1', + 'scaledown/scaledown-extract-1', + 'scaledown/scaledown-summarize-1', 'spacexai/grok-4.1-fast-non-reasoning', 'spacexai/grok-4.1-fast-reasoning', 'spacexai/grok-4.20-multi-agent', + 'spacexai/grok-4.20-multi-agent-batch', 'spacexai/grok-4.20-multi-agent-beta', 'spacexai/grok-4.20-non-reasoning', + 'spacexai/grok-4.20-non-reasoning-batch', 'spacexai/grok-4.20-non-reasoning-beta', 'spacexai/grok-4.20-reasoning', + 'spacexai/grok-4.20-reasoning-batch', 'spacexai/grok-4.20-reasoning-beta', 'spacexai/grok-4.3', + 'spacexai/grok-4.3-batch', 'spacexai/grok-4.5', 'spacexai/grok-4.6', 'spacexai/grok-4.7', 'spacexai/grok-build-0.1', 'spacexai/grok-stt', 'spacexai/grok-tts', - 'spacexai/grok-voice-think-fast-1.0', + 'spacexai/grok-voice-3.0', 'spacexai/grok-voice-think-fast-2.0', - 'stepfun/step-3.5-flash', + 'stealth/glyph-cluster', 'stepfun/step-3.7-flash', 'stepfun/step-5-preview', 'tencent/hy-mt2-lite', @@ -299,6 +364,8 @@ export const VERCEL_GATEWAY_CHAT_MODELS = [ 'thinkingmachines/inkling', 'thinkingmachines/inkling-small', 'typesafe-ai/jev', + 'typesafe-ai/jev-1.13.0', + 'typesafe-ai/jev-1.14.0', 'xiaomi/mimo-v2.5', 'xiaomi/mimo-v2.5-pro', 'xiaomi/mimo-v2.6-flash', @@ -330,14 +397,18 @@ export const VERCEL_GATEWAY_PROVIDERS = [ 'amazon', 'anthropic', 'arcee-ai', + 'baseten', 'bfl', 'bytedance', + 'callstack', 'cohere', 'convaiinnovations', 'deepseek', + 'elorian', 'fireworks', 'fish-audio', 'google', + 'heygen', 'inception', 'inclusionai', 'inference-net', @@ -359,8 +430,11 @@ export const VERCEL_GATEWAY_PROVIDERS = [ 'prodia', 'quiverai', 'recraft', + 'reflection', 'sakana', + 'scaledown', 'spacexai', + 'stealth', 'stepfun', 'tencent', 'thinkingmachines', @@ -381,6 +455,7 @@ export const VERCEL_GATEWAY_MODEL_TAGS = [ 'free', 'image-generation', 'implicit-caching', + 'open-weights', 'reasoning', 'structured-output', 'tool-use', @@ -435,6 +510,7 @@ export const VERCEL_GATEWAY_IMAGE_MODELS = [ 'bfl/flux-2-max', 'bfl/flux-2-pro', 'bfl/flux-3-image', + 'bfl/flux-3-image-klein', 'bfl/flux-kontext-max', 'bfl/flux-kontext-pro', 'bfl/flux-pro-1.0-fill', @@ -445,6 +521,8 @@ export const VERCEL_GATEWAY_IMAGE_MODELS = [ 'bytedance/seedream-5.0-lite', 'bytedance/seedream-5.0-pro', 'meta/muse-image-1.0', + 'microsoft/mai-image-2.6', + 'microsoft/mai-image-2.6-flash', 'openai/gpt-image-1', 'openai/gpt-image-1-mini', 'openai/gpt-image-1.5', @@ -452,7 +530,6 @@ export const VERCEL_GATEWAY_IMAGE_MODELS = [ 'openai/gpt-image-2.5-flare', 'openai/gpt-image-2.5-sunburst', 'prodia/flux-fast-schnell', - 'quiverai/arrow-1.1', 'recraft/recraft-v2', 'recraft/recraft-v3', 'recraft/recraft-v4', @@ -511,21 +588,6 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'alibaba/qwen-3.6-max-preview': VercelGatewayCommonOptions & - Pick< - VercelGatewayBaseOptions, - 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' - > - 'alibaba/qwen3-235b-a22b-thinking': VercelGatewayCommonOptions & - Pick< - VercelGatewayBaseOptions, - | 'max_tokens' - | 'max_output_tokens' - | 'temperature' - | 'stop' - | 'response_format' - | 'structured_outputs' - > 'alibaba/qwen3-coder': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -556,31 +618,6 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'alibaba/qwen3-coder-plus': VercelGatewayCommonOptions & - Pick< - VercelGatewayBaseOptions, - 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' - > - 'alibaba/qwen3-max': VercelGatewayCommonOptions & - Pick< - VercelGatewayBaseOptions, - | 'max_tokens' - | 'max_output_tokens' - | 'temperature' - | 'stop' - | 'response_format' - | 'structured_outputs' - > - 'alibaba/qwen3-max-preview': VercelGatewayCommonOptions & - Pick< - VercelGatewayBaseOptions, - | 'max_tokens' - | 'max_output_tokens' - | 'temperature' - | 'stop' - | 'response_format' - | 'structured_outputs' - > 'alibaba/qwen3-max-thinking': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -611,22 +648,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'alibaba/qwen3-vl-235b-a22b-instruct': VercelGatewayCommonOptions & - Pick< - VercelGatewayBaseOptions, - 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' - > 'alibaba/qwen3-vl-instruct': VercelGatewayCommonOptions & - Pick< - VercelGatewayBaseOptions, - | 'max_tokens' - | 'max_output_tokens' - | 'temperature' - | 'stop' - | 'response_format' - | 'structured_outputs' - > - 'alibaba/qwen3-vl-thinking': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' @@ -786,17 +808,16 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'anthropic/claude-3-haiku': VercelGatewayCommonOptions & + 'anthropic/claude-fable-5': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' | 'max_output_tokens' - | 'temperature' | 'stop' | 'response_format' | 'structured_outputs' > - 'anthropic/claude-fable-5': VercelGatewayCommonOptions & + 'anthropic/claude-fable-5-batch': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -815,6 +836,16 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > + 'anthropic/claude-fable-5.1-batch': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > 'anthropic/claude-haiku-4.5': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -825,10 +856,33 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'anthropic/claude-opus-4': VercelGatewayCommonOptions & + 'anthropic/claude-haiku-4.5-batch': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, - 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'anthropic/claude-haiku-5.5': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'anthropic/claude-haiku-5.5-batch': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'stop' + | 'response_format' + | 'structured_outputs' > 'anthropic/claude-opus-4.5': VercelGatewayCommonOptions & Pick< @@ -840,6 +894,16 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > + 'anthropic/claude-opus-4.5-batch': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > 'anthropic/claude-opus-4.6': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -850,6 +914,16 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > + 'anthropic/claude-opus-4.6-batch': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > 'anthropic/claude-opus-4.7': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -860,6 +934,16 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > + 'anthropic/claude-opus-4.7-batch': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > 'anthropic/claude-opus-4.8': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -870,6 +954,16 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > + 'anthropic/claude-opus-4.8-batch': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > 'anthropic/claude-opus-4.8-fast': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -889,6 +983,15 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > + 'anthropic/claude-opus-5-batch': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'stop' + | 'response_format' + | 'structured_outputs' + > 'anthropic/claude-opus-5-fast': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -907,6 +1010,15 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > + 'anthropic/claude-opus-5.5-batch': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'stop' + | 'response_format' + | 'structured_outputs' + > 'anthropic/claude-opus-5.5-fast': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -916,7 +1028,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'anthropic/claude-sonnet-4': VercelGatewayCommonOptions & + 'anthropic/claude-sonnet-4.5': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -926,7 +1038,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'anthropic/claude-sonnet-4.5': VercelGatewayCommonOptions & + 'anthropic/claude-sonnet-4.5-batch': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -946,6 +1058,16 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > + 'anthropic/claude-sonnet-4.6-batch': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > 'anthropic/claude-sonnet-5': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -955,6 +1077,15 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > + 'anthropic/claude-sonnet-5-batch': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'stop' + | 'response_format' + | 'structured_outputs' + > 'anthropic/claude-sonnet-5.5': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -964,6 +1095,15 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > + 'anthropic/claude-sonnet-5.5-batch': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'stop' + | 'response_format' + | 'structured_outputs' + > 'arcee-ai/trinity-large-thinking': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -974,6 +1114,8 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > + 'baseten/elephant-1': VercelGatewayCommonOptions + 'baseten/mammoth-1': VercelGatewayCommonOptions 'bytedance/seed-1.6': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -989,6 +1131,11 @@ export type VercelGatewayChatModelProviderOptionsByName = { VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' > + 'callstack/apex': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' + > 'cohere/command-a': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -1016,16 +1163,6 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'deepseek/deepseek-v3.1-terminus': VercelGatewayCommonOptions & - Pick< - VercelGatewayBaseOptions, - | 'max_tokens' - | 'max_output_tokens' - | 'temperature' - | 'stop' - | 'response_format' - | 'structured_outputs' - > 'deepseek/deepseek-v3.2': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -1096,7 +1233,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'deepseek/deepseek-v4.1-flash-fast': VercelGatewayCommonOptions & + 'deepseek/deepseek-v4.1-flash-1017': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1106,16 +1243,17 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'fireworks/ember-1': VercelGatewayCommonOptions & + 'deepseek/deepseek-v4.1-flash-1017-fast': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, - 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' > - 'fish-audio/s1': VercelGatewayCommonOptions - 'fish-audio/s2-pro': VercelGatewayCommonOptions - 'fish-audio/s2.1-pro': VercelGatewayCommonOptions - 'fish-audio/transcribe-1': VercelGatewayCommonOptions - 'google/gemini-2.5-flash': VercelGatewayCommonOptions & + 'deepseek/deepseek-v4.1-flash-fast': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1125,12 +1263,22 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'google/gemini-2.5-flash-image': VercelGatewayCommonOptions & + 'elorian/glimpse': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' > - 'google/gemini-2.5-flash-lite': VercelGatewayCommonOptions & + 'fireworks/ember-1': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' + > + 'fish-audio/drama-3': VercelGatewayCommonOptions + 'fish-audio/s1': VercelGatewayCommonOptions + 'fish-audio/s2-pro': VercelGatewayCommonOptions + 'fish-audio/s2.1-pro': VercelGatewayCommonOptions + 'fish-audio/transcribe-1': VercelGatewayCommonOptions + 'google/gemini-2.5-flash': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1140,7 +1288,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'google/gemini-2.5-pro': VercelGatewayCommonOptions & + 'google/gemini-2.5-flash-batch': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1150,7 +1298,12 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'google/gemini-3-flash': VercelGatewayCommonOptions & + 'google/gemini-2.5-flash-image': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' + > + 'google/gemini-2.5-flash-lite': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1160,7 +1313,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'google/gemini-3-pro-image': VercelGatewayCommonOptions & + 'google/gemini-2.5-flash-lite-batch': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1170,7 +1323,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'google/gemini-3.1-flash-image': VercelGatewayCommonOptions & + 'google/gemini-2.5-pro': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1180,7 +1333,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'google/gemini-3.1-flash-image-preview': VercelGatewayCommonOptions & + 'google/gemini-2.5-pro-batch': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1190,7 +1343,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'google/gemini-3.1-flash-lite': VercelGatewayCommonOptions & + 'google/gemini-3-flash': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1200,12 +1353,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'google/gemini-3.1-flash-lite-image': VercelGatewayCommonOptions & - Pick< - VercelGatewayBaseOptions, - 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' - > - 'google/gemini-3.1-pro-preview': VercelGatewayCommonOptions & + 'google/gemini-3-flash-batch': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1215,7 +1363,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'google/gemini-3.5-flash': VercelGatewayCommonOptions & + 'google/gemini-3-pro-image': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1225,7 +1373,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'google/gemini-3.5-flash-lite': VercelGatewayCommonOptions & + 'google/gemini-3.1-flash-image': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1235,9 +1383,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'google/gemini-3.5-transcribe': VercelGatewayCommonOptions - 'google/gemini-3.5-transcribe-live': VercelGatewayCommonOptions - 'google/gemini-3.6-flash': VercelGatewayCommonOptions & + 'google/gemini-3.1-flash-image-preview': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1247,7 +1393,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'google/gemini-3.7-flash': VercelGatewayCommonOptions & + 'google/gemini-3.1-flash-lite': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1257,7 +1403,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'google/gemini-3.8-flash': VercelGatewayCommonOptions & + 'google/gemini-3.1-flash-lite-batch': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1267,19 +1413,12 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'google/gemini-3.8-flash-lite-tts': VercelGatewayCommonOptions - 'google/gemini-3.8-flash-tts': VercelGatewayCommonOptions - 'google/gemini-3.8-live': VercelGatewayCommonOptions & - Pick< - VercelGatewayBaseOptions, - 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' - > - 'google/gemini-3.8-live-extended-thinking': VercelGatewayCommonOptions & + 'google/gemini-3.1-flash-lite-image': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' > - 'google/gemini-nano-banana-2.1': VercelGatewayCommonOptions & + 'google/gemini-3.1-pro-preview': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1289,7 +1428,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'google/gemini-omni-flash-preview': VercelGatewayCommonOptions & + 'google/gemini-3.1-pro-preview-batch': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1299,7 +1438,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'google/gemma-4-26b-a4b-it': VercelGatewayCommonOptions & + 'google/gemini-3.5-flash': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1309,7 +1448,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'google/gemma-4-31b-it': VercelGatewayCommonOptions & + 'google/gemini-3.5-flash-batch': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1319,7 +1458,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'inception/mercury-2': VercelGatewayCommonOptions & + 'google/gemini-3.5-flash-lite': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1329,7 +1468,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'inception/mercury-2.5': VercelGatewayCommonOptions & + 'google/gemini-3.5-flash-lite-batch': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1339,7 +1478,9 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'inception/mercury-coder-small': VercelGatewayCommonOptions & + 'google/gemini-3.5-transcribe': VercelGatewayCommonOptions + 'google/gemini-3.5-transcribe-live': VercelGatewayCommonOptions + 'google/gemini-3.6-flash': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1349,12 +1490,59 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'inclusionai/ling-3.0-flash': VercelGatewayCommonOptions & + 'google/gemini-3.6-flash-batch': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'google/gemini-3.7-flash': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'google/gemini-3.7-flash-batch': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'google/gemini-3.8-flash': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'google/gemini-3.8-flash-lite-tts': VercelGatewayCommonOptions + 'google/gemini-3.8-flash-tts': VercelGatewayCommonOptions + 'google/gemini-3.8-live': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' > - 'inclusionai/ling-3.0-flash-fin': VercelGatewayCommonOptions & + 'google/gemini-3.8-live-extended-thinking': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' + > + 'google/gemini-4-argon': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1364,22 +1552,112 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'inclusionai/ling-3.0-flash-sante': VercelGatewayCommonOptions & + 'google/gemini-nano-banana-2.1': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'google/gemini-omni-flash-preview': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'google/gemma-4-26b-a4b-it': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'google/gemma-4-31b-it': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'inception/mercury-2': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'inception/mercury-2.5': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'inception/mercury-3': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'inception/mercury-coder-small': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'inclusionai/ling-3.0-flash': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' > - 'inclusionai/ling-3.0-flash-vl': VercelGatewayCommonOptions & + 'inclusionai/ling-3.0-flash-fin': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'inclusionai/ling-3.0-flash-sante': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' > - 'inclusionai/ling-3.1-flash': VercelGatewayCommonOptions & + 'inclusionai/ling-3.0-flash-vl': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' > - 'inclusionai/ling-3.1-flash-free': VercelGatewayCommonOptions & + 'inclusionai/ling-3.1-flash': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' @@ -1415,7 +1693,8 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'structured_outputs' > 'liquid/d1': VercelGatewayCommonOptions - 'meituan/longcat-2.5-preview': VercelGatewayCommonOptions & + 'liquid/d1-ultra': VercelGatewayCommonOptions + 'liquid/lfm2.5-24b-a2b': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1425,7 +1704,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'meta/llama-3.1-70b': VercelGatewayCommonOptions & + 'meituan/longcat-2.5-preview': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1435,6 +1714,11 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > + 'meta/llama-3.1-70b': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' + > 'meta/llama-3.1-8b': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -1453,12 +1737,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { 'meta/llama-4-maverick': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, - | 'max_tokens' - | 'max_output_tokens' - | 'temperature' - | 'stop' - | 'response_format' - | 'structured_outputs' + 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' > 'meta/llama-4-scout': VercelGatewayCommonOptions & Pick< @@ -1530,12 +1809,33 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > + 'meta/muse-spark-open': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'meta/muse-wonder-1.0': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > 'microsoft/mai-transcribe-2': VercelGatewayCommonOptions 'microsoft/mai-transcribe-2-streaming': VercelGatewayCommonOptions 'microsoft/mai-voice-2': VercelGatewayCommonOptions 'microsoft/mai-voice-2-flash': VercelGatewayCommonOptions 'microsoft/mai-voice-2.1': VercelGatewayCommonOptions 'microsoft/mai-voice-2.1-flash': VercelGatewayCommonOptions + 'microsoft/microsoft-decision-1': VercelGatewayCommonOptions 'minimax/minimax-m2': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -1616,6 +1916,16 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > + 'minimax/minimax-m3.1-flash': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > 'mistral/codestral': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -1701,6 +2011,9 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > + 'mistral/voxtral-mini-transcribe-3': VercelGatewayCommonOptions + 'mistral/voxtral-mini-tts-3': VercelGatewayCommonOptions + 'mistral/voxtral-small-transcribe-3': VercelGatewayCommonOptions 'mixedbread/toast-1': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -1716,7 +2029,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' > - 'moonshotai/kimi-k2-thinking': VercelGatewayCommonOptions & + 'moonshotai/kimi-k2.5': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1726,7 +2039,238 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'moonshotai/kimi-k2.5': VercelGatewayCommonOptions & + 'moonshotai/kimi-k2.6': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'moonshotai/kimi-k2.7-code': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'moonshotai/kimi-k2.7-code-highspeed': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'moonshotai/kimi-k3': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'moonshotai/kimi-k3-fast': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'morph/morph-v3-fast': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'morph/morph-v3-large': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'nvidia/nemotron-3-nano-30b-a3b': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' + > + 'nvidia/nemotron-3-super-120b-a12b': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'nvidia/nemotron-3-ultra-550b-a55b': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'nvidia/nemotron-3.5-lightning': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'nvidia/nemotron-3.5-lightning-free': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'nvidia/nemotron-3.5-super-vl': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'nvidia/nemotron-nano-12b-v2-vl': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' + > + 'nvidia/nemotron-nano-9b-v2': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' + > + 'openai/gpt-3.5-turbo': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' + > + 'openai/gpt-4-turbo': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' + > + 'openai/gpt-4.1': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'openai/gpt-4.1-batch': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'openai/gpt-4.1-fast': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'openai/gpt-4.1-mini': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'openai/gpt-4.1-mini-batch': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'openai/gpt-4.1-mini-fast': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'openai/gpt-4.1-nano': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'openai/gpt-4.1-nano-batch': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'openai/gpt-4.1-nano-fast': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'openai/gpt-4o': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1736,7 +2280,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'moonshotai/kimi-k2.6': VercelGatewayCommonOptions & + 'openai/gpt-4o-batch': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1746,7 +2290,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'moonshotai/kimi-k2.7-code': VercelGatewayCommonOptions & + 'openai/gpt-4o-fast': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1756,7 +2300,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'moonshotai/kimi-k2.7-code-highspeed': VercelGatewayCommonOptions & + 'openai/gpt-4o-mini': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1766,25 +2310,29 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'moonshotai/kimi-k3': VercelGatewayCommonOptions & + 'openai/gpt-4o-mini-batch': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' | 'max_output_tokens' + | 'temperature' | 'stop' | 'response_format' | 'structured_outputs' > - 'moonshotai/kimi-k3-fast': VercelGatewayCommonOptions & + 'openai/gpt-4o-mini-fast': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' | 'max_output_tokens' + | 'temperature' | 'stop' | 'response_format' | 'structured_outputs' > - 'morph/morph-v3-fast': VercelGatewayCommonOptions & + 'openai/gpt-4o-mini-transcribe': VercelGatewayCommonOptions + 'openai/gpt-4o-transcribe': VercelGatewayCommonOptions + 'openai/gpt-5': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1793,7 +2341,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'morph/morph-v3-large': VercelGatewayCommonOptions & + 'openai/gpt-5-batch': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1802,97 +2350,80 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'nvidia/nemotron-3-nano-30b-a3b': VercelGatewayCommonOptions & - Pick< - VercelGatewayBaseOptions, - 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' - > - 'nvidia/nemotron-3-super-120b-a12b': VercelGatewayCommonOptions & + 'openai/gpt-5-codex': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' | 'max_output_tokens' - | 'temperature' | 'stop' | 'response_format' | 'structured_outputs' > - 'nvidia/nemotron-3-ultra-550b-a55b': VercelGatewayCommonOptions & + 'openai/gpt-5-fast': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' | 'max_output_tokens' - | 'temperature' | 'stop' | 'response_format' | 'structured_outputs' > - 'nvidia/nemotron-3.5-lightning': VercelGatewayCommonOptions & + 'openai/gpt-5-mini': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' | 'max_output_tokens' - | 'temperature' | 'stop' | 'response_format' | 'structured_outputs' > - 'nvidia/nemotron-nano-12b-v2-vl': VercelGatewayCommonOptions & + 'openai/gpt-5-mini-batch': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' | 'max_output_tokens' - | 'temperature' | 'stop' | 'response_format' | 'structured_outputs' > - 'nvidia/nemotron-nano-9b-v2': VercelGatewayCommonOptions & - Pick< - VercelGatewayBaseOptions, - 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' - > - 'openai/gpt-3.5-turbo': VercelGatewayCommonOptions & - Pick< - VercelGatewayBaseOptions, - 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' - > - 'openai/gpt-4-turbo': VercelGatewayCommonOptions & - Pick< - VercelGatewayBaseOptions, - 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' - > - 'openai/gpt-4.1': VercelGatewayCommonOptions & + 'openai/gpt-5-mini-fast': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' | 'max_output_tokens' - | 'temperature' | 'stop' | 'response_format' | 'structured_outputs' > - 'openai/gpt-4.1-fast': VercelGatewayCommonOptions & + 'openai/gpt-5-nano': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' | 'max_output_tokens' - | 'temperature' | 'stop' | 'response_format' | 'structured_outputs' > - 'openai/gpt-4.1-mini': VercelGatewayCommonOptions & + 'openai/gpt-5-nano-batch': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' | 'max_output_tokens' - | 'temperature' | 'stop' | 'response_format' | 'structured_outputs' > - 'openai/gpt-4.1-mini-fast': VercelGatewayCommonOptions & + 'openai/gpt-5-pro': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' + > + 'openai/gpt-5-pro-batch': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' + > + 'openai/gpt-5.1-codex': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1902,7 +2433,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-4.1-nano': VercelGatewayCommonOptions & + 'openai/gpt-5.1-codex-max': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1912,7 +2443,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-4.1-nano-fast': VercelGatewayCommonOptions & + 'openai/gpt-5.1-codex-mini': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1922,7 +2453,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-4o': VercelGatewayCommonOptions & + 'openai/gpt-5.1-thinking': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1932,7 +2463,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-4o-fast': VercelGatewayCommonOptions & + 'openai/gpt-5.1-thinking-fast': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1942,7 +2473,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-4o-mini': VercelGatewayCommonOptions & + 'openai/gpt-5.2': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1952,7 +2483,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-4o-mini-fast': VercelGatewayCommonOptions & + 'openai/gpt-5.2-batch': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -1962,68 +2493,67 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-4o-mini-transcribe': VercelGatewayCommonOptions - 'openai/gpt-4o-transcribe': VercelGatewayCommonOptions - 'openai/gpt-5': VercelGatewayCommonOptions & + 'openai/gpt-5.2-codex': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' | 'max_output_tokens' + | 'temperature' | 'stop' | 'response_format' | 'structured_outputs' > - 'openai/gpt-5-codex': VercelGatewayCommonOptions & + 'openai/gpt-5.2-fast': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' | 'max_output_tokens' + | 'temperature' | 'stop' | 'response_format' | 'structured_outputs' > - 'openai/gpt-5-fast': VercelGatewayCommonOptions & + 'openai/gpt-5.2-pro': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' | 'max_output_tokens' + | 'temperature' | 'stop' | 'response_format' | 'structured_outputs' > - 'openai/gpt-5-mini': VercelGatewayCommonOptions & + 'openai/gpt-5.3-codex': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' | 'max_output_tokens' + | 'temperature' | 'stop' | 'response_format' | 'structured_outputs' > - 'openai/gpt-5-mini-fast': VercelGatewayCommonOptions & + 'openai/gpt-5.3-codex-fast': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' | 'max_output_tokens' + | 'temperature' | 'stop' | 'response_format' | 'structured_outputs' > - 'openai/gpt-5-nano': VercelGatewayCommonOptions & + 'openai/gpt-5.4': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' | 'max_output_tokens' + | 'temperature' | 'stop' | 'response_format' | 'structured_outputs' > - 'openai/gpt-5-pro': VercelGatewayCommonOptions & - Pick< - VercelGatewayBaseOptions, - 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' - > - 'openai/gpt-5.1-codex': VercelGatewayCommonOptions & + 'openai/gpt-5.4-batch': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -2033,7 +2563,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-5.1-codex-max': VercelGatewayCommonOptions & + 'openai/gpt-5.4-fast': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -2043,7 +2573,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-5.1-codex-mini': VercelGatewayCommonOptions & + 'openai/gpt-5.4-mini': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -2053,7 +2583,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-5.1-thinking': VercelGatewayCommonOptions & + 'openai/gpt-5.4-mini-batch': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -2063,7 +2593,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-5.1-thinking-fast': VercelGatewayCommonOptions & + 'openai/gpt-5.4-mini-fast': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -2073,7 +2603,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-5.2': VercelGatewayCommonOptions & + 'openai/gpt-5.4-nano': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -2083,7 +2613,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-5.2-codex': VercelGatewayCommonOptions & + 'openai/gpt-5.4-nano-batch': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -2093,7 +2623,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-5.2-fast': VercelGatewayCommonOptions & + 'openai/gpt-5.4-pro': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -2103,7 +2633,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-5.2-pro': VercelGatewayCommonOptions & + 'openai/gpt-5.5': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -2113,7 +2643,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-5.3-codex': VercelGatewayCommonOptions & + 'openai/gpt-5.5-batch': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -2123,17 +2653,16 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-5.3-codex-fast': VercelGatewayCommonOptions & + 'openai/gpt-5.5-fast': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' | 'max_output_tokens' - | 'temperature' | 'stop' | 'response_format' | 'structured_outputs' > - 'openai/gpt-5.4': VercelGatewayCommonOptions & + 'openai/gpt-5.5-pro': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -2143,7 +2672,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-5.4-fast': VercelGatewayCommonOptions & + 'openai/gpt-5.5-pro-batch': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -2153,7 +2682,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-5.4-mini': VercelGatewayCommonOptions & + 'openai/gpt-5.6-luna': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -2163,7 +2692,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-5.4-mini-fast': VercelGatewayCommonOptions & + 'openai/gpt-5.6-luna-batch': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -2173,17 +2702,16 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-5.4-nano': VercelGatewayCommonOptions & + 'openai/gpt-5.6-luna-fast': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' | 'max_output_tokens' - | 'temperature' | 'stop' | 'response_format' | 'structured_outputs' > - 'openai/gpt-5.4-pro': VercelGatewayCommonOptions & + 'openai/gpt-5.6-sol': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -2193,7 +2721,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-5.5': VercelGatewayCommonOptions & + 'openai/gpt-5.6-sol-batch': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -2203,7 +2731,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-5.5-fast': VercelGatewayCommonOptions & + 'openai/gpt-5.6-sol-fast': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -2212,7 +2740,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-5.5-pro': VercelGatewayCommonOptions & + 'openai/gpt-5.6-terra': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -2222,7 +2750,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-5.6-luna': VercelGatewayCommonOptions & + 'openai/gpt-5.6-terra-batch': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -2232,7 +2760,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-5.6-luna-fast': VercelGatewayCommonOptions & + 'openai/gpt-5.6-terra-fast': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -2241,17 +2769,16 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-5.6-sol': VercelGatewayCommonOptions & + 'openai/gpt-6-astra': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' | 'max_output_tokens' - | 'temperature' | 'stop' | 'response_format' | 'structured_outputs' > - 'openai/gpt-5.6-sol-fast': VercelGatewayCommonOptions & + 'openai/gpt-6-astra-batch': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -2260,44 +2787,47 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-5.6-terra': VercelGatewayCommonOptions & + 'openai/gpt-6-astra-fast': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' | 'max_output_tokens' - | 'temperature' | 'stop' | 'response_format' | 'structured_outputs' > - 'openai/gpt-5.6-terra-fast': VercelGatewayCommonOptions & + 'openai/gpt-6-luna': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' | 'max_output_tokens' + | 'temperature' | 'stop' | 'response_format' | 'structured_outputs' > - 'openai/gpt-6-astra': VercelGatewayCommonOptions & + 'openai/gpt-6-luna-batch': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' | 'max_output_tokens' + | 'temperature' | 'stop' | 'response_format' | 'structured_outputs' > - 'openai/gpt-6-astra-fast': VercelGatewayCommonOptions & + 'openai/gpt-6-luna-decisions': VercelGatewayCommonOptions + 'openai/gpt-6-luna-fast': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' | 'max_output_tokens' + | 'temperature' | 'stop' | 'response_format' | 'structured_outputs' > - 'openai/gpt-6-luna': VercelGatewayCommonOptions & + 'openai/gpt-6-sol': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -2307,8 +2837,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-6-luna-decisions': VercelGatewayCommonOptions - 'openai/gpt-6-luna-fast': VercelGatewayCommonOptions & + 'openai/gpt-6-sol-batch': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -2318,7 +2847,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-6-sol': VercelGatewayCommonOptions & + 'openai/gpt-6-sol-fast': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -2328,7 +2857,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-6-sol-fast': VercelGatewayCommonOptions & + 'openai/gpt-6.1-sol': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -2338,7 +2867,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/gpt-6.1-sol': VercelGatewayCommonOptions & + 'openai/gpt-6.1-sol-batch': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -2491,6 +3020,8 @@ export type VercelGatewayChatModelProviderOptionsByName = { 'openai/tts-1': VercelGatewayCommonOptions 'openai/tts-1-hd': VercelGatewayCommonOptions 'openai/whisper-1': VercelGatewayCommonOptions + 'perplexity/pplx-decider-flash-v1.2': VercelGatewayCommonOptions + 'perplexity/pplx-decider-v1.2': VercelGatewayCommonOptions 'perplexity/sonar': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -2521,6 +3052,26 @@ export type VercelGatewayChatModelProviderOptionsByName = { VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' > + 'reflection/beam': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'reflection/beam-free': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > 'sakana/fugu-max': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -2561,6 +3112,22 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > + 'scaledown/scaledown-classify-1': VercelGatewayCommonOptions + 'scaledown/scaledown-extract-1': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'scaledown/scaledown-summarize-1': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' + > 'spacexai/grok-4.1-fast-non-reasoning': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -2591,6 +3158,16 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > + 'spacexai/grok-4.20-multi-agent-batch': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > 'spacexai/grok-4.20-multi-agent-beta': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -2611,6 +3188,16 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > + 'spacexai/grok-4.20-non-reasoning-batch': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > 'spacexai/grok-4.20-non-reasoning-beta': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -2631,6 +3218,16 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > + 'spacexai/grok-4.20-reasoning-batch': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > 'spacexai/grok-4.20-reasoning-beta': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -2651,6 +3248,16 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > + 'spacexai/grok-4.3-batch': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > 'spacexai/grok-4.5': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -2693,7 +3300,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { > 'spacexai/grok-stt': VercelGatewayCommonOptions 'spacexai/grok-tts': VercelGatewayCommonOptions - 'spacexai/grok-voice-think-fast-1.0': VercelGatewayCommonOptions & + 'spacexai/grok-voice-3.0': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' @@ -2703,7 +3310,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' > - 'stepfun/step-3.5-flash': VercelGatewayCommonOptions & + 'stealth/glyph-cluster': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' @@ -2789,6 +3396,8 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'structured_outputs' > 'typesafe-ai/jev': VercelGatewayCommonOptions + 'typesafe-ai/jev-1.13.0': VercelGatewayCommonOptions + 'typesafe-ai/jev-1.14.0': VercelGatewayCommonOptions 'xiaomi/mimo-v2.5': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -3006,20 +3615,13 @@ export type VercelGatewayModelInputModalitiesByName = { 'alibaba/qwen-3-235b': readonly ['text'] 'alibaba/qwen-3-30b': readonly ['text'] 'alibaba/qwen-3-32b': readonly ['text'] - 'alibaba/qwen-3.6-max-preview': readonly ['text'] - 'alibaba/qwen3-235b-a22b-thinking': readonly ['text', 'image', 'document'] 'alibaba/qwen3-coder': readonly ['text'] 'alibaba/qwen3-coder-30b-a3b': readonly ['text'] 'alibaba/qwen3-coder-next': readonly ['text'] - 'alibaba/qwen3-coder-plus': readonly ['text'] - 'alibaba/qwen3-max': readonly ['text'] - 'alibaba/qwen3-max-preview': readonly ['text'] 'alibaba/qwen3-max-thinking': readonly ['text'] 'alibaba/qwen3-next-80b-a3b-instruct': readonly ['text'] 'alibaba/qwen3-next-80b-a3b-thinking': readonly ['text'] - 'alibaba/qwen3-vl-235b-a22b-instruct': readonly ['text', 'image'] 'alibaba/qwen3-vl-instruct': readonly ['text', 'image'] - 'alibaba/qwen3-vl-thinking': readonly ['text', 'image', 'document'] 'alibaba/qwen3.5-flash': readonly ['text', 'image', 'document'] 'alibaba/qwen3.5-plus': readonly ['text', 'image', 'document'] 'alibaba/qwen3.6-27b': readonly ['text', 'image', 'document'] @@ -3038,35 +3640,49 @@ export type VercelGatewayModelInputModalitiesByName = { 'amazon/nova-lite': readonly ['text', 'image', 'document'] 'amazon/nova-micro': readonly ['text'] 'amazon/nova-pro': readonly ['text', 'image', 'document'] - 'anthropic/claude-3-haiku': readonly ['text', 'image'] 'anthropic/claude-fable-5': readonly ['text', 'image', 'document'] + 'anthropic/claude-fable-5-batch': readonly ['text', 'image', 'document'] 'anthropic/claude-fable-5.1': readonly ['text', 'image', 'document'] + 'anthropic/claude-fable-5.1-batch': readonly ['text', 'image', 'document'] 'anthropic/claude-haiku-4.5': readonly ['text', 'image', 'document'] - 'anthropic/claude-opus-4': readonly ['text', 'image', 'document'] + 'anthropic/claude-haiku-4.5-batch': readonly ['text', 'image', 'document'] + 'anthropic/claude-haiku-5.5': readonly ['text', 'image', 'document'] + 'anthropic/claude-haiku-5.5-batch': readonly ['text', 'image', 'document'] 'anthropic/claude-opus-4.5': readonly ['text', 'image', 'document'] + 'anthropic/claude-opus-4.5-batch': readonly ['text', 'image', 'document'] 'anthropic/claude-opus-4.6': readonly ['text', 'image', 'document'] + 'anthropic/claude-opus-4.6-batch': readonly ['text', 'image', 'document'] 'anthropic/claude-opus-4.7': readonly ['text', 'image', 'document'] + 'anthropic/claude-opus-4.7-batch': readonly ['text', 'image', 'document'] 'anthropic/claude-opus-4.8': readonly ['text', 'image', 'document'] + 'anthropic/claude-opus-4.8-batch': readonly ['text', 'image', 'document'] 'anthropic/claude-opus-4.8-fast': readonly ['text', 'image', 'document'] 'anthropic/claude-opus-5': readonly ['text', 'image', 'document'] + 'anthropic/claude-opus-5-batch': readonly ['text', 'image', 'document'] 'anthropic/claude-opus-5-fast': readonly ['text', 'image', 'document'] 'anthropic/claude-opus-5.5': readonly ['text', 'image', 'document'] + 'anthropic/claude-opus-5.5-batch': readonly ['text', 'image', 'document'] 'anthropic/claude-opus-5.5-fast': readonly ['text', 'image', 'document'] - 'anthropic/claude-sonnet-4': readonly ['text', 'image', 'document'] 'anthropic/claude-sonnet-4.5': readonly ['text', 'image', 'document'] + 'anthropic/claude-sonnet-4.5-batch': readonly ['text', 'image', 'document'] 'anthropic/claude-sonnet-4.6': readonly ['text', 'image', 'document'] + 'anthropic/claude-sonnet-4.6-batch': readonly ['text', 'image', 'document'] 'anthropic/claude-sonnet-5': readonly ['text', 'image', 'document'] + 'anthropic/claude-sonnet-5-batch': readonly ['text', 'image', 'document'] 'anthropic/claude-sonnet-5.5': readonly ['text', 'image', 'document'] + 'anthropic/claude-sonnet-5.5-batch': readonly ['text', 'image', 'document'] 'arcee-ai/trinity-large-thinking': readonly ['text'] + 'baseten/elephant-1': readonly ['text'] + 'baseten/mammoth-1': readonly ['text'] 'bytedance/seed-1.6': readonly ['text', 'image'] 'bytedance/seed-1.8': readonly ['text', 'image'] 'bytedance/seed-2.1-turbo': readonly ['text', 'image', 'video'] + 'callstack/apex': readonly ['text', 'image'] 'cohere/command-a': readonly ['text'] 'convaiinnovations/laya': readonly ['text'] 'convaiinnovations/laya-free': readonly ['text'] 'deepseek/deepseek-r1': readonly ['text'] 'deepseek/deepseek-v3.1': readonly ['text'] - 'deepseek/deepseek-v3.1-terminus': readonly ['text'] 'deepseek/deepseek-v3.2': readonly ['text'] 'deepseek/deepseek-v3.2-thinking': readonly ['text'] 'deepseek/deepseek-v4-flash': readonly ['text'] @@ -3074,40 +3690,75 @@ export type VercelGatewayModelInputModalitiesByName = { 'deepseek/deepseek-v4-flash-vision-exp': readonly ['text', 'image'] 'deepseek/deepseek-v4-pro': readonly ['text'] 'deepseek/deepseek-v4-pro-0813': readonly ['text'] - 'deepseek/deepseek-v4.1-flash': readonly ['text', 'image'] + 'deepseek/deepseek-v4.1-flash': readonly ['text', 'image', 'document'] + 'deepseek/deepseek-v4.1-flash-1017': readonly ['text', 'image'] + 'deepseek/deepseek-v4.1-flash-1017-fast': readonly ['text', 'image'] 'deepseek/deepseek-v4.1-flash-fast': readonly ['text', 'image'] + 'elorian/glimpse': readonly ['text', 'image', 'video'] 'fireworks/ember-1': readonly ['text', 'image'] + 'fish-audio/drama-3': readonly ['text'] 'fish-audio/s1': readonly ['text'] 'fish-audio/s2-pro': readonly ['text'] 'fish-audio/s2.1-pro': readonly ['text'] 'fish-audio/transcribe-1': readonly ['text', 'audio'] 'google/gemini-2.5-flash': readonly ['text', 'image', 'document'] + 'google/gemini-2.5-flash-batch': readonly ['text', 'image', 'document'] 'google/gemini-2.5-flash-image': readonly ['text', 'image'] 'google/gemini-2.5-flash-lite': readonly ['text', 'image', 'document'] + 'google/gemini-2.5-flash-lite-batch': readonly ['text', 'image', 'document'] 'google/gemini-2.5-pro': readonly ['text', 'image', 'document'] + 'google/gemini-2.5-pro-batch': readonly ['text', 'image', 'document'] 'google/gemini-3-flash': readonly ['text', 'image', 'document'] + 'google/gemini-3-flash-batch': readonly ['text', 'image', 'document'] 'google/gemini-3-pro-image': readonly ['text', 'image'] 'google/gemini-3.1-flash-image': readonly ['text', 'image'] 'google/gemini-3.1-flash-image-preview': readonly ['text', 'image'] 'google/gemini-3.1-flash-lite': readonly ['text', 'image', 'document'] + 'google/gemini-3.1-flash-lite-batch': readonly ['text', 'image', 'document'] 'google/gemini-3.1-flash-lite-image': readonly ['text', 'image'] 'google/gemini-3.1-pro-preview': readonly ['text', 'image', 'document'] + 'google/gemini-3.1-pro-preview-batch': readonly ['text', 'image', 'document'] 'google/gemini-3.5-flash': readonly ['text', 'image', 'document', 'video'] + 'google/gemini-3.5-flash-batch': readonly [ + 'text', + 'image', + 'document', + 'video', + ] 'google/gemini-3.5-flash-lite': readonly [ 'text', 'image', 'document', 'video', ] + 'google/gemini-3.5-flash-lite-batch': readonly [ + 'text', + 'image', + 'document', + 'video', + ] 'google/gemini-3.5-transcribe': readonly ['text', 'audio'] 'google/gemini-3.5-transcribe-live': readonly ['text', 'audio'] 'google/gemini-3.6-flash': readonly ['text', 'image', 'document', 'video'] + 'google/gemini-3.6-flash-batch': readonly [ + 'text', + 'image', + 'document', + 'video', + ] 'google/gemini-3.7-flash': readonly ['text', 'image', 'document', 'video'] + 'google/gemini-3.7-flash-batch': readonly [ + 'text', + 'image', + 'document', + 'video', + ] 'google/gemini-3.8-flash': readonly ['text', 'image', 'document', 'video'] 'google/gemini-3.8-flash-lite-tts': readonly ['text'] 'google/gemini-3.8-flash-tts': readonly ['text'] 'google/gemini-3.8-live': readonly ['text', 'audio'] 'google/gemini-3.8-live-extended-thinking': readonly ['text', 'audio'] + 'google/gemini-4-argon': readonly ['text', 'image', 'document', 'video'] 'google/gemini-nano-banana-2.1': readonly ['text', 'image'] 'google/gemini-omni-flash-preview': readonly [ 'text', @@ -3119,17 +3770,19 @@ export type VercelGatewayModelInputModalitiesByName = { 'google/gemma-4-31b-it': readonly ['text', 'image', 'document'] 'inception/mercury-2': readonly ['text'] 'inception/mercury-2.5': readonly ['text'] + 'inception/mercury-3': readonly ['text'] 'inception/mercury-coder-small': readonly ['text'] 'inclusionai/ling-3.0-flash': readonly ['text'] 'inclusionai/ling-3.0-flash-fin': readonly ['text'] 'inclusionai/ling-3.0-flash-sante': readonly ['text'] 'inclusionai/ling-3.0-flash-vl': readonly ['text', 'image', 'video'] 'inclusionai/ling-3.1-flash': readonly ['text'] - 'inclusionai/ling-3.1-flash-free': readonly ['text'] 'inference-net/schematron-v2-small': readonly ['text'] 'inference-net/schematron-v2-turbo': readonly ['text'] 'interfaze/interfaze-beta': readonly ['text', 'image', 'document'] - 'liquid/d1': readonly ['text'] + 'liquid/d1': readonly ['text', 'image'] + 'liquid/d1-ultra': readonly ['text', 'image'] + 'liquid/lfm2.5-24b-a2b': readonly ['text'] 'meituan/longcat-2.5-preview': readonly ['text', 'image'] 'meta/llama-3.1-70b': readonly ['text'] 'meta/llama-3.1-8b': readonly ['text'] @@ -3142,12 +3795,15 @@ export type VercelGatewayModelInputModalitiesByName = { 'meta/muse-spark-1.2-contributor': readonly ['text', 'image', 'document'] 'meta/muse-spark-1.3': readonly ['text', 'image', 'document'] 'meta/muse-spark-1.3-contributor': readonly ['text', 'image', 'document'] + 'meta/muse-spark-open': readonly ['text', 'image', 'audio', 'video'] + 'meta/muse-wonder-1.0': readonly ['text', 'image', 'document'] 'microsoft/mai-transcribe-2': readonly ['text', 'audio'] 'microsoft/mai-transcribe-2-streaming': readonly ['text', 'audio'] 'microsoft/mai-voice-2': readonly ['text'] 'microsoft/mai-voice-2-flash': readonly ['text'] 'microsoft/mai-voice-2.1': readonly ['text'] 'microsoft/mai-voice-2.1-flash': readonly ['text'] + 'microsoft/microsoft-decision-1': readonly ['text'] 'minimax/minimax-m2': readonly ['text'] 'minimax/minimax-m2.1': readonly ['text'] 'minimax/minimax-m2.1-lightning': readonly ['text'] @@ -3156,6 +3812,7 @@ export type VercelGatewayModelInputModalitiesByName = { 'minimax/minimax-m2.7': readonly ['text'] 'minimax/minimax-m2.7-highspeed': readonly ['text'] 'minimax/minimax-m3': readonly ['text', 'image', 'document'] + 'minimax/minimax-m3.1-flash': readonly ['text', 'image'] 'mistral/codestral': readonly ['text'] 'mistral/ministral-14b': readonly ['text', 'image', 'document'] 'mistral/ministral-3b': readonly ['text', 'image'] @@ -3165,9 +3822,11 @@ export type VercelGatewayModelInputModalitiesByName = { 'mistral/mistral-medium-3.5': readonly ['text', 'image'] 'mistral/mistral-nemo': readonly ['text'] 'mistral/mistral-small': readonly ['text', 'image'] + 'mistral/voxtral-mini-transcribe-3': readonly ['text', 'audio'] + 'mistral/voxtral-mini-tts-3': readonly ['text'] + 'mistral/voxtral-small-transcribe-3': readonly ['text', 'audio'] 'mixedbread/toast-1': readonly ['text'] 'moonshotai/kimi-k2': readonly ['text'] - 'moonshotai/kimi-k2-thinking': readonly ['text'] 'moonshotai/kimi-k2.5': readonly ['text', 'image'] 'moonshotai/kimi-k2.6': readonly ['text', 'image', 'video'] 'moonshotai/kimi-k2.7-code': readonly ['text', 'image', 'document', 'video'] @@ -3185,63 +3844,87 @@ export type VercelGatewayModelInputModalitiesByName = { 'nvidia/nemotron-3-super-120b-a12b': readonly ['text'] 'nvidia/nemotron-3-ultra-550b-a55b': readonly ['text'] 'nvidia/nemotron-3.5-lightning': readonly ['text'] + 'nvidia/nemotron-3.5-lightning-free': readonly ['text'] + 'nvidia/nemotron-3.5-super-vl': readonly ['text', 'image', 'video'] 'nvidia/nemotron-nano-12b-v2-vl': readonly ['text', 'image'] 'nvidia/nemotron-nano-9b-v2': readonly ['text'] 'openai/gpt-3.5-turbo': readonly ['text'] 'openai/gpt-4-turbo': readonly ['text', 'image'] 'openai/gpt-4.1': readonly ['text', 'image', 'document'] + 'openai/gpt-4.1-batch': readonly ['text', 'image', 'document'] 'openai/gpt-4.1-fast': readonly ['text', 'image', 'document'] 'openai/gpt-4.1-mini': readonly ['text', 'image', 'document'] + 'openai/gpt-4.1-mini-batch': readonly ['text', 'image', 'document'] 'openai/gpt-4.1-mini-fast': readonly ['text', 'image', 'document'] 'openai/gpt-4.1-nano': readonly ['text', 'image', 'document'] + 'openai/gpt-4.1-nano-batch': readonly ['text', 'image', 'document'] 'openai/gpt-4.1-nano-fast': readonly ['text', 'image', 'document'] 'openai/gpt-4o': readonly ['text', 'image', 'document'] + 'openai/gpt-4o-batch': readonly ['text', 'image', 'document'] 'openai/gpt-4o-fast': readonly ['text', 'image', 'document'] 'openai/gpt-4o-mini': readonly ['text', 'image', 'document'] + 'openai/gpt-4o-mini-batch': readonly ['text', 'image', 'document'] 'openai/gpt-4o-mini-fast': readonly ['text', 'image', 'document'] 'openai/gpt-4o-mini-transcribe': readonly ['text', 'audio'] 'openai/gpt-4o-transcribe': readonly ['text', 'audio'] 'openai/gpt-5': readonly ['text', 'image', 'document'] + 'openai/gpt-5-batch': readonly ['text', 'image', 'document'] 'openai/gpt-5-codex': readonly ['text', 'image', 'document'] 'openai/gpt-5-fast': readonly ['text', 'image', 'document'] 'openai/gpt-5-mini': readonly ['text', 'image', 'document'] + 'openai/gpt-5-mini-batch': readonly ['text', 'image', 'document'] 'openai/gpt-5-mini-fast': readonly ['text', 'image', 'document'] 'openai/gpt-5-nano': readonly ['text', 'image', 'document'] + 'openai/gpt-5-nano-batch': readonly ['text', 'image', 'document'] 'openai/gpt-5-pro': readonly ['text', 'image', 'document'] + 'openai/gpt-5-pro-batch': readonly ['text', 'image', 'document'] 'openai/gpt-5.1-codex': readonly ['text', 'image', 'document'] 'openai/gpt-5.1-codex-max': readonly ['text', 'image', 'document'] 'openai/gpt-5.1-codex-mini': readonly ['text', 'image', 'document'] 'openai/gpt-5.1-thinking': readonly ['text', 'image', 'document'] 'openai/gpt-5.1-thinking-fast': readonly ['text', 'image', 'document'] 'openai/gpt-5.2': readonly ['text', 'image', 'document'] + 'openai/gpt-5.2-batch': readonly ['text', 'image', 'document'] 'openai/gpt-5.2-codex': readonly ['text', 'image', 'document'] 'openai/gpt-5.2-fast': readonly ['text', 'image', 'document'] 'openai/gpt-5.2-pro': readonly ['text', 'image', 'document'] 'openai/gpt-5.3-codex': readonly ['text', 'image', 'document'] 'openai/gpt-5.3-codex-fast': readonly ['text', 'image', 'document'] 'openai/gpt-5.4': readonly ['text', 'image', 'document'] + 'openai/gpt-5.4-batch': readonly ['text', 'image', 'document'] 'openai/gpt-5.4-fast': readonly ['text', 'image', 'document'] 'openai/gpt-5.4-mini': readonly ['text', 'image', 'document'] + 'openai/gpt-5.4-mini-batch': readonly ['text', 'image', 'document'] 'openai/gpt-5.4-mini-fast': readonly ['text', 'image', 'document'] 'openai/gpt-5.4-nano': readonly ['text', 'image', 'document'] + 'openai/gpt-5.4-nano-batch': readonly ['text', 'image', 'document'] 'openai/gpt-5.4-pro': readonly ['text', 'image', 'document'] 'openai/gpt-5.5': readonly ['text', 'image', 'document'] + 'openai/gpt-5.5-batch': readonly ['text', 'image', 'document'] 'openai/gpt-5.5-fast': readonly ['text', 'image', 'document'] 'openai/gpt-5.5-pro': readonly ['text', 'image', 'document'] + 'openai/gpt-5.5-pro-batch': readonly ['text', 'image', 'document'] 'openai/gpt-5.6-luna': readonly ['text', 'image', 'document'] + 'openai/gpt-5.6-luna-batch': readonly ['text', 'image', 'document'] 'openai/gpt-5.6-luna-fast': readonly ['text', 'image', 'document'] 'openai/gpt-5.6-sol': readonly ['text', 'image', 'document'] + 'openai/gpt-5.6-sol-batch': readonly ['text', 'image', 'document'] 'openai/gpt-5.6-sol-fast': readonly ['text', 'image', 'document'] 'openai/gpt-5.6-terra': readonly ['text', 'image', 'document'] + 'openai/gpt-5.6-terra-batch': readonly ['text', 'image', 'document'] 'openai/gpt-5.6-terra-fast': readonly ['text', 'image', 'document'] 'openai/gpt-6-astra': readonly ['text', 'image', 'document'] + 'openai/gpt-6-astra-batch': readonly ['text', 'image', 'document'] 'openai/gpt-6-astra-fast': readonly ['text', 'image', 'document'] 'openai/gpt-6-luna': readonly ['text', 'image', 'document'] + 'openai/gpt-6-luna-batch': readonly ['text', 'image', 'document'] 'openai/gpt-6-luna-decisions': readonly ['text'] 'openai/gpt-6-luna-fast': readonly ['text', 'image', 'document'] 'openai/gpt-6-sol': readonly ['text', 'image', 'document'] + 'openai/gpt-6-sol-batch': readonly ['text', 'image', 'document'] 'openai/gpt-6-sol-fast': readonly ['text', 'image', 'document'] 'openai/gpt-6.1-sol': readonly ['text', 'image', 'document'] + 'openai/gpt-6.1-sol-batch': readonly ['text', 'image', 'document'] 'openai/gpt-6.1-sol-fast': readonly ['text', 'image', 'document'] 'openai/gpt-live-1': readonly ['text', 'audio'] 'openai/gpt-oss-120b': readonly ['text'] @@ -3263,39 +3946,54 @@ export type VercelGatewayModelInputModalitiesByName = { 'openai/tts-1': readonly ['text'] 'openai/tts-1-hd': readonly ['text'] 'openai/whisper-1': readonly ['text', 'audio'] + 'perplexity/pplx-decider-flash-v1.2': readonly ['text', 'image'] + 'perplexity/pplx-decider-v1.2': readonly ['text', 'image'] 'perplexity/sonar': readonly ['text', 'image'] 'poolside/laguna-s-2.1': readonly ['text'] 'poolside/laguna-s-2.1-free': readonly ['text'] 'quiverai/arrow-2': readonly ['text', 'image'] 'quiverai/arrow-2-telos': readonly ['text', 'image'] + 'reflection/beam': readonly ['text'] + 'reflection/beam-free': readonly ['text'] 'sakana/fugu-max': readonly ['text', 'image'] 'sakana/fugu-ultra': readonly ['text', 'image'] 'sakana/fugu-ultra-v2': readonly ['text', 'image'] 'sakana/namazu': readonly ['text', 'image', 'document'] + 'scaledown/scaledown-classify-1': readonly ['text'] + 'scaledown/scaledown-extract-1': readonly ['text'] + 'scaledown/scaledown-summarize-1': readonly ['text'] 'spacexai/grok-4.1-fast-non-reasoning': readonly ['text', 'image', 'document'] 'spacexai/grok-4.1-fast-reasoning': readonly ['text', 'image', 'document'] 'spacexai/grok-4.20-multi-agent': readonly ['text', 'image', 'document'] + 'spacexai/grok-4.20-multi-agent-batch': readonly ['text', 'image', 'document'] 'spacexai/grok-4.20-multi-agent-beta': readonly ['text', 'image', 'document'] 'spacexai/grok-4.20-non-reasoning': readonly ['text', 'image', 'document'] + 'spacexai/grok-4.20-non-reasoning-batch': readonly [ + 'text', + 'image', + 'document', + ] 'spacexai/grok-4.20-non-reasoning-beta': readonly [ 'text', 'image', 'document', ] 'spacexai/grok-4.20-reasoning': readonly ['text', 'image', 'document'] + 'spacexai/grok-4.20-reasoning-batch': readonly ['text', 'image', 'document'] 'spacexai/grok-4.20-reasoning-beta': readonly ['text', 'image', 'document'] 'spacexai/grok-4.3': readonly ['text', 'image', 'document'] + 'spacexai/grok-4.3-batch': readonly ['text', 'image', 'document'] 'spacexai/grok-4.5': readonly ['text', 'image', 'document'] 'spacexai/grok-4.6': readonly ['text', 'image'] 'spacexai/grok-4.7': readonly ['text', 'image'] 'spacexai/grok-build-0.1': readonly ['text', 'image'] 'spacexai/grok-stt': readonly ['text', 'audio'] 'spacexai/grok-tts': readonly ['text'] - 'spacexai/grok-voice-think-fast-1.0': readonly ['text', 'audio'] + 'spacexai/grok-voice-3.0': readonly ['text', 'audio'] 'spacexai/grok-voice-think-fast-2.0': readonly ['text', 'audio'] - 'stepfun/step-3.5-flash': readonly ['text', 'image'] + 'stealth/glyph-cluster': readonly ['text'] 'stepfun/step-3.7-flash': readonly ['text', 'image'] - 'stepfun/step-5-preview': readonly ['text', 'image'] + 'stepfun/step-5-preview': readonly ['text', 'image', 'video'] 'tencent/hy-mt2-lite': readonly ['text'] 'tencent/hy-mt2-plus': readonly ['text'] 'tencent/hy-mt2-pro': readonly ['text'] @@ -3304,6 +4002,8 @@ export type VercelGatewayModelInputModalitiesByName = { 'thinkingmachines/inkling': readonly ['text', 'image', 'document'] 'thinkingmachines/inkling-small': readonly ['text', 'image', 'document'] 'typesafe-ai/jev': readonly ['text'] + 'typesafe-ai/jev-1.13.0': readonly ['text', 'image'] + 'typesafe-ai/jev-1.14.0': readonly ['text', 'image'] 'xiaomi/mimo-v2.5': readonly ['text', 'image'] 'xiaomi/mimo-v2.5-pro': readonly ['text'] 'xiaomi/mimo-v2.6-flash': readonly ['text', 'image', 'audio', 'video'] @@ -3328,7 +4028,7 @@ export type VercelGatewayModelInputModalitiesByName = { 'zai/glm-5.2-fast': readonly ['text'] 'zai/glm-5.3': readonly ['text'] 'zai/glm-5.3-fast': readonly ['text'] - 'zai/glm-5.3-flash': readonly ['text', 'image'] + 'zai/glm-5.3-flash': readonly ['text', 'image', 'video'] 'zai/glm-5.3-flashx': readonly ['text', 'image'] 'zai/glm-5v-turbo': readonly ['text', 'image', 'document'] } @@ -3583,14 +4283,11 @@ const VERCEL_GATEWAY_REASONING = { 'alibaba/qwen-3-235b': EFFORT_NONE_LOW_TO_HIGH, 'alibaba/qwen-3-30b': EFFORT_OFF_HIGH, 'alibaba/qwen-3-32b': BUDGET_OFF_HIGH, - 'alibaba/qwen-3.6-max-preview': BUDGET_OFF_HIGH, - 'alibaba/qwen3-235b-a22b-thinking': BUDGET_MINIMAL_TO_HIGH, 'alibaba/qwen3-coder': EFFORT_MINIMAL_TO_HIGH, 'alibaba/qwen3-coder-30b-a3b': EFFORT_MINIMAL_TO_HIGH, 'alibaba/qwen3-coder-next': EFFORT_MINIMAL_TO_HIGH, 'alibaba/qwen3-max-thinking': BUDGET_MINIMAL_TO_HIGH, 'alibaba/qwen3-next-80b-a3b-thinking': BUDGET_MINIMAL_TO_HIGH, - 'alibaba/qwen3-vl-thinking': BUDGET_MINIMAL_TO_HIGH, 'alibaba/qwen3.5-flash': BUDGET_NONE_MINIMAL_TO_MAX, 'alibaba/qwen3.5-plus': BUDGET_NONE_MINIMAL_TO_MAX, 'alibaba/qwen3.6-27b': BUDGET_OFF_HIGH, @@ -3609,7 +4306,6 @@ const VERCEL_GATEWAY_REASONING = { 'anthropic/claude-fable-5': BUDGET_NONE_LOW_TO_MAX, 'anthropic/claude-fable-5.1': BUDGET_NONE_LOW_TO_MAX, 'anthropic/claude-haiku-4.5': BUDGET_OFF_HIGH, - 'anthropic/claude-opus-4': BUDGET_OFF_HIGH, 'anthropic/claude-opus-4.5': BUDGET_NONE_LOW_TO_HIGH, 'anthropic/claude-opus-4.6': BUDGET_NONE_LOW_TO_HIGH_MAX, 'anthropic/claude-opus-4.7': BUDGET_NONE_LOW_TO_MAX, @@ -3619,7 +4315,6 @@ const VERCEL_GATEWAY_REASONING = { 'anthropic/claude-opus-5-fast': BUDGET_NONE_LOW_TO_MAX, 'anthropic/claude-opus-5.5': EFFORT_LOW_TO_MAX, 'anthropic/claude-opus-5.5-fast': EFFORT_LOW_TO_MAX, - 'anthropic/claude-sonnet-4': BUDGET_OFF_HIGH, 'anthropic/claude-sonnet-4.5': BUDGET_OFF_TO_HIGH, 'anthropic/claude-sonnet-4.6': BUDGET_NONE_LOW_TO_HIGH_MAX, 'anthropic/claude-sonnet-5': BUDGET_NONE_LOW_TO_MAX, @@ -3630,7 +4325,6 @@ const VERCEL_GATEWAY_REASONING = { 'bytedance/seed-2.1-turbo': EFFORT_NONE_LOW_TO_HIGH, 'deepseek/deepseek-r1': EFFORT_MINIMAL_TO_HIGH, 'deepseek/deepseek-v3.1': EFFORT_NONE_LOW_TO_HIGH, - 'deepseek/deepseek-v3.1-terminus': EFFORT_NONE_LOW_TO_HIGH, 'deepseek/deepseek-v3.2-thinking': EFFORT_NONE_LOW_TO_HIGH, 'deepseek/deepseek-v4-flash': EFFORT_NONE_LOW_TO_HIGH, 'deepseek/deepseek-v4-flash-0731': EFFORT_NONE_LOW_TO_HIGH, @@ -3663,7 +4357,6 @@ const VERCEL_GATEWAY_REASONING = { 'inclusionai/ling-3.0-flash-sante': EFFORT_NONE_LOW_TO_HIGH, 'inclusionai/ling-3.0-flash-vl': EFFORT_OFF_HIGH, 'inclusionai/ling-3.1-flash': EFFORT_NONE_LOW_TO_HIGH, - 'inclusionai/ling-3.1-flash-free': EFFORT_NONE_LOW_TO_HIGH, 'interfaze/interfaze-beta': EFFORT_LOW_TO_HIGH, 'meituan/longcat-2.5-preview': EFFORT_OFF_HIGH, 'meta/muse-glimmer-30b': EFFORT_NONE_LOW_TO_HIGH, @@ -3681,7 +4374,6 @@ const VERCEL_GATEWAY_REASONING = { 'minimax/minimax-m2.7-highspeed': BUDGET_MINIMAL_TO_HIGH, 'minimax/minimax-m3': BUDGET_MINIMAL_TO_HIGH, 'mistral/mistral-medium-3.5': EFFORT_NONE_HIGH, - 'moonshotai/kimi-k2-thinking': EFFORT_NONE_LOW_TO_HIGH, 'moonshotai/kimi-k2.5': EFFORT_OFF_HIGH, 'moonshotai/kimi-k2.6': EFFORT_OFF_HIGH, 'moonshotai/kimi-k2.7-code': EFFORT_NONE_LOW_TO_HIGH, @@ -3765,7 +4457,6 @@ const VERCEL_GATEWAY_REASONING = { 'spacexai/grok-4.6': EFFORT_LOW_TO_XHIGH, 'spacexai/grok-4.7': EFFORT_LOW_TO_XHIGH, 'spacexai/grok-build-0.1': EFFORT_NONE_LOW_TO_HIGH, - 'stepfun/step-3.5-flash': EFFORT_LOW_TO_HIGH, 'stepfun/step-3.7-flash': EFFORT_LOW_TO_HIGH, 'tencent/hy3': EFFORT_NONE_LOW_HIGH, 'tencent/hy4-preview': EFFORT_NONE_HIGH, diff --git a/scripts/.sync-models-last-run b/scripts/.sync-models-last-run index ee2a3c7ddb..0e8cd66fa9 100644 --- a/scripts/.sync-models-last-run +++ b/scripts/.sync-models-last-run @@ -1 +1 @@ -1791374971 +1792665861 diff --git a/scripts/llmgateway.models.json b/scripts/llmgateway.models.json index 0cd08ef5e8..f02f0e0a0c 100644 --- a/scripts/llmgateway.models.json +++ b/scripts/llmgateway.models.json @@ -2875,7 +2875,7 @@ "name": "DeepSeek V4.1 Flash", "display_name": "DeepSeek V4.1 Flash", "created": 1788998400, - "description": "deepseek-v4.1-flash provided by deepseek, alibaba, deepinfra, fireworks, together-ai, novita, baidu, entrim, luminal, sciforium, scx-ai-gp, runware, consensusprotocol", + "description": "deepseek-v4.1-flash provided by deepseek, alibaba, deepinfra, fireworks, together-ai, novita, baidu, entrim, reka-ai, luminal, sciforium, scx-ai-gp, runware, consensusprotocol", "family": "deepseek", "architecture": { "input_modalities": ["text", "image"], @@ -3086,6 +3086,36 @@ "reasoning_efforts": ["max", "xhigh", "high", "medium", "low"], "stability": "stable" }, + { + "providerId": "reka-ai", + "externalId": "deepseek41-flash", + "pricing": { + "prompt": "0.0000003", + "completion": "0.0000012", + "image": "0", + "request": "0", + "input_cache_read": "0.000000006", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "streaming": true, + "vision": true, + "cancellation": false, + "tools": true, + "parallelToolCalls": false, + "reasoning": true, + "reasoning_efforts": [ + "none", + "minimal", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "max_output": 393216, + "stability": "stable" + }, { "providerId": "luminal", "externalId": "deepseek-ai/DeepSeek-V4.1-Flash", @@ -3225,7 +3255,7 @@ "name": "DeepSeek V4.1 Flash 1017", "display_name": "DeepSeek V4.1 Flash 1017", "created": 1792195200, - "description": "deepseek-v4.1-flash-1017 provided by deepseek, alibaba, together-ai, novita, inference.net, deepinfra", + "description": "deepseek-v4.1-flash-1017 provided by deepseek, alibaba, together-ai, novita, inference.net, deepinfra, reka-ai", "family": "deepseek", "architecture": { "input_modalities": ["text", "image"], @@ -3385,6 +3415,36 @@ "max" ], "max_output": 393216 + }, + { + "providerId": "reka-ai", + "externalId": "deepseek41-flash-20261017", + "pricing": { + "prompt": "0.00000015", + "completion": "0.0000006", + "image": "0", + "request": "0", + "input_cache_read": "0.000000003", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "streaming": true, + "vision": true, + "cancellation": false, + "tools": true, + "parallelToolCalls": false, + "reasoning": true, + "reasoning_efforts": [ + "none", + "minimal", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "max_output": 393216, + "stability": "stable" } ], "pricing": { @@ -17634,11 +17694,11 @@ } ], "pricing": { - "prompt": "0.168e-6", - "completion": "0.336e-6", + "prompt": "0.14e-6", + "completion": "0.28e-6", "image": "0", "request": "0", - "input_cache_read": "0.0034e-6", + "input_cache_read": "0.0028e-6", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", @@ -17659,7 +17719,8 @@ ], "json_output": true, "structured_outputs": false, - "free": false + "free": false, + "deactivated_at": "2026-10-23T00:00:00.000Z" }, { "id": "mimo-v2.5-pro", @@ -17771,11 +17832,11 @@ } ], "pricing": { - "prompt": "0.522e-6", - "completion": "1.044e-6", + "prompt": "0.435e-6", + "completion": "0.87e-6", "image": "0", "request": "0", - "input_cache_read": "0.0043e-6", + "input_cache_read": "0.0036e-6", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", @@ -17796,7 +17857,8 @@ ], "json_output": true, "structured_outputs": false, - "free": false + "free": false, + "deactivated_at": "2026-10-23T00:00:00.000Z" }, { "id": "mimo-v2.6-flash", diff --git a/scripts/lovable-gateway.models.json b/scripts/lovable-gateway.models.json index 0e25e9a92f..e6aa71be12 100644 --- a/scripts/lovable-gateway.models.json +++ b/scripts/lovable-gateway.models.json @@ -1,11 +1,933 @@ [ + { + "premium_output_modalities": [], + "id": "anthropic/claude-fable-5-1", + "object": "model", + "created": 1789344000, + "released": 1788220800, + "expiration_date": null, + "deprecated": false, + "owned_by": "anthropic", + "name": "Claude Fable 5.1", + "description": "Anthropic's most capable model for demanding reasoning and long-running agent tasks.", + "context_window": 1000000, + "max_tokens": 128000, + "knowledge": "2026-06", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text", + "search" + ] + }, + "supported_surfaces": [ + "messages" + ], + "pricing": { + "input": { + "image": { + "billed_as": "text" + }, + "text": { + "tiers": [ + { + "cost": "0.00001", + "min": 0 + } + ], + "cache_read": { + "tiers": [ + { + "cost": "0.00000025", + "min": 0 + } + ] + }, + "cache_write": { + "tiers": [ + { + "cost": "0.0000125", + "min": 0 + } + ] + }, + "cache_write_1h": { + "tiers": [ + { + "cost": "0.00002", + "min": 0 + } + ] + } + } + }, + "output": { + "search": { + "tiers": [ + { + "cost": "0.01", + "min": 0 + } + ], + "unit": "request" + }, + "text": { + "tiers": [ + { + "cost": "0.00005", + "min": 0 + } + ] + } + }, + "service_tiers": { + "us": { + "input": { + "image": { + "billed_as": "text" + }, + "text": { + "tiers": [ + { + "cost": "0.000011", + "min": 0 + } + ], + "cache_read": { + "tiers": [ + { + "cost": "0.000000275", + "min": 0 + } + ] + }, + "cache_write": { + "tiers": [ + { + "cost": "0.00001375", + "min": 0 + } + ] + }, + "cache_write_1h": { + "tiers": [ + { + "cost": "0.000022", + "min": 0 + } + ] + } + } + }, + "output": { + "search": { + "tiers": [ + { + "cost": "0.01", + "min": 0 + } + ], + "unit": "request" + }, + "text": { + "tiers": [ + { + "cost": "0.000055", + "min": 0 + } + ] + } + } + } + } + }, + "data_retention": "provider_retained", + "data_retention_by_surface": { + "messages": "provider_retained" + } + }, + { + "premium_output_modalities": [], + "id": "anthropic/claude-haiku-4-5", + "object": "model", + "created": 1789344000, + "released": 1760486400, + "expiration_date": null, + "deprecated": false, + "owned_by": "anthropic", + "name": "Claude Haiku 4.5", + "description": "Anthropic's fastest model for straightforward tasks.", + "context_window": 200000, + "max_tokens": 64000, + "knowledge": "2025-02", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text", + "search" + ] + }, + "supported_surfaces": [ + "messages" + ], + "pricing": { + "input": { + "image": { + "billed_as": "text" + }, + "text": { + "tiers": [ + { + "cost": "0.000001", + "min": 0 + } + ], + "cache_read": { + "tiers": [ + { + "cost": "0.0000001", + "min": 0 + } + ] + }, + "cache_write": { + "tiers": [ + { + "cost": "0.00000125", + "min": 0 + } + ] + }, + "cache_write_1h": { + "tiers": [ + { + "cost": "0.000002", + "min": 0 + } + ] + } + } + }, + "output": { + "search": { + "tiers": [ + { + "cost": "0.01", + "min": 0 + } + ], + "unit": "request" + }, + "text": { + "tiers": [ + { + "cost": "0.000005", + "min": 0 + } + ] + } + } + }, + "data_retention": "provider_retained", + "data_retention_by_surface": { + "messages": "provider_retained" + } + }, + { + "premium_output_modalities": [], + "id": "anthropic/claude-opus-5", + "object": "model", + "created": 1789344000, + "released": 1784851200, + "expiration_date": null, + "deprecated": false, + "owned_by": "anthropic", + "name": "Claude Opus 5", + "description": "Anthropic's model for complex coding and agent tasks.", + "context_window": 1000000, + "max_tokens": 128000, + "knowledge": "2026-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text", + "search" + ] + }, + "supported_surfaces": [ + "messages" + ], + "pricing": { + "input": { + "image": { + "billed_as": "text" + }, + "text": { + "tiers": [ + { + "cost": "0.000005", + "min": 0 + } + ], + "cache_read": { + "tiers": [ + { + "cost": "0.0000005", + "min": 0 + } + ] + }, + "cache_write": { + "tiers": [ + { + "cost": "0.00000625", + "min": 0 + } + ] + }, + "cache_write_1h": { + "tiers": [ + { + "cost": "0.00001", + "min": 0 + } + ] + } + } + }, + "output": { + "search": { + "tiers": [ + { + "cost": "0.01", + "min": 0 + } + ], + "unit": "request" + }, + "text": { + "tiers": [ + { + "cost": "0.000025", + "min": 0 + } + ] + } + }, + "service_tiers": { + "fast": { + "input": { + "image": { + "billed_as": "text" + }, + "text": { + "tiers": [ + { + "cost": "0.00001", + "min": 0 + } + ], + "cache_read": { + "tiers": [ + { + "cost": "0.000001", + "min": 0 + } + ] + }, + "cache_write": { + "tiers": [ + { + "cost": "0.0000125", + "min": 0 + } + ] + }, + "cache_write_1h": { + "tiers": [ + { + "cost": "0.00002", + "min": 0 + } + ] + } + } + }, + "output": { + "search": { + "tiers": [ + { + "cost": "0.01", + "min": 0 + } + ], + "unit": "request" + }, + "text": { + "tiers": [ + { + "cost": "0.00005", + "min": 0 + } + ] + } + } + }, + "fast_us": { + "input": { + "image": { + "billed_as": "text" + }, + "text": { + "tiers": [ + { + "cost": "0.000011", + "min": 0 + } + ], + "cache_read": { + "tiers": [ + { + "cost": "0.0000011", + "min": 0 + } + ] + }, + "cache_write": { + "tiers": [ + { + "cost": "0.00001375", + "min": 0 + } + ] + }, + "cache_write_1h": { + "tiers": [ + { + "cost": "0.000022", + "min": 0 + } + ] + } + } + }, + "output": { + "search": { + "tiers": [ + { + "cost": "0.01", + "min": 0 + } + ], + "unit": "request" + }, + "text": { + "tiers": [ + { + "cost": "0.000055", + "min": 0 + } + ] + } + } + }, + "us": { + "input": { + "image": { + "billed_as": "text" + }, + "text": { + "tiers": [ + { + "cost": "0.0000055", + "min": 0 + } + ], + "cache_read": { + "tiers": [ + { + "cost": "0.00000055", + "min": 0 + } + ] + }, + "cache_write": { + "tiers": [ + { + "cost": "0.000006875", + "min": 0 + } + ] + }, + "cache_write_1h": { + "tiers": [ + { + "cost": "0.000011", + "min": 0 + } + ] + } + } + }, + "output": { + "search": { + "tiers": [ + { + "cost": "0.01", + "min": 0 + } + ], + "unit": "request" + }, + "text": { + "tiers": [ + { + "cost": "0.0000275", + "min": 0 + } + ] + } + } + } + } + }, + "data_retention": "provider_retained", + "data_retention_by_surface": { + "messages": "provider_retained" + } + }, + { + "premium_output_modalities": [], + "id": "anthropic/claude-opus-5-5", + "object": "model", + "created": 1790035200, + "released": 1790035200, + "expiration_date": null, + "deprecated": false, + "owned_by": "anthropic", + "name": "Claude Opus 5.5", + "description": "Anthropic's model for long-running agentic coding and knowledge work.", + "context_window": 1000000, + "max_tokens": 128000, + "knowledge": "2026-06", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text", + "search" + ] + }, + "supported_surfaces": [ + "messages" + ], + "pricing": { + "input": { + "image": { + "billed_as": "text" + }, + "text": { + "tiers": [ + { + "cost": "0.000004", + "min": 0 + } + ], + "cache_read": { + "tiers": [ + { + "cost": "0.0000002", + "min": 0 + } + ] + }, + "cache_write": { + "tiers": [ + { + "cost": "0.000005", + "min": 0 + } + ] + }, + "cache_write_1h": { + "tiers": [ + { + "cost": "0.000008", + "min": 0 + } + ] + } + } + }, + "output": { + "search": { + "tiers": [ + { + "cost": "0.01", + "min": 0 + } + ], + "unit": "request" + }, + "text": { + "tiers": [ + { + "cost": "0.00002", + "min": 0 + } + ] + } + }, + "service_tiers": { + "fast": { + "input": { + "image": { + "billed_as": "text" + }, + "text": { + "tiers": [ + { + "cost": "0.000008", + "min": 0 + } + ], + "cache_read": { + "tiers": [ + { + "cost": "0.0000004", + "min": 0 + } + ] + }, + "cache_write": { + "tiers": [ + { + "cost": "0.00001", + "min": 0 + } + ] + }, + "cache_write_1h": { + "tiers": [ + { + "cost": "0.000016", + "min": 0 + } + ] + } + } + }, + "output": { + "search": { + "tiers": [ + { + "cost": "0.01", + "min": 0 + } + ], + "unit": "request" + }, + "text": { + "tiers": [ + { + "cost": "0.00004", + "min": 0 + } + ] + } + } + }, + "fast_us": { + "input": { + "image": { + "billed_as": "text" + }, + "text": { + "tiers": [ + { + "cost": "0.0000088", + "min": 0 + } + ], + "cache_read": { + "tiers": [ + { + "cost": "0.00000044", + "min": 0 + } + ] + }, + "cache_write": { + "tiers": [ + { + "cost": "0.000011", + "min": 0 + } + ] + }, + "cache_write_1h": { + "tiers": [ + { + "cost": "0.0000176", + "min": 0 + } + ] + } + } + }, + "output": { + "search": { + "tiers": [ + { + "cost": "0.01", + "min": 0 + } + ], + "unit": "request" + }, + "text": { + "tiers": [ + { + "cost": "0.000044", + "min": 0 + } + ] + } + } + }, + "us": { + "input": { + "image": { + "billed_as": "text" + }, + "text": { + "tiers": [ + { + "cost": "0.0000044", + "min": 0 + } + ], + "cache_read": { + "tiers": [ + { + "cost": "0.00000022", + "min": 0 + } + ] + }, + "cache_write": { + "tiers": [ + { + "cost": "0.0000055", + "min": 0 + } + ] + }, + "cache_write_1h": { + "tiers": [ + { + "cost": "0.0000088", + "min": 0 + } + ] + } + } + }, + "output": { + "search": { + "tiers": [ + { + "cost": "0.01", + "min": 0 + } + ], + "unit": "request" + }, + "text": { + "tiers": [ + { + "cost": "0.000022", + "min": 0 + } + ] + } + } + } + } + }, + "data_retention": "provider_retained", + "data_retention_by_surface": { + "messages": "provider_retained" + } + }, + { + "premium_output_modalities": [], + "id": "anthropic/claude-sonnet-5", + "object": "model", + "created": 1789344000, + "released": 1782777600, + "expiration_date": null, + "deprecated": false, + "owned_by": "anthropic", + "name": "Claude Sonnet 5", + "description": "Anthropic's model balancing speed and intelligence.", + "context_window": 1000000, + "max_tokens": 128000, + "knowledge": "2026-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text", + "search" + ] + }, + "supported_surfaces": [ + "messages" + ], + "pricing": { + "input": { + "image": { + "billed_as": "text" + }, + "text": { + "tiers": [ + { + "cost": "0.000002", + "min": 0 + } + ], + "cache_read": { + "tiers": [ + { + "cost": "0.0000002", + "min": 0 + } + ] + }, + "cache_write": { + "tiers": [ + { + "cost": "0.0000025", + "min": 0 + } + ] + }, + "cache_write_1h": { + "tiers": [ + { + "cost": "0.000004", + "min": 0 + } + ] + } + } + }, + "output": { + "search": { + "tiers": [ + { + "cost": "0.01", + "min": 0 + } + ], + "unit": "request" + }, + "text": { + "tiers": [ + { + "cost": "0.00001", + "min": 0 + } + ] + } + }, + "service_tiers": { + "us": { + "input": { + "image": { + "billed_as": "text" + }, + "text": { + "tiers": [ + { + "cost": "0.0000022", + "min": 0 + } + ], + "cache_read": { + "tiers": [ + { + "cost": "0.00000022", + "min": 0 + } + ] + }, + "cache_write": { + "tiers": [ + { + "cost": "0.00000275", + "min": 0 + } + ] + }, + "cache_write_1h": { + "tiers": [ + { + "cost": "0.0000044", + "min": 0 + } + ] + } + } + }, + "output": { + "search": { + "tiers": [ + { + "cost": "0.01", + "min": 0 + } + ], + "unit": "request" + }, + "text": { + "tiers": [ + { + "cost": "0.000011", + "min": 0 + } + ] + } + } + } + } + }, + "data_retention": "provider_retained", + "data_retention_by_surface": { + "messages": "provider_retained" + } + }, { "premium_output_modalities": [], "id": "google/gemini-2.5-flash", "object": "model", "created": 1779667200, "released": 1742428800, - "expiration_date": 1806451200, + "expiration_date": 1792454400, "deprecated": true, "owned_by": "google", "name": "Gemini 2.5 Flash", @@ -214,7 +1136,7 @@ "object": "model", "created": 1779667200, "released": 1750118400, - "expiration_date": 1801094400, + "expiration_date": 1792454400, "deprecated": true, "owned_by": "google", "name": "Gemini 2.5 Flash Lite", @@ -450,7 +1372,7 @@ "object": "model", "created": 1779667200, "released": 1742428800, - "expiration_date": 1806451200, + "expiration_date": 1792454400, "deprecated": true, "owned_by": "google", "name": "Gemini 2.5 Pro", @@ -908,7 +1830,7 @@ "created": 1782086400, "released": 1779926400, "expiration_date": null, - "deprecated": false, + "deprecated": true, "owned_by": "google", "name": "Gemini 3.1 Flash Image", "description": "Fast image generation and editing model with pro-level quality.", @@ -2034,6 +2956,87 @@ "interactions": "provider_retained" } }, + { + "premium_output_modalities": [], + "id": "google/gemini-4-argon", + "object": "model", + "created": 1791849600, + "released": 1791849600, + "expiration_date": null, + "deprecated": false, + "owned_by": "google", + "name": "Gemini 4 Argon", + "description": "Frontier Gemini model for long-horizon coding, reasoning, and enterprise knowledge work.", + "context_window": 1048576, + "max_tokens": 1048576, + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "supported_surfaces": [ + "chat-completions" + ], + "pricing": { + "input": { + "audio": { + "tiers": [ + { + "cost": "0.000002", + "min": 0 + } + ] + }, + "image": { + "billed_as": "text" + }, + "text": { + "tiers": [ + { + "cost": "0.000002", + "min": 0 + } + ], + "cache_read": { + "tiers": [ + { + "cost": "0.0000001", + "min": 0 + } + ] + } + }, + "video": { + "tiers": [ + { + "cost": "0.000002", + "min": 0 + } + ] + } + }, + "output": { + "text": { + "tiers": [ + { + "cost": "0.00001", + "min": 0 + } + ] + } + } + }, + "data_retention": "zero", + "data_retention_by_surface": { + "chat-completions": "zero" + } + }, { "premium_output_modalities": [], "id": "google/gemini-embedding-001", @@ -2222,6 +3225,92 @@ "videos": "provider_retained" } }, + { + "premium_output_modalities": [], + "id": "google/lyria-3-clip-preview", + "object": "model", + "created": 1790640000, + "released": 1774396800, + "expiration_date": null, + "deprecated": false, + "owned_by": "google", + "name": "Lyria 3 Clip Preview", + "description": "Generate 30-second music clips with vocals or instrumentals from text or images.", + "context_window": 0, + "max_tokens": 0, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "audio" + ] + }, + "supported_surfaces": [ + "music" + ], + "pricing": { + "output": { + "audio": { + "tiers": [ + { + "cost": "0.04", + "min": 0 + } + ], + "unit": "request" + } + } + }, + "data_retention": "zero", + "data_retention_by_surface": { + "music": "zero" + } + }, + { + "premium_output_modalities": [], + "id": "google/lyria-3-pro-preview", + "object": "model", + "created": 1790640000, + "released": 1774396800, + "expiration_date": null, + "deprecated": false, + "owned_by": "google", + "name": "Lyria 3 Pro Preview", + "description": "Generate full music tracks up to 184 seconds with vocals or instrumentals from text or images.", + "context_window": 0, + "max_tokens": 0, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "audio" + ] + }, + "supported_surfaces": [ + "music" + ], + "pricing": { + "output": { + "audio": { + "tiers": [ + { + "cost": "0.08", + "min": 0 + } + ], + "unit": "request" + } + } + }, + "data_retention": "zero", + "data_retention_by_surface": { + "music": "zero" + } + }, { "premium_output_modalities": [ "video" @@ -2421,8 +3510,8 @@ "object": "model", "created": 1781568000, "released": 1742428800, - "expiration_date": null, - "deprecated": false, + "expiration_date": 1803600000, + "deprecated": true, "owned_by": "openai", "name": "GPT-4o mini Transcribe", "description": "Fast, cost-efficient OpenAI speech-to-text model for dictation, voice input, and high-volume transcription.", @@ -2481,8 +3570,8 @@ "object": "model", "created": 1781568000, "released": 1742428800, - "expiration_date": null, - "deprecated": false, + "expiration_date": 1799193600, + "deprecated": true, "owned_by": "openai", "name": "GPT-4o mini TTS", "description": "OpenAI text-to-speech model with instructions-steerable delivery (tone, accent, pacing) for natural-sounding audio.", @@ -2534,8 +3623,8 @@ "object": "model", "created": 1781654400, "released": 1742428800, - "expiration_date": null, - "deprecated": false, + "expiration_date": 1803600000, + "deprecated": true, "owned_by": "openai", "name": "GPT-4o Transcribe", "description": "Higher-accuracy OpenAI speech-to-text model for noisy audio, accents, and specialist vocabulary.", @@ -2579,29 +3668,130 @@ "cost": "0.00001", "min": 0 } - ] + ] + } + } + }, + "data_retention": "zero", + "data_retention_by_surface": { + "transcription": "zero" + } + }, + { + "premium_output_modalities": [], + "id": "openai/gpt-5", + "object": "model", + "created": 1779667200, + "released": 1754524800, + "expiration_date": 1796947200, + "deprecated": true, + "owned_by": "openai", + "name": "GPT-5", + "description": "Powerful all-rounder for reasoning, long-context, and multimodal tasks.", + "context_window": 400000, + "max_tokens": 128000, + "knowledge": "2024-09-30", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "supported_surfaces": [ + "chat-completions", + "responses" + ], + "pricing": { + "input": { + "image": { + "billed_as": "text" + }, + "text": { + "tiers": [ + { + "cost": "0.00000125", + "min": 0 + } + ], + "cache_read": { + "tiers": [ + { + "cost": "0.000000125", + "min": 0 + } + ] + } + } + }, + "output": { + "text": { + "tiers": [ + { + "cost": "0.00001", + "min": 0 + } + ] + } + }, + "service_tiers": { + "priority": { + "input": { + "image": { + "billed_as": "text" + }, + "text": { + "tiers": [ + { + "cost": "0.0000025", + "min": 0 + } + ], + "cache_read": { + "tiers": [ + { + "cost": "0.00000025", + "min": 0 + } + ] + } + } + }, + "output": { + "text": { + "tiers": [ + { + "cost": "0.00002", + "min": 0 + } + ] + } + } } } }, "data_retention": "zero", "data_retention_by_surface": { - "transcription": "zero" + "chat-completions": "zero", + "responses": "zero" } }, { "premium_output_modalities": [], - "id": "openai/gpt-5", + "id": "openai/gpt-5-mini", "object": "model", "created": 1779667200, "released": 1754524800, - "expiration_date": null, + "expiration_date": 1796947200, "deprecated": true, "owned_by": "openai", - "name": "GPT-5", - "description": "Powerful all-rounder for reasoning, long-context, and multimodal tasks.", + "name": "GPT-5 mini", + "description": "Smaller, faster GPT-5 model for efficient tasks.", "context_window": 400000, "max_tokens": 128000, - "knowledge": "2024-09-30", + "knowledge": "2024-05-30", "modalities": { "input": [ "text", @@ -2623,14 +3813,14 @@ "text": { "tiers": [ { - "cost": "0.00000125", + "cost": "0.00000025", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.000000125", + "cost": "0.000000025", "min": 0 } ] @@ -2641,7 +3831,7 @@ "text": { "tiers": [ { - "cost": "0.00001", + "cost": "0.000002", "min": 0 } ] @@ -2656,14 +3846,14 @@ "text": { "tiers": [ { - "cost": "0.0000025", + "cost": "0.00000045", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.00000025", + "cost": "0.000000045", "min": 0 } ] @@ -2674,7 +3864,7 @@ "text": { "tiers": [ { - "cost": "0.00002", + "cost": "0.0000036", "min": 0 } ] @@ -2691,15 +3881,15 @@ }, { "premium_output_modalities": [], - "id": "openai/gpt-5-mini", + "id": "openai/gpt-5-nano", "object": "model", "created": 1779667200, "released": 1754524800, - "expiration_date": null, + "expiration_date": 1796947200, "deprecated": true, "owned_by": "openai", - "name": "GPT-5 mini", - "description": "Smaller, faster GPT-5 model for efficient tasks.", + "name": "GPT-5 nano", + "description": "Most compact GPT-5 model for speed and cost efficiency.", "context_window": 400000, "max_tokens": 128000, "knowledge": "2024-05-30", @@ -2724,14 +3914,14 @@ "text": { "tiers": [ { - "cost": "0.00000025", + "cost": "0.00000005", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.000000025", + "cost": "0.000000005", "min": 0 } ] @@ -2742,7 +3932,73 @@ "text": { "tiers": [ { - "cost": "0.000002", + "cost": "0.0000004", + "min": 0 + } + ] + } + } + }, + "data_retention": "zero", + "data_retention_by_surface": { + "chat-completions": "zero", + "responses": "zero" + } + }, + { + "premium_output_modalities": [], + "id": "openai/gpt-5.2", + "object": "model", + "created": 1779667200, + "released": 1765411200, + "expiration_date": null, + "deprecated": true, + "owned_by": "openai", + "name": "GPT-5.2", + "description": "OpenAI reasoning model for complex problem-solving tasks.", + "context_window": 400000, + "max_tokens": 128000, + "knowledge": "2024-10", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "supported_surfaces": [ + "chat-completions", + "responses" + ], + "pricing": { + "input": { + "image": { + "billed_as": "text" + }, + "text": { + "tiers": [ + { + "cost": "0.00000175", + "min": 0 + } + ], + "cache_read": { + "tiers": [ + { + "cost": "0.000000175", + "min": 0 + } + ] + } + } + }, + "output": { + "text": { + "tiers": [ + { + "cost": "0.000014", "min": 0 } ] @@ -2757,14 +4013,14 @@ "text": { "tiers": [ { - "cost": "0.00000045", + "cost": "0.0000035", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.000000045", + "cost": "0.00000035", "min": 0 } ] @@ -2775,7 +4031,7 @@ "text": { "tiers": [ { - "cost": "0.0000036", + "cost": "0.000028", "min": 0 } ] @@ -2792,18 +4048,18 @@ }, { "premium_output_modalities": [], - "id": "openai/gpt-5-nano", + "id": "openai/gpt-5.4", "object": "model", "created": 1779667200, - "released": 1754524800, + "released": 1772668800, "expiration_date": null, "deprecated": false, "owned_by": "openai", - "name": "GPT-5 nano", - "description": "Most compact GPT-5 model for speed and cost efficiency.", - "context_window": 400000, + "name": "GPT-5.4", + "description": "Advanced GPT-5.4 reasoning model for complex analysis and code generation.", + "context_window": 1050000, "max_tokens": 128000, - "knowledge": "2024-05-30", + "knowledge": "2025-08-31", "modalities": { "input": [ "text", @@ -2825,15 +4081,25 @@ "text": { "tiers": [ { - "cost": "0.00000005", - "min": 0 + "cost": "0.0000025", + "min": 0, + "max": 272000 + }, + { + "cost": "0.000005", + "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.000000005", - "min": 0 + "cost": "0.00000025", + "min": 0, + "max": 272000 + }, + { + "cost": "0.0000005", + "min": 272000 } ] } @@ -2843,11 +4109,51 @@ "text": { "tiers": [ { - "cost": "0.0000004", - "min": 0 + "cost": "0.000015", + "min": 0, + "max": 272000 + }, + { + "cost": "0.0000225", + "min": 272000 } ] } + }, + "service_tiers": { + "priority": { + "input": { + "image": { + "billed_as": "text" + }, + "text": { + "tiers": [ + { + "cost": "0.000005", + "min": 0 + } + ], + "cache_read": { + "tiers": [ + { + "cost": "0.0000005", + "min": 0 + } + ] + } + } + }, + "output": { + "text": { + "tiers": [ + { + "cost": "0.00003", + "min": 0 + } + ] + } + } + } } }, "data_retention": "zero", @@ -2858,18 +4164,18 @@ }, { "premium_output_modalities": [], - "id": "openai/gpt-5.2", + "id": "openai/gpt-5.4-mini", "object": "model", "created": 1779667200, - "released": 1765411200, + "released": 1773705600, "expiration_date": null, - "deprecated": true, + "deprecated": false, "owned_by": "openai", - "name": "GPT-5.2", - "description": "OpenAI reasoning model for complex problem-solving tasks.", + "name": "GPT-5.4 Mini", + "description": "Smaller, faster GPT-5.4 variant balancing reasoning quality and cost.", "context_window": 400000, "max_tokens": 128000, - "knowledge": "2024-10", + "knowledge": "2025-08-31", "modalities": { "input": [ "text", @@ -2891,14 +4197,14 @@ "text": { "tiers": [ { - "cost": "0.00000175", + "cost": "0.00000075", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.000000175", + "cost": "0.000000075", "min": 0 } ] @@ -2909,7 +4215,7 @@ "text": { "tiers": [ { - "cost": "0.000014", + "cost": "0.0000045", "min": 0 } ] @@ -2924,14 +4230,14 @@ "text": { "tiers": [ { - "cost": "0.0000035", + "cost": "0.0000015", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.00000035", + "cost": "0.00000015", "min": 0 } ] @@ -2942,7 +4248,7 @@ "text": { "tiers": [ { - "cost": "0.000028", + "cost": "0.000009", "min": 0 } ] @@ -2959,15 +4265,81 @@ }, { "premium_output_modalities": [], - "id": "openai/gpt-5.4", + "id": "openai/gpt-5.4-nano", + "object": "model", + "created": 1779667200, + "released": 1773705600, + "expiration_date": 1806537600, + "deprecated": true, + "owned_by": "openai", + "name": "GPT-5.4 Nano", + "description": "Fastest and lowest-cost GPT-5.4 variant for high-volume tasks.", + "context_window": 400000, + "max_tokens": 128000, + "knowledge": "2025-08-31", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "supported_surfaces": [ + "chat-completions", + "responses" + ], + "pricing": { + "input": { + "image": { + "billed_as": "text" + }, + "text": { + "tiers": [ + { + "cost": "0.0000002", + "min": 0 + } + ], + "cache_read": { + "tiers": [ + { + "cost": "0.00000002", + "min": 0 + } + ] + } + } + }, + "output": { + "text": { + "tiers": [ + { + "cost": "0.00000125", + "min": 0 + } + ] + } + } + }, + "data_retention": "zero", + "data_retention_by_surface": { + "chat-completions": "zero", + "responses": "zero" + } + }, + { + "premium_output_modalities": [], + "id": "openai/gpt-5.4-pro", "object": "model", "created": 1779667200, "released": 1772668800, "expiration_date": null, - "deprecated": false, + "deprecated": true, "owned_by": "openai", - "name": "GPT-5.4", - "description": "Advanced GPT-5.4 reasoning model for complex analysis and code generation.", + "name": "GPT-5.4 Pro", + "description": "Premium GPT-5.4 variant with enhanced reasoning for complex tasks.", "context_window": 1050000, "max_tokens": 128000, "knowledge": "2025-08-31", @@ -2981,7 +4353,6 @@ ] }, "supported_surfaces": [ - "chat-completions", "responses" ], "pricing": { @@ -2992,24 +4363,24 @@ "text": { "tiers": [ { - "cost": "0.0000025", + "cost": "0.00003", "min": 0, "max": 272000 }, { - "cost": "0.000005", + "cost": "0.00006", "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.00000025", + "cost": "0.000003", "min": 0, "max": 272000 }, { - "cost": "0.0000005", + "cost": "0.000006", "min": 272000 } ] @@ -3020,73 +4391,39 @@ "text": { "tiers": [ { - "cost": "0.000015", + "cost": "0.00018", "min": 0, "max": 272000 }, { - "cost": "0.0000225", + "cost": "0.00027", "min": 272000 } ] } - }, - "service_tiers": { - "priority": { - "input": { - "image": { - "billed_as": "text" - }, - "text": { - "tiers": [ - { - "cost": "0.000005", - "min": 0 - } - ], - "cache_read": { - "tiers": [ - { - "cost": "0.0000005", - "min": 0 - } - ] - } - } - }, - "output": { - "text": { - "tiers": [ - { - "cost": "0.00003", - "min": 0 - } - ] - } - } - } } }, "data_retention": "zero", "data_retention_by_surface": { - "chat-completions": "zero", "responses": "zero" } }, { - "premium_output_modalities": [], - "id": "openai/gpt-5.4-mini", + "premium_output_modalities": [ + "text" + ], + "id": "openai/gpt-5.5", "object": "model", "created": 1779667200, - "released": 1773705600, + "released": 1776988800, "expiration_date": null, "deprecated": false, "owned_by": "openai", - "name": "GPT-5.4 Mini", - "description": "Smaller, faster GPT-5.4 variant balancing reasoning quality and cost.", - "context_window": 400000, + "name": "GPT-5.5", + "description": "OpenAI's most capable GPT-5.5 model for demanding reasoning and coding tasks.", + "context_window": 1000000, "max_tokens": 128000, - "knowledge": "2025-08-31", + "knowledge": "2025-12-01", "modalities": { "input": [ "text", @@ -3108,15 +4445,25 @@ "text": { "tiers": [ { - "cost": "0.00000075", - "min": 0 + "cost": "0.000005", + "min": 0, + "max": 272000 + }, + { + "cost": "0.00001", + "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.000000075", - "min": 0 + "cost": "0.0000005", + "min": 0, + "max": 272000 + }, + { + "cost": "0.000001", + "min": 272000 } ] } @@ -3126,8 +4473,13 @@ "text": { "tiers": [ { - "cost": "0.0000045", - "min": 0 + "cost": "0.00003", + "min": 0, + "max": 272000 + }, + { + "cost": "0.000045", + "min": 272000 } ] } @@ -3141,14 +4493,14 @@ "text": { "tiers": [ { - "cost": "0.0000015", + "cost": "0.0000125", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.00000015", + "cost": "0.00000125", "min": 0 } ] @@ -3159,7 +4511,7 @@ "text": { "tiers": [ { - "cost": "0.000009", + "cost": "0.000075", "min": 0 } ] @@ -3176,18 +4528,18 @@ }, { "premium_output_modalities": [], - "id": "openai/gpt-5.4-nano", + "id": "openai/gpt-5.5-pro", "object": "model", - "created": 1779667200, - "released": 1773705600, + "created": 1783382400, + "released": 1776988800, "expiration_date": null, "deprecated": false, "owned_by": "openai", - "name": "GPT-5.4 Nano", - "description": "Fastest and lowest-cost GPT-5.4 variant for high-volume tasks.", - "context_window": 400000, + "name": "GPT-5.5 Pro", + "description": "Premium GPT-5.5 variant with extended reasoning for the hardest problems.", + "context_window": 1000000, "max_tokens": 128000, - "knowledge": "2025-08-31", + "knowledge": "2025-12-01", "modalities": { "input": [ "text", @@ -3198,7 +4550,6 @@ ] }, "supported_surfaces": [ - "chat-completions", "responses" ], "pricing": { @@ -3209,15 +4560,25 @@ "text": { "tiers": [ { - "cost": "0.0000002", - "min": 0 + "cost": "0.00003", + "min": 0, + "max": 272000 + }, + { + "cost": "0.00006", + "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.00000002", - "min": 0 + "cost": "0.00003", + "min": 0, + "max": 272000 + }, + { + "cost": "0.00006", + "min": 272000 } ] } @@ -3227,8 +4588,13 @@ "text": { "tiers": [ { - "cost": "0.00000125", - "min": 0 + "cost": "0.00018", + "min": 0, + "max": 272000 + }, + { + "cost": "0.00027", + "min": 272000 } ] } @@ -3236,24 +4602,23 @@ }, "data_retention": "zero", "data_retention_by_surface": { - "chat-completions": "zero", "responses": "zero" } }, { "premium_output_modalities": [], - "id": "openai/gpt-5.4-pro", + "id": "openai/gpt-5.6-luna", "object": "model", - "created": 1779667200, - "released": 1772668800, + "created": 1784073600, + "released": 1783555200, "expiration_date": null, - "deprecated": true, + "deprecated": false, "owned_by": "openai", - "name": "GPT-5.4 Pro", - "description": "Premium GPT-5.4 variant with enhanced reasoning for complex tasks.", + "name": "GPT-5.6 Luna", + "description": "Fast, low-cost GPT-5.6 model for simple or high-volume tasks.", "context_window": 1050000, "max_tokens": 128000, - "knowledge": "2025-08-31", + "knowledge": "2026-02-16", "modalities": { "input": [ "text", @@ -3264,6 +4629,7 @@ ] }, "supported_surfaces": [ + "chat-completions", "responses" ], "pricing": { @@ -3274,24 +4640,24 @@ "text": { "tiers": [ { - "cost": "0.00003", + "cost": "0.0000002", "min": 0, "max": 272000 }, { - "cost": "0.00006", + "cost": "0.0000004", "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.000003", + "cost": "0.00000002", "min": 0, "max": 272000 }, { - "cost": "0.000006", + "cost": "0.00000004", "min": 272000 } ] @@ -3302,20 +4668,71 @@ "text": { "tiers": [ { - "cost": "0.00018", + "cost": "0.0000012", "min": 0, "max": 272000 }, { - "cost": "0.00027", + "cost": "0.0000018", "min": 272000 } ] } + }, + "service_tiers": { + "priority": { + "input": { + "image": { + "billed_as": "text" + }, + "text": { + "tiers": [ + { + "cost": "0.0000004", + "min": 0, + "max": 272000 + }, + { + "cost": "0.0000008", + "min": 272000 + } + ], + "cache_read": { + "tiers": [ + { + "cost": "0.00000004", + "min": 0, + "max": 272000 + }, + { + "cost": "0.00000008", + "min": 272000 + } + ] + } + } + }, + "output": { + "text": { + "tiers": [ + { + "cost": "0.0000024", + "min": 0, + "max": 272000 + }, + { + "cost": "0.0000036", + "min": 272000 + } + ] + } + } + } } }, "data_retention": "zero", "data_retention_by_surface": { + "chat-completions": "zero", "responses": "zero" } }, @@ -3323,18 +4740,18 @@ "premium_output_modalities": [ "text" ], - "id": "openai/gpt-5.5", - "object": "model", - "created": 1779667200, - "released": 1776988800, + "id": "openai/gpt-5.6-sol", + "object": "model", + "created": 1783987200, + "released": 1783555200, "expiration_date": null, "deprecated": false, "owned_by": "openai", - "name": "GPT-5.5", - "description": "OpenAI's most capable GPT-5.5 model for demanding reasoning and coding tasks.", - "context_window": 1000000, + "name": "GPT-5.6 Sol", + "description": "OpenAI's flagship GPT-5.6 model for the hardest reasoning, coding, and agentic tasks.", + "context_window": 1050000, "max_tokens": 128000, - "knowledge": "2025-12-01", + "knowledge": "2026-02-16", "modalities": { "input": [ "text", @@ -3356,24 +4773,24 @@ "text": { "tiers": [ { - "cost": "0.000005", + "cost": "0.000004", "min": 0, "max": 272000 }, { - "cost": "0.00001", + "cost": "0.000008", "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.0000005", + "cost": "0.0000004", "min": 0, "max": 272000 }, { - "cost": "0.000001", + "cost": "0.0000008", "min": 272000 } ] @@ -3384,12 +4801,12 @@ "text": { "tiers": [ { - "cost": "0.00003", + "cost": "0.00002", "min": 0, "max": 272000 }, { - "cost": "0.000045", + "cost": "0.00003", "min": 272000 } ] @@ -3404,15 +4821,25 @@ "text": { "tiers": [ { - "cost": "0.0000125", - "min": 0 + "cost": "0.000008", + "min": 0, + "max": 272000 + }, + { + "cost": "0.000016", + "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.00000125", - "min": 0 + "cost": "0.0000008", + "min": 0, + "max": 272000 + }, + { + "cost": "0.0000016", + "min": 272000 } ] } @@ -3422,8 +4849,13 @@ "text": { "tiers": [ { - "cost": "0.000075", - "min": 0 + "cost": "0.00004", + "min": 0, + "max": 272000 + }, + { + "cost": "0.00006", + "min": 272000 } ] } @@ -3439,18 +4871,18 @@ }, { "premium_output_modalities": [], - "id": "openai/gpt-5.5-pro", + "id": "openai/gpt-5.6-terra", "object": "model", - "created": 1783382400, - "released": 1776988800, + "created": 1784073600, + "released": 1783555200, "expiration_date": null, "deprecated": false, "owned_by": "openai", - "name": "GPT-5.5 Pro", - "description": "Premium GPT-5.5 variant with extended reasoning for the hardest problems.", - "context_window": 1000000, + "name": "GPT-5.6 Terra", + "description": "Balanced GPT-5.6 model for everyday work at lower cost.", + "context_window": 1050000, "max_tokens": 128000, - "knowledge": "2025-12-01", + "knowledge": "2026-02-16", "modalities": { "input": [ "text", @@ -3461,6 +4893,7 @@ ] }, "supported_surfaces": [ + "chat-completions", "responses" ], "pricing": { @@ -3471,24 +4904,24 @@ "text": { "tiers": [ { - "cost": "0.00003", + "cost": "0.000002", "min": 0, "max": 272000 }, { - "cost": "0.00006", + "cost": "0.000004", "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.000003", + "cost": "0.0000002", "min": 0, "max": 272000 }, { - "cost": "0.000006", + "cost": "0.0000004", "min": 272000 } ] @@ -3499,37 +4932,90 @@ "text": { "tiers": [ { - "cost": "0.00018", + "cost": "0.000012", "min": 0, "max": 272000 }, { - "cost": "0.00027", + "cost": "0.000018", "min": 272000 } ] } + }, + "service_tiers": { + "priority": { + "input": { + "image": { + "billed_as": "text" + }, + "text": { + "tiers": [ + { + "cost": "0.000004", + "min": 0, + "max": 272000 + }, + { + "cost": "0.000008", + "min": 272000 + } + ], + "cache_read": { + "tiers": [ + { + "cost": "0.0000004", + "min": 0, + "max": 272000 + }, + { + "cost": "0.0000008", + "min": 272000 + } + ] + } + } + }, + "output": { + "text": { + "tiers": [ + { + "cost": "0.000024", + "min": 0, + "max": 272000 + }, + { + "cost": "0.000036", + "min": 272000 + } + ] + } + } + } } }, "data_retention": "zero", "data_retention_by_surface": { + "chat-completions": "zero", "responses": "zero" } }, { - "premium_output_modalities": [], - "id": "openai/gpt-5.6-luna", + "premium_output_modalities": [ + "text" + ], + "id": "openai/gpt-6-astra", "object": "model", - "created": 1784073600, - "released": 1783555200, + "created": 1788739200, + "released": 1788480000, "expiration_date": null, "deprecated": false, "owned_by": "openai", - "name": "GPT-5.6 Luna", - "description": "Fast, low-cost GPT-5.6 model for simple or high-volume tasks.", + "name": "GPT-6 Astra", + "description": "OpenAI's most capable model for complex reasoning, coding, research, and document creation.", "context_window": 1050000, "max_tokens": 128000, - "knowledge": "2026-02-16", + "knowledge": "2026-04-30", "modalities": { "input": [ "text", @@ -3551,24 +5037,37 @@ "text": { "tiers": [ { - "cost": "0.0000002", + "cost": "0.00001", "min": 0, "max": 272000 }, { - "cost": "0.0000004", + "cost": "0.00002", "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.00000002", + "cost": "0.000001", "min": 0, "max": 272000 }, { - "cost": "0.00000004", + "cost": "0.000002", + "min": 272000 + } + ] + }, + "cache_write": { + "tiers": [ + { + "cost": "0.0000125", + "min": 0, + "max": 272000 + }, + { + "cost": "0.000025", "min": 272000 } ] @@ -3579,12 +5078,12 @@ "text": { "tiers": [ { - "cost": "0.0000012", + "cost": "0.00005", "min": 0, "max": 272000 }, { - "cost": "0.0000018", + "cost": "0.000075", "min": 272000 } ] @@ -3599,15 +5098,38 @@ "text": { "tiers": [ { - "cost": "0.0000004", - "min": 0 + "cost": "0.00002", + "min": 0, + "max": 272000 + }, + { + "cost": "0.00004", + "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.00000004", - "min": 0 + "cost": "0.000002", + "min": 0, + "max": 272000 + }, + { + "cost": "0.000004", + "min": 272000 + } + ] + }, + "cache_write": { + "tiers": [ + { + "cost": "0.000025", + "min": 0, + "max": 272000 + }, + { + "cost": "0.00005", + "min": 272000 } ] } @@ -3617,8 +5139,13 @@ "text": { "tiers": [ { - "cost": "0.0000024", - "min": 0 + "cost": "0.0001", + "min": 0, + "max": 272000 + }, + { + "cost": "0.00015", + "min": 272000 } ] } @@ -3633,21 +5160,19 @@ } }, { - "premium_output_modalities": [ - "text" - ], - "id": "openai/gpt-5.6-sol", + "premium_output_modalities": [], + "id": "openai/gpt-6-luna", "object": "model", - "created": 1783987200, - "released": 1783555200, + "created": 1790035200, + "released": 1790035200, "expiration_date": null, "deprecated": false, "owned_by": "openai", - "name": "GPT-5.6 Sol", - "description": "OpenAI's flagship GPT-5.6 model for the hardest reasoning, coding, and agentic tasks.", + "name": "GPT-6 Luna", + "description": "Low-cost GPT-6 model from OpenAI.", "context_window": 1050000, "max_tokens": 128000, - "knowledge": "2026-02-16", + "knowledge": "2026-05-18", "modalities": { "input": [ "text", @@ -3669,24 +5194,24 @@ "text": { "tiers": [ { - "cost": "0.000004", + "cost": "0.0000001", "min": 0, "max": 272000 }, { - "cost": "0.000008", + "cost": "0.0000002", "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.0000004", + "cost": "0.00000001", "min": 0, "max": 272000 }, { - "cost": "0.0000008", + "cost": "0.00000002", "min": 272000 } ] @@ -3697,12 +5222,12 @@ "text": { "tiers": [ { - "cost": "0.00002", + "cost": "0.0000005", "min": 0, "max": 272000 }, { - "cost": "0.00003", + "cost": "0.00000075", "min": 272000 } ] @@ -3717,15 +5242,25 @@ "text": { "tiers": [ { - "cost": "0.000008", - "min": 0 + "cost": "0.0000002", + "min": 0, + "max": 272000 + }, + { + "cost": "0.0000004", + "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.0000008", - "min": 0 + "cost": "0.00000002", + "min": 0, + "max": 272000 + }, + { + "cost": "0.00000004", + "min": 272000 } ] } @@ -3735,8 +5270,13 @@ "text": { "tiers": [ { - "cost": "0.00004", - "min": 0 + "cost": "0.000001", + "min": 0, + "max": 272000 + }, + { + "cost": "0.0000015", + "min": 272000 } ] } @@ -3752,18 +5292,18 @@ }, { "premium_output_modalities": [], - "id": "openai/gpt-5.6-terra", + "id": "openai/gpt-6-sol", "object": "model", - "created": 1784073600, - "released": 1783555200, + "created": 1790035200, + "released": 1790035200, "expiration_date": null, "deprecated": false, "owned_by": "openai", - "name": "GPT-5.6 Terra", - "description": "Balanced GPT-5.6 model for everyday work at lower cost.", + "name": "GPT-6 Sol", + "description": "Mid-tier GPT-6 model from OpenAI.", "context_window": 1050000, "max_tokens": 128000, - "knowledge": "2026-02-16", + "knowledge": "2026-04-20", "modalities": { "input": [ "text", @@ -3813,12 +5353,12 @@ "text": { "tiers": [ { - "cost": "0.000012", + "cost": "0.00001", "min": 0, "max": 272000 }, { - "cost": "0.000018", + "cost": "0.000015", "min": 272000 } ] @@ -3834,14 +5374,24 @@ "tiers": [ { "cost": "0.000004", - "min": 0 + "min": 0, + "max": 272000 + }, + { + "cost": "0.000008", + "min": 272000 } ], "cache_read": { "tiers": [ { "cost": "0.0000004", - "min": 0 + "min": 0, + "max": 272000 + }, + { + "cost": "0.0000008", + "min": 272000 } ] } @@ -3851,8 +5401,13 @@ "text": { "tiers": [ { - "cost": "0.000024", - "min": 0 + "cost": "0.00002", + "min": 0, + "max": 272000 + }, + { + "cost": "0.00003", + "min": 272000 } ] } @@ -3867,18 +5422,16 @@ } }, { - "premium_output_modalities": [ - "text" - ], - "id": "openai/gpt-6-astra", + "premium_output_modalities": [], + "id": "openai/gpt-6.1-sol", "object": "model", - "created": 1788739200, - "released": 1788480000, + "created": 1791936000, + "released": 1790640000, "expiration_date": null, "deprecated": false, "owned_by": "openai", - "name": "GPT-6 Astra", - "description": "OpenAI's most capable model for complex reasoning, coding, research, and document creation.", + "name": "GPT-6.1 Sol", + "description": "Near-Astra performance for complex coding and professional work. Use Responses for tool calling; Chat Completions supports requests without tools.", "context_window": 1050000, "max_tokens": 128000, "knowledge": "2026-04-30", @@ -3903,24 +5456,24 @@ "text": { "tiers": [ { - "cost": "0.00001", + "cost": "0.000002", "min": 0, "max": 272000 }, { - "cost": "0.00002", + "cost": "0.000004", "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.000001", + "cost": "0.0000001", "min": 0, "max": 272000 }, { - "cost": "0.000002", + "cost": "0.0000002", "min": 272000 } ] @@ -3928,12 +5481,12 @@ "cache_write": { "tiers": [ { - "cost": "0.0000125", + "cost": "0.0000025", "min": 0, "max": 272000 }, { - "cost": "0.000025", + "cost": "0.000005", "min": 272000 } ] @@ -3944,12 +5497,12 @@ "text": { "tiers": [ { - "cost": "0.00005", + "cost": "0.00001", "min": 0, "max": 272000 }, { - "cost": "0.000075", + "cost": "0.000015", "min": 272000 } ] @@ -3964,24 +5517,24 @@ "text": { "tiers": [ { - "cost": "0.00002", + "cost": "0.000004", "min": 0, "max": 272000 }, { - "cost": "0.00004", + "cost": "0.000008", "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.000002", + "cost": "0.0000002", "min": 0, "max": 272000 }, { - "cost": "0.000004", + "cost": "0.0000004", "min": 272000 } ] @@ -3989,12 +5542,12 @@ "cache_write": { "tiers": [ { - "cost": "0.000025", + "cost": "0.000005", "min": 0, "max": 272000 }, { - "cost": "0.00005", + "cost": "0.00001", "min": 272000 } ] @@ -4005,12 +5558,12 @@ "text": { "tiers": [ { - "cost": "0.0001", + "cost": "0.00002", "min": 0, "max": 272000 }, { - "cost": "0.00015", + "cost": "0.00003", "min": 272000 } ] @@ -4031,7 +5584,7 @@ "object": "model", "created": 1779753600, "released": 1759708800, - "expiration_date": null, + "expiration_date": 1796083200, "deprecated": true, "owned_by": "openai", "name": "GPT Image 1 Mini", @@ -4151,6 +5704,177 @@ "image-generation": "zero" } }, + { + "premium_output_modalities": [], + "id": "openai/gpt-image-2.5-flare", + "object": "model", + "created": 1788912000, + "released": 1788825600, + "expiration_date": null, + "deprecated": false, + "owned_by": "openai", + "name": "GPT Image 2.5 Flare", + "description": "Latency-first OpenAI image generation and editing model.", + "context_window": 0, + "max_tokens": 0, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "image" + ] + }, + "supported_surfaces": [ + "image-generation", + "image-edit" + ], + "pricing": { + "input": { + "image": { + "tiers": [ + { + "cost": "0.000008", + "min": 0 + } + ] + }, + "text": { + "tiers": [ + { + "cost": "0.000005", + "min": 0 + } + ] + } + }, + "output": { + "image": { + "tiers": [ + { + "cost": "0.00003", + "min": 0 + } + ] + } + } + }, + "data_retention": "zero", + "data_retention_by_surface": { + "image-edit": "zero", + "image-generation": "zero" + } + }, + { + "premium_output_modalities": [ + "image" + ], + "id": "openai/gpt-image-2.5-sunburst", + "object": "model", + "created": 1788912000, + "released": 1788825600, + "expiration_date": null, + "deprecated": false, + "owned_by": "openai", + "name": "GPT Image 2.5 Sunburst", + "description": "Quality-first OpenAI image generation and editing model.", + "context_window": 0, + "max_tokens": 0, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "image" + ] + }, + "supported_surfaces": [ + "image-generation", + "image-edit" + ], + "pricing": { + "input": { + "image": { + "tiers": [ + { + "cost": "0.000008", + "min": 0 + } + ] + }, + "text": { + "tiers": [ + { + "cost": "0.000005", + "min": 0 + } + ] + } + }, + "output": { + "image": { + "tiers": [ + { + "cost": "0.00003", + "min": 0 + } + ] + } + } + }, + "data_retention": "zero", + "data_retention_by_surface": { + "image-edit": "zero", + "image-generation": "zero" + } + }, + { + "premium_output_modalities": [], + "id": "openai/gpt-live-1", + "object": "model", + "created": 1789344000, + "released": 1788998400, + "expiration_date": null, + "deprecated": false, + "owned_by": "openai", + "name": "GPT-Live 1", + "description": "Low-latency voice conversations with interruptions and client delegation.", + "context_window": 0, + "max_tokens": 0, + "knowledge": "2025-07-31", + "modalities": { + "input": [ + "text", + "audio" + ], + "output": [ + "text", + "audio" + ] + }, + "supported_surfaces": [ + "live" + ], + "pricing": { + "output": { + "audio": { + "tiers": [ + { + "cost": "0.000833333", + "min": 0 + } + ], + "unit": "second" + } + } + }, + "data_retention": "zero", + "data_retention_by_surface": { + "live": "zero" + } + }, { "premium_output_modalities": [ "text" @@ -4279,5 +6003,56 @@ "data_retention_by_surface": { "embeddings": "zero" } + }, + { + "premium_output_modalities": [], + "id": "typesafe/jev-1.13", + "object": "model", + "created": 1789689600, + "released": 1789689600, + "expiration_date": null, + "deprecated": false, + "owned_by": "typesafe", + "name": "Jev 1.13", + "description": "Structured decisions from state and typed questions, returning probabilities for classification, scoring, and routing.", + "context_window": 32000, + "max_tokens": 0, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "supported_surfaces": [ + "systemone" + ], + "pricing": { + "input": { + "text": { + "tiers": [ + { + "cost": "0.000000042", + "min": 0 + } + ] + } + }, + "output": { + "text": { + "tiers": [ + { + "cost": "0", + "min": 0 + } + ] + } + } + }, + "data_retention": "zero", + "data_retention_by_surface": { + "systemone": "zero" + } } ] diff --git a/scripts/openrouter.models.json b/scripts/openrouter.models.json index c19243c4b7..2b76e96661 100644 --- a/scripts/openrouter.models.json +++ b/scripts/openrouter.models.json @@ -62,14 +62,14 @@ "id": "~anthropic/claude-haiku-latest", "canonical_slug": "~anthropic/claude-haiku-latest", "alias_target": { - "name": "Anthropic: Claude Haiku 4.5", - "slug": "anthropic/claude-haiku-4.5" + "name": "Anthropic: Claude Haiku 5.5", + "slug": "anthropic/claude-haiku-5.5" }, "hugging_face_id": null, "name": "Anthropic: Claude Haiku Latest", "created": 1777318492, "description": "This model always redirects to the latest model in the Claude Haiku family.", - "context_length": 200000, + "context_length": 1000000, "architecture": { "modality": "text+image+file->text", "input_modalities": ["text", "image", "file"], @@ -78,16 +78,26 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000001", - "completion": "0.000005", + "prompt": "0.0000001", + "completion": "0.0000005", "web_search": "0.01", - "input_cache_read": "0.0000001", - "input_cache_write": "0.00000125", - "input_cache_write_1h": "0.000002" + "input_cache_read": "0.00000001", + "input_cache_write": "0.000000125", + "input_cache_write_1h": "0.0000002", + "overrides": [ + { + "min_prompt_tokens": 100000, + "prompt": "0.0000005", + "completion": "0.0000025", + "input_cache_read": "0.00000005", + "input_cache_write": "0.000000625", + "input_cache_write_1h": "0.000001" + } + ] }, "top_provider": { - "context_length": 200000, - "max_completion_tokens": 64000, + "context_length": 1000000, + "max_completion_tokens": 128000, "is_moderated": false }, "per_request_limits": null, @@ -96,23 +106,15 @@ "max_completion_tokens", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "stop", "structured_outputs", - "temperature", "tool_choice", "tools", - "top_k", - "top_p" + "verbosity" ], - "default_parameters": { - "temperature": null, - "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, + "default_parameters": {}, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, @@ -120,7 +122,9 @@ "details": "/api/v1/models/~anthropic/claude-haiku-latest/endpoints" }, "reasoning": { - "mandatory": false + "mandatory": false, + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], + "default_effort": "medium" } }, { @@ -165,7 +169,6 @@ "response_format", "stop", "structured_outputs", - "temperature", "tool_choice", "tools", "verbosity" @@ -206,7 +209,7 @@ "prompt": "0.000002", "completion": "0.00001", "web_search": "0.01", - "input_cache_read": "0.0000002", + "input_cache_read": "0.0000001", "input_cache_write": "0.0000025", "input_cache_write_1h": "0.000004" }, @@ -225,7 +228,6 @@ "response_format", "stop", "structured_outputs", - "temperature", "tool_choice", "tools", "verbosity" @@ -247,8 +249,8 @@ "id": "~deepseek/deepseek-flash-latest", "canonical_slug": "~deepseek/deepseek-flash-latest", "alias_target": { - "name": "DeepSeek: DeepSeek V4.1 Flash", - "slug": "deepseek/deepseek-v4.1-flash" + "name": "DeepSeek: DeepSeek V4.1 Flash 1017", + "slug": "deepseek/deepseek-v4.1-flash-1017" }, "hugging_face_id": null, "name": "DeepSeek: DeepSeek Flash Latest", @@ -263,9 +265,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000005", - "completion": "0.0000012", - "input_cache_read": "0.00000002" + "prompt": "0.00000007", + "completion": "0.0000005", + "input_cache_read": "0.000000008" }, "top_provider": { "context_length": 1048576, @@ -278,8 +280,10 @@ "include_reasoning", "logit_bias", "logprobs", + "max_completion_tokens", "max_tokens", "min_p", + "parallel_tool_calls", "presence_penalty", "reasoning", "reasoning_effort", @@ -305,7 +309,7 @@ "reasoning": { "mandatory": false, "default_enabled": true, - "supported_efforts": ["max", "high", "low"], + "supported_efforts": ["max", "high", "low", "none"], "default_effort": "high" } }, @@ -329,13 +333,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000019", - "completion": "0.000005", - "input_cache_read": "0.00000018" + "prompt": "0.0000002235", + "completion": "0.000008", + "input_cache_read": "0.00000022" }, "top_provider": { "context_length": 1048576, - "max_completion_tokens": 943718, + "max_completion_tokens": 393216, "is_moderated": false }, "per_request_limits": null, @@ -373,7 +377,7 @@ }, "reasoning": { "mandatory": false, - "supported_efforts": ["max", "high", "low"], + "supported_efforts": ["max", "high", "low", "none"], "default_effort": "high" } }, @@ -397,9 +401,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000000018", - "completion": "0.00000128", - "input_cache_read": "0.000000018" + "prompt": "0.0000000475", + "completion": "0.0000001568", + "input_cache_read": "0.000000028" }, "top_provider": { "context_length": 1048576, @@ -441,7 +445,7 @@ "reasoning": { "mandatory": false, "default_enabled": true, - "supported_efforts": ["max", "high", "low"], + "supported_efforts": ["max", "high", "low", "none"], "default_effort": "high" } }, @@ -513,8 +517,8 @@ "id": "~google/gemini-pro-latest", "canonical_slug": "~google/gemini-pro-latest", "alias_target": { - "name": "Google: Gemini 3.1 Pro Preview", - "slug": "google/gemini-3.1-pro-preview" + "name": "Google: Gemini 4 Argon", + "slug": "google/gemini-4-argon" }, "hugging_face_id": null, "name": "Google: Gemini Pro Latest", @@ -530,28 +534,18 @@ }, "pricing": { "prompt": "0.000002", - "completion": "0.000012", + "completion": "0.00001", "image": "0.000002", "audio": "0.000002", - "input_audio_cache": "0.0000002", + "input_audio_cache": "0.0000001", "web_search": "0.014", - "internal_reasoning": "0.000012", - "input_cache_read": "0.0000002", - "input_cache_write": "0.000000375", - "overrides": [ - { - "min_prompt_tokens": 200000, - "prompt": "0.000004", - "completion": "0.000018", - "audio": "0.000004", - "input_audio_cache": "0.0000004", - "input_cache_read": "0.0000004" - } - ] + "internal_reasoning": "0.00001", + "input_cache_read": "0.0000001", + "input_cache_write": "0.0000001875" }, "top_provider": { "context_length": 1048576, - "max_completion_tokens": 65536, + "max_completion_tokens": 943718, "is_moderated": false }, "per_request_limits": null, @@ -609,9 +603,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000061", - "completion": "0.000013", - "input_cache_read": "0.00000045" + "prompt": "0.000000238", + "completion": "0.000016", + "input_cache_read": "0.000000228" }, "top_provider": { "context_length": 1048576, @@ -658,7 +652,7 @@ "reasoning": { "mandatory": false, "default_enabled": true, - "supported_efforts": ["max", "high", "low"], + "supported_efforts": ["max", "high", "low", "none"], "default_effort": "max" } }, @@ -1013,6 +1007,51 @@ "default_effort": "medium" } }, + { + "id": "~unbiased/pareto-latest", + "canonical_slug": "~unbiased/pareto-latest", + "alias_target": { + "name": "Pareto 26.10", + "slug": "unbiased/pareto-26.10" + }, + "hugging_face_id": null, + "name": "Pareto Latest", + "created": 1791933050, + "description": "This model always redirects to the latest model in the Pareto family.", + "context_length": 1048576, + "architecture": { + "modality": "text+image->text", + "input_modalities": ["text", "image"], + "output_modalities": ["text"], + "tokenizer": "Router", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000008", + "completion": "0.0000032", + "input_cache_read": "0.00000003" + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 131072, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/~unbiased/pareto-latest/endpoints" + } + }, { "id": "~x-ai/grok-latest", "canonical_slug": "~x-ai/grok-latest", @@ -1104,13 +1143,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000000278", - "completion": "0.0000005", - "input_cache_read": "0.0000000278" + "prompt": "0.0000000052", + "completion": "0.0000001985", + "input_cache_read": "0.0000000052" }, "top_provider": { "context_length": 1048576, - "max_completion_tokens": 131072, + "max_completion_tokens": 943718, "is_moderated": false }, "per_request_limits": null, @@ -1174,13 +1213,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000000063", - "completion": "0.0000063", - "input_cache_read": "0.0000000585" + "prompt": "0.000000079", + "completion": "0.0000014", + "input_cache_read": "0.000000078" }, "top_provider": { "context_length": 1048576, - "max_completion_tokens": 131072, + "max_completion_tokens": 943718, "is_moderated": false }, "per_request_limits": null, @@ -1710,9 +1749,9 @@ { "arena": "models", "category": "website", - "elo": 840, + "elo": 835, "win_rate": 26.2, - "rank": 132 + "rank": 143 } ], "artificial_analysis": { @@ -1767,9 +1806,9 @@ { "arena": "models", "category": "website", - "elo": 801, + "elo": 796, "win_rate": 21.4, - "rank": 134 + "rank": 145 } ], "artificial_analysis": { @@ -1912,14 +1951,14 @@ { "arena": "agents", "category": "androidnative", - "elo": 1297, + "elo": 1283, "win_rate": 65.1, "rank": 2 }, { "arena": "agents", "category": "fullstack", - "elo": 1278, + "elo": 1280, "win_rate": 58.2, "rank": 6 }, @@ -1940,79 +1979,79 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1259, - "win_rate": 60.5, + "elo": 1264, + "win_rate": 60.4, "rank": 5 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1295, + "elo": 1293, "win_rate": 61.4, "rank": 3 }, { "arena": "agents", "category": "webapps", - "elo": 1254, - "win_rate": 56.4, - "rank": 8 + "elo": 1261, + "win_rate": 56.3, + "rank": 11 }, { "arena": "models", "category": "3d", - "elo": 1327, + "elo": 1319, "win_rate": 61.8, - "rank": 10 + "rank": 16 }, { "arena": "models", "category": "asciiart", - "elo": 1336, - "win_rate": 68, + "elo": 1329, + "win_rate": 68.1, "rank": 2 }, { "arena": "models", "category": "codecategories", - "elo": 1316, - "win_rate": 57.7, - "rank": 8 + "elo": 1310, + "win_rate": 57.6, + "rank": 13 }, { "arena": "models", "category": "dataviz", - "elo": 1311, - "win_rate": 57.6, - "rank": 11 + "elo": 1304, + "win_rate": 57.5, + "rank": 14 }, { "arena": "models", "category": "gamedev", - "elo": 1346, + "elo": 1335, "win_rate": 60.8, - "rank": 6 + "rank": 11 }, { "arena": "models", "category": "svg", "elo": 1303, "win_rate": 62.6, - "rank": 5 + "rank": 4 }, { "arena": "models", "category": "uicomponent", - "elo": 1325, + "elo": 1319, "win_rate": 58.1, - "rank": 9 + "rank": 12 }, { "arena": "models", "category": "website", - "elo": 1302, + "elo": 1296, "win_rate": 56, - "rank": 13 + "rank": 17 } ], "artificial_analysis": { @@ -2108,14 +2147,14 @@ { "arena": "agents", "category": "androidnative", - "elo": 1297, + "elo": 1283, "win_rate": 65.1, "rank": 2 }, { "arena": "agents", "category": "fullstack", - "elo": 1278, + "elo": 1280, "win_rate": 58.2, "rank": 6 }, @@ -2136,79 +2175,79 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1259, - "win_rate": 60.5, + "elo": 1264, + "win_rate": 60.4, "rank": 5 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1295, + "elo": 1293, "win_rate": 61.4, "rank": 3 }, { "arena": "agents", "category": "webapps", - "elo": 1254, - "win_rate": 56.4, - "rank": 8 + "elo": 1261, + "win_rate": 56.3, + "rank": 11 }, { "arena": "models", "category": "3d", - "elo": 1327, + "elo": 1319, "win_rate": 61.8, - "rank": 10 + "rank": 16 }, { "arena": "models", "category": "asciiart", - "elo": 1336, - "win_rate": 68, + "elo": 1329, + "win_rate": 68.1, "rank": 2 }, { "arena": "models", "category": "codecategories", - "elo": 1316, - "win_rate": 57.7, - "rank": 8 + "elo": 1310, + "win_rate": 57.6, + "rank": 13 }, { "arena": "models", "category": "dataviz", - "elo": 1311, - "win_rate": 57.6, - "rank": 11 + "elo": 1304, + "win_rate": 57.5, + "rank": 14 }, { "arena": "models", "category": "gamedev", - "elo": 1346, + "elo": 1335, "win_rate": 60.8, - "rank": 6 + "rank": 11 }, { "arena": "models", "category": "svg", "elo": 1303, "win_rate": 62.6, - "rank": 5 + "rank": 4 }, { "arena": "models", "category": "uicomponent", - "elo": 1325, + "elo": 1319, "win_rate": 58.1, - "rank": 9 + "rank": 12 }, { "arena": "models", "category": "website", - "elo": 1302, + "elo": 1296, "win_rate": 56, - "rank": 13 + "rank": 17 } ], "artificial_analysis": { @@ -2277,7 +2316,7 @@ { "arena": "agents", "category": "fullstack", - "elo": 1325, + "elo": 1326, "win_rate": 57.2, "rank": 1 }, @@ -2291,79 +2330,86 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1265, + "elo": 1267, "win_rate": 56.3, - "rank": 3 + "rank": 4 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1328, - "win_rate": 62.6, + "elo": 1318, + "win_rate": 62.1, + "rank": 1 + }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1356, + "win_rate": 70.4, "rank": 1 }, { "arena": "agents", "category": "webapps", - "elo": 1310, + "elo": 1318, "win_rate": 56.1, "rank": 1 }, { "arena": "models", "category": "3d", - "elo": 1401, + "elo": 1393, "win_rate": 67.7, - "rank": 3 + "rank": 6 }, { "arena": "models", "category": "asciiart", - "elo": 1331, + "elo": 1323, "win_rate": 65, "rank": 3 }, { "arena": "models", "category": "codecategories", - "elo": 1341, + "elo": 1336, "win_rate": 59.3, - "rank": 4 + "rank": 7 }, { "arena": "models", "category": "dataviz", - "elo": 1352, + "elo": 1344, "win_rate": 61.8, - "rank": 4 + "rank": 5 }, { "arena": "models", "category": "gamedev", - "elo": 1392, + "elo": 1381, "win_rate": 65.6, - "rank": 2 + "rank": 4 }, { "arena": "models", "category": "svg", - "elo": 1302, + "elo": 1301, "win_rate": 56.4, "rank": 6 }, { "arena": "models", "category": "uicomponent", - "elo": 1345, + "elo": 1339, "win_rate": 59.6, - "rank": 6 + "rank": 9 }, { "arena": "models", "category": "website", - "elo": 1318, + "elo": 1313, "win_rate": 56.3, - "rank": 6 + "rank": 9 } ], "artificial_analysis": { @@ -2431,7 +2477,7 @@ { "arena": "agents", "category": "fullstack", - "elo": 1325, + "elo": 1326, "win_rate": 57.2, "rank": 1 }, @@ -2445,79 +2491,86 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1265, + "elo": 1267, "win_rate": 56.3, - "rank": 3 + "rank": 4 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1328, - "win_rate": 62.6, + "elo": 1318, + "win_rate": 62.1, + "rank": 1 + }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1356, + "win_rate": 70.4, "rank": 1 }, { "arena": "agents", "category": "webapps", - "elo": 1310, + "elo": 1318, "win_rate": 56.1, "rank": 1 }, { "arena": "models", "category": "3d", - "elo": 1401, + "elo": 1393, "win_rate": 67.7, - "rank": 3 + "rank": 6 }, { "arena": "models", "category": "asciiart", - "elo": 1331, + "elo": 1323, "win_rate": 65, "rank": 3 }, { "arena": "models", "category": "codecategories", - "elo": 1341, + "elo": 1336, "win_rate": 59.3, - "rank": 4 + "rank": 7 }, { "arena": "models", "category": "dataviz", - "elo": 1352, + "elo": 1344, "win_rate": 61.8, - "rank": 4 + "rank": 5 }, { "arena": "models", "category": "gamedev", - "elo": 1392, + "elo": 1381, "win_rate": 65.6, - "rank": 2 + "rank": 4 }, { "arena": "models", "category": "svg", - "elo": 1302, + "elo": 1301, "win_rate": 56.4, "rank": 6 }, { "arena": "models", "category": "uicomponent", - "elo": 1345, + "elo": 1339, "win_rate": 59.6, - "rank": 6 + "rank": 9 }, { "arena": "models", "category": "website", - "elo": 1318, + "elo": 1313, "win_rate": 56.3, - "rank": 6 + "rank": 9 } ], "artificial_analysis": { @@ -2594,58 +2647,58 @@ { "arena": "models", "category": "3d", - "elo": 1080, + "elo": 1072, "win_rate": 41.1, - "rank": 91 + "rank": 100 }, { "arena": "models", "category": "asciiart", - "elo": 1149, + "elo": 1140, "win_rate": 49.3, - "rank": 45 + "rank": 49 }, { "arena": "models", "category": "codecategories", - "elo": 1119, + "elo": 1115, "win_rate": 44.9, - "rank": 87 + "rank": 98 }, { "arena": "models", "category": "dataviz", - "elo": 1131, + "elo": 1124, "win_rate": 45.6, - "rank": 86 + "rank": 94 }, { "arena": "models", "category": "gamedev", - "elo": 1107, + "elo": 1097, "win_rate": 44.7, - "rank": 85 + "rank": 97 }, { "arena": "models", "category": "svg", - "elo": 1025, + "elo": 1026, "win_rate": 39.1, - "rank": 79 + "rank": 80 }, { "arena": "models", "category": "uicomponent", - "elo": 1107, + "elo": 1100, "win_rate": 42.6, - "rank": 86 + "rank": 95 }, { "arena": "models", "category": "website", - "elo": 1127, + "elo": 1122, "win_rate": 45.1, - "rank": 91 + "rank": 101 } ], "artificial_analysis": { @@ -2719,58 +2772,58 @@ { "arena": "models", "category": "3d", - "elo": 1080, + "elo": 1072, "win_rate": 41.1, - "rank": 91 + "rank": 100 }, { "arena": "models", "category": "asciiart", - "elo": 1149, + "elo": 1140, "win_rate": 49.3, - "rank": 45 + "rank": 49 }, { "arena": "models", "category": "codecategories", - "elo": 1119, + "elo": 1115, "win_rate": 44.9, - "rank": 87 + "rank": 98 }, { "arena": "models", "category": "dataviz", - "elo": 1131, + "elo": 1124, "win_rate": 45.6, - "rank": 86 + "rank": 94 }, { "arena": "models", "category": "gamedev", - "elo": 1107, + "elo": 1097, "win_rate": 44.7, - "rank": 85 + "rank": 97 }, { "arena": "models", "category": "svg", - "elo": 1025, + "elo": 1026, "win_rate": 39.1, - "rank": 79 + "rank": 80 }, { "arena": "models", "category": "uicomponent", - "elo": 1107, + "elo": 1100, "win_rate": 42.6, - "rank": 86 + "rank": 95 }, { "arena": "models", "category": "website", - "elo": 1127, + "elo": 1122, "win_rate": 45.1, - "rank": 91 + "rank": 101 } ], "artificial_analysis": { @@ -2783,6 +2836,237 @@ "mandatory": false } }, + { + "id": "anthropic/claude-haiku-5.5", + "canonical_slug": "anthropic/claude-haiku-5.5-20261007", + "hugging_face_id": null, + "name": "Anthropic: Claude Haiku 5.5", + "created": 1791397883, + "description": "Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...", + "context_length": 1000000, + "architecture": { + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], + "output_modalities": ["text"], + "tokenizer": "Claude", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000001", + "completion": "0.0000005", + "web_search": "0.01", + "input_cache_read": "0.00000001", + "input_cache_write": "0.000000125", + "input_cache_write_1h": "0.0000002", + "overrides": [ + { + "min_prompt_tokens": 100000, + "prompt": "0.0000005", + "completion": "0.0000025", + "input_cache_read": "0.00000005", + "input_cache_write": "0.000000625", + "input_cache_write_1h": "0.000001" + } + ] + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 128000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_completion_tokens", + "max_tokens", + "reasoning", + "reasoning_effort", + "response_format", + "stop", + "structured_outputs", + "tool_choice", + "tools", + "verbosity" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/anthropic/claude-haiku-5.5-20261007/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1343, + "win_rate": 58.3, + "rank": 10 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1278, + "win_rate": 50.1, + "rank": 23 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1295, + "win_rate": 54.8, + "rank": 15 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1315, + "win_rate": 53.8, + "rank": 13 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1292, + "win_rate": 52.8, + "rank": 22 + }, + { + "arena": "models", + "category": "website", + "elo": 1263, + "win_rate": 48.5, + "rank": 36 + } + ], + "artificial_analysis": { + "intelligence_index": 43.4, + "coding_index": null, + "agentic_index": null + } + }, + "reasoning": { + "mandatory": false, + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], + "default_effort": "medium" + } + }, + { + "id": "anthropic/claude-haiku-5.5:batch", + "canonical_slug": "anthropic/claude-haiku-5.5-20261007", + "hugging_face_id": null, + "name": "Anthropic: Claude Haiku 5.5 (batch)", + "created": 1791397883, + "description": "Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...", + "context_length": 1000000, + "architecture": { + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], + "output_modalities": ["text"], + "tokenizer": "Claude", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000005", + "completion": "0.00000025", + "web_search": "0.01", + "input_cache_read": "0.000000005", + "input_cache_write": "0.0000000625", + "input_cache_write_1h": "0.0000001", + "overrides": [ + { + "min_prompt_tokens": 100000, + "prompt": "0.00000025", + "completion": "0.00000125", + "input_cache_read": "0.000000025", + "input_cache_write": "0.0000003125", + "input_cache_write_1h": "0.0000005" + } + ] + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 128000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "reasoning_effort", + "response_format", + "stop", + "structured_outputs", + "tool_choice", + "tools", + "verbosity" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/anthropic/claude-haiku-5.5-20261007/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1343, + "win_rate": 58.3, + "rank": 10 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1278, + "win_rate": 50.1, + "rank": 23 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1295, + "win_rate": 54.8, + "rank": 15 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1315, + "win_rate": 53.8, + "rank": 13 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1292, + "win_rate": 52.8, + "rank": 22 + }, + { + "arena": "models", + "category": "website", + "elo": 1263, + "win_rate": 48.5, + "rank": 36 + } + ], + "artificial_analysis": { + "intelligence_index": 43.4, + "coding_index": null, + "agentic_index": null + } + }, + "reasoning": { + "mandatory": false, + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], + "default_effort": "medium" + } + }, { "id": "anthropic/claude-opus-4.1", "canonical_slug": "anthropic/claude-4.1-opus-20250805", @@ -2842,58 +3126,58 @@ { "arena": "models", "category": "3d", - "elo": 1161, + "elo": 1153, "win_rate": 51.9, - "rank": 60 + "rank": 67 }, { "arena": "models", "category": "asciiart", - "elo": 1175, + "elo": 1167, "win_rate": 51.5, - "rank": 29 + "rank": 31 }, { "arena": "models", "category": "codecategories", - "elo": 1175, + "elo": 1171, "win_rate": 55.8, - "rank": 62 + "rank": 71 }, { "arena": "models", "category": "dataviz", - "elo": 1172, + "elo": 1166, "win_rate": 56.4, - "rank": 67 + "rank": 74 }, { "arena": "models", "category": "gamedev", - "elo": 1182, + "elo": 1171, "win_rate": 58.4, - "rank": 56 + "rank": 66 }, { "arena": "models", "category": "svg", - "elo": 1151, + "elo": 1153, "win_rate": 60.8, - "rank": 41 + "rank": 42 }, { "arena": "models", "category": "uicomponent", - "elo": 1171, + "elo": 1165, "win_rate": 57.8, - "rank": 65 + "rank": 72 }, { "arena": "models", "category": "website", - "elo": 1183, + "elo": 1177, "win_rate": 55.3, - "rank": 68 + "rank": 77 } ], "artificial_analysis": { @@ -2965,58 +3249,58 @@ { "arena": "models", "category": "3d", - "elo": 1161, + "elo": 1153, "win_rate": 51.9, - "rank": 60 + "rank": 67 }, { "arena": "models", "category": "asciiart", - "elo": 1175, + "elo": 1167, "win_rate": 51.5, - "rank": 29 + "rank": 31 }, { "arena": "models", "category": "codecategories", - "elo": 1175, + "elo": 1171, "win_rate": 55.8, - "rank": 62 + "rank": 71 }, { "arena": "models", "category": "dataviz", - "elo": 1172, + "elo": 1166, "win_rate": 56.4, - "rank": 67 + "rank": 74 }, { "arena": "models", "category": "gamedev", - "elo": 1182, + "elo": 1171, "win_rate": 58.4, - "rank": 56 + "rank": 66 }, { "arena": "models", "category": "svg", - "elo": 1151, + "elo": 1153, "win_rate": 60.8, - "rank": 41 + "rank": 42 }, { "arena": "models", "category": "uicomponent", - "elo": 1171, + "elo": 1165, "win_rate": 57.8, - "rank": 65 + "rank": 72 }, { "arena": "models", "category": "website", - "elo": 1183, + "elo": 1177, "win_rate": 55.3, - "rank": 68 + "rank": 77 } ], "artificial_analysis": { @@ -3084,86 +3368,86 @@ { "arena": "models", "category": "3d", - "elo": 1222, + "elo": 1214, "win_rate": 58.5, - "rank": 37 + "rank": 44 }, { "arena": "models", "category": "asciiart", - "elo": 1199, + "elo": 1190, "win_rate": 54.8, - "rank": 27 + "rank": 28 }, { "arena": "models", "category": "codecategories", - "elo": 1246, + "elo": 1242, "win_rate": 59.5, - "rank": 36 + "rank": 44 }, { "arena": "models", "category": "dataviz", - "elo": 1249, + "elo": 1243, "win_rate": 58.5, - "rank": 31 + "rank": 37 }, { "arena": "models", "category": "gamedev", - "elo": 1239, + "elo": 1229, "win_rate": 59.3, - "rank": 35 + "rank": 42 }, { "arena": "models", "category": "svg", - "elo": 1180, + "elo": 1181, "win_rate": 58.7, - "rank": 32 + "rank": 33 }, { "arena": "models", "category": "uicomponent", - "elo": 1245, + "elo": 1238, "win_rate": 58.1, - "rank": 37 + "rank": 45 }, { "arena": "models", "category": "website", - "elo": 1253, + "elo": 1247, "win_rate": 59.7, - "rank": 38 + "rank": 46 }, { "arena": "agents", "category": "androidnative", - "elo": 1191, + "elo": 1175, "win_rate": 65.5, - "rank": 17 + "rank": 20 }, { "arena": "agents", "category": "fullstack", - "elo": 1155, + "elo": 1156, "win_rate": 60.2, "rank": 24 }, { "arena": "agents", "category": "mobileapps", - "elo": 1186, + "elo": 1189, "win_rate": 60.7, - "rank": 19 + "rank": 21 }, { "arena": "agents", "category": "webapps", - "elo": 1152, + "elo": 1159, "win_rate": 55.1, - "rank": 26 + "rank": 30 } ], "artificial_analysis": { @@ -3229,86 +3513,86 @@ { "arena": "models", "category": "3d", - "elo": 1222, + "elo": 1214, "win_rate": 58.5, - "rank": 37 + "rank": 44 }, { "arena": "models", "category": "asciiart", - "elo": 1199, + "elo": 1190, "win_rate": 54.8, - "rank": 27 + "rank": 28 }, { "arena": "models", "category": "codecategories", - "elo": 1246, + "elo": 1242, "win_rate": 59.5, - "rank": 36 + "rank": 44 }, { "arena": "models", "category": "dataviz", - "elo": 1249, + "elo": 1243, "win_rate": 58.5, - "rank": 31 + "rank": 37 }, { "arena": "models", "category": "gamedev", - "elo": 1239, + "elo": 1229, "win_rate": 59.3, - "rank": 35 + "rank": 42 }, { "arena": "models", "category": "svg", - "elo": 1180, + "elo": 1181, "win_rate": 58.7, - "rank": 32 + "rank": 33 }, { "arena": "models", "category": "uicomponent", - "elo": 1245, + "elo": 1238, "win_rate": 58.1, - "rank": 37 + "rank": 45 }, { "arena": "models", "category": "website", - "elo": 1253, + "elo": 1247, "win_rate": 59.7, - "rank": 38 + "rank": 46 }, { "arena": "agents", "category": "androidnative", - "elo": 1191, + "elo": 1175, "win_rate": 65.5, - "rank": 17 + "rank": 20 }, { "arena": "agents", "category": "fullstack", - "elo": 1155, + "elo": 1156, "win_rate": 60.2, "rank": 24 }, { "arena": "agents", "category": "mobileapps", - "elo": 1186, + "elo": 1189, "win_rate": 60.7, - "rank": 19 + "rank": 21 }, { "arena": "agents", "category": "webapps", - "elo": 1152, + "elo": 1159, "win_rate": 55.1, - "rank": 26 + "rank": 30 } ], "artificial_analysis": { @@ -3378,93 +3662,93 @@ { "arena": "agents", "category": "agenticgamedev", - "elo": 1213, - "win_rate": 50, + "elo": 1212, + "win_rate": 48.2, "rank": 8 }, { "arena": "agents", "category": "androidnative", - "elo": 1215, - "win_rate": 63.8, - "rank": 12 + "elo": 1196, + "win_rate": 63, + "rank": 13 }, { "arena": "agents", "category": "fullstack", - "elo": 1218, - "win_rate": 59.8, + "elo": 1220, + "win_rate": 59.9, "rank": 13 }, { "arena": "agents", "category": "mobileapps", - "elo": 1204, - "win_rate": 59.2, - "rank": 15 + "elo": 1207, + "win_rate": 58.5, + "rank": 17 }, { "arena": "agents", "category": "webapps", - "elo": 1199, - "win_rate": 57, - "rank": 18 + "elo": 1206, + "win_rate": 56.3, + "rank": 22 }, { "arena": "models", "category": "3d", - "elo": 1282, + "elo": 1274, "win_rate": 62.5, - "rank": 17 + "rank": 23 }, { "arena": "models", "category": "asciiart", - "elo": 1263, + "elo": 1255, "win_rate": 61.9, - "rank": 13 + "rank": 15 }, { "arena": "models", "category": "codecategories", - "elo": 1293, + "elo": 1289, "win_rate": 61.2, - "rank": 16 + "rank": 20 }, { "arena": "models", "category": "dataviz", - "elo": 1285, + "elo": 1279, "win_rate": 58.7, - "rank": 16 + "rank": 21 }, { "arena": "models", "category": "gamedev", - "elo": 1288, + "elo": 1278, "win_rate": 61, - "rank": 18 + "rank": 23 }, { "arena": "models", "category": "svg", - "elo": 1227, + "elo": 1228, "win_rate": 60.9, - "rank": 17 + "rank": 18 }, { "arena": "models", "category": "uicomponent", - "elo": 1291, + "elo": 1284, "win_rate": 59.8, - "rank": 21 + "rank": 25 }, { "arena": "models", "category": "website", - "elo": 1296, + "elo": 1291, "win_rate": 61.2, - "rank": 14 + "rank": 19 } ], "artificial_analysis": { @@ -3477,7 +3761,7 @@ "mandatory": false, "default_enabled": false, "supports_max_tokens": true, - "supported_efforts": ["max", "high", "medium", "low"], + "supported_efforts": ["max", "high", "medium", "low", "none"], "default_effort": "high" } }, @@ -3536,93 +3820,93 @@ { "arena": "agents", "category": "agenticgamedev", - "elo": 1213, - "win_rate": 50, + "elo": 1212, + "win_rate": 48.2, "rank": 8 }, { "arena": "agents", "category": "androidnative", - "elo": 1215, - "win_rate": 63.8, - "rank": 12 + "elo": 1196, + "win_rate": 63, + "rank": 13 }, { "arena": "agents", "category": "fullstack", - "elo": 1218, - "win_rate": 59.8, + "elo": 1220, + "win_rate": 59.9, "rank": 13 }, { "arena": "agents", "category": "mobileapps", - "elo": 1204, - "win_rate": 59.2, - "rank": 15 + "elo": 1207, + "win_rate": 58.5, + "rank": 17 }, { "arena": "agents", "category": "webapps", - "elo": 1199, - "win_rate": 57, - "rank": 18 + "elo": 1206, + "win_rate": 56.3, + "rank": 22 }, { "arena": "models", "category": "3d", - "elo": 1282, + "elo": 1274, "win_rate": 62.5, - "rank": 17 + "rank": 23 }, { "arena": "models", "category": "asciiart", - "elo": 1263, + "elo": 1255, "win_rate": 61.9, - "rank": 13 + "rank": 15 }, { "arena": "models", "category": "codecategories", - "elo": 1293, + "elo": 1289, "win_rate": 61.2, - "rank": 16 + "rank": 20 }, { "arena": "models", "category": "dataviz", - "elo": 1285, + "elo": 1279, "win_rate": 58.7, - "rank": 16 + "rank": 21 }, { "arena": "models", "category": "gamedev", - "elo": 1288, + "elo": 1278, "win_rate": 61, - "rank": 18 + "rank": 23 }, { "arena": "models", "category": "svg", - "elo": 1227, + "elo": 1228, "win_rate": 60.9, - "rank": 17 + "rank": 18 }, { "arena": "models", "category": "uicomponent", - "elo": 1291, + "elo": 1284, "win_rate": 59.8, - "rank": 21 + "rank": 25 }, { "arena": "models", "category": "website", - "elo": 1296, + "elo": 1291, "win_rate": 61.2, - "rank": 14 + "rank": 19 } ], "artificial_analysis": { @@ -3635,7 +3919,7 @@ "mandatory": false, "default_enabled": false, "supports_max_tokens": true, - "supported_efforts": ["max", "high", "medium", "low"], + "supported_efforts": ["max", "high", "medium", "low", "none"], "default_effort": "high" } }, @@ -3699,7 +3983,7 @@ "reasoning": { "mandatory": false, "default_enabled": false, - "supported_efforts": ["max", "xhigh", "high", "medium", "low"], + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], "default_effort": "high" } }, @@ -3762,7 +4046,7 @@ "reasoning": { "mandatory": false, "default_enabled": false, - "supported_efforts": ["max", "xhigh", "high", "medium", "low"], + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], "default_effort": "high" } }, @@ -3804,7 +4088,6 @@ "response_format", "stop", "structured_outputs", - "temperature", "tool_choice", "tools", "verbosity" @@ -3821,8 +4104,8 @@ { "arena": "agents", "category": "agenticgamedev", - "elo": 1238, - "win_rate": 55.8, + "elo": 1239, + "win_rate": 55.7, "rank": 4 }, { @@ -3856,14 +4139,14 @@ { "arena": "agents", "category": "androidnative", - "elo": 1247, - "win_rate": 56.4, + "elo": 1232, + "win_rate": 56.2, "rank": 8 }, { "arena": "agents", "category": "fullstack", - "elo": 1248, + "elo": 1249, "win_rate": 55.3, "rank": 8 }, @@ -3877,16 +4160,16 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1220, + "elo": 1221, "win_rate": 58, "rank": 4 }, { "arena": "agents", "category": "mobileapps", - "elo": 1220, - "win_rate": 55.4, - "rank": 9 + "elo": 1222, + "win_rate": 55, + "rank": 11 }, { "arena": "agents", @@ -3902,68 +4185,75 @@ "win_rate": 65.9, "rank": 2 }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1296, + "win_rate": 75, + "rank": 4 + }, { "arena": "agents", "category": "webapps", - "elo": 1224, + "elo": 1233, "win_rate": 51.4, - "rank": 12 + "rank": 15 }, { "arena": "models", "category": "3d", - "elo": 1230, - "win_rate": 51.9, - "rank": 35 + "elo": 1223, + "win_rate": 51.6, + "rank": 42 }, { "arena": "models", "category": "asciiart", - "elo": 1289, - "win_rate": 62.4, - "rank": 5 + "elo": 1277, + "win_rate": 62.3, + "rank": 8 }, { "arena": "models", "category": "codecategories", - "elo": 1258, - "win_rate": 52.7, - "rank": 31 + "elo": 1255, + "win_rate": 52.5, + "rank": 39 }, { "arena": "models", "category": "dataviz", - "elo": 1245, - "win_rate": 53.1, - "rank": 32 + "elo": 1240, + "win_rate": 52.8, + "rank": 38 }, { "arena": "models", "category": "gamedev", - "elo": 1273, - "win_rate": 53.3, - "rank": 22 + "elo": 1264, + "win_rate": 52.7, + "rank": 30 }, { "arena": "models", "category": "svg", - "elo": 1194, - "win_rate": 51.7, - "rank": 26 + "elo": 1195, + "win_rate": 51.4, + "rank": 27 }, { "arena": "models", "category": "uicomponent", - "elo": 1264, - "win_rate": 53.5, - "rank": 33 + "elo": 1257, + "win_rate": 53, + "rank": 41 }, { "arena": "models", "category": "website", - "elo": 1262, - "win_rate": 53.1, - "rank": 33 + "elo": 1258, + "win_rate": 52.9, + "rank": 38 } ], "artificial_analysis": { @@ -3975,7 +4265,7 @@ "reasoning": { "mandatory": false, "default_enabled": false, - "supported_efforts": ["max", "xhigh", "high", "medium", "low"], + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], "default_effort": "high" } }, @@ -4032,8 +4322,8 @@ { "arena": "agents", "category": "agenticgamedev", - "elo": 1238, - "win_rate": 55.8, + "elo": 1239, + "win_rate": 55.7, "rank": 4 }, { @@ -4067,14 +4357,14 @@ { "arena": "agents", "category": "androidnative", - "elo": 1247, - "win_rate": 56.4, + "elo": 1232, + "win_rate": 56.2, "rank": 8 }, { "arena": "agents", "category": "fullstack", - "elo": 1248, + "elo": 1249, "win_rate": 55.3, "rank": 8 }, @@ -4088,16 +4378,16 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1220, + "elo": 1221, "win_rate": 58, "rank": 4 }, { "arena": "agents", "category": "mobileapps", - "elo": 1220, - "win_rate": 55.4, - "rank": 9 + "elo": 1222, + "win_rate": 55, + "rank": 11 }, { "arena": "agents", @@ -4113,68 +4403,75 @@ "win_rate": 65.9, "rank": 2 }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1296, + "win_rate": 75, + "rank": 4 + }, { "arena": "agents", "category": "webapps", - "elo": 1224, + "elo": 1233, "win_rate": 51.4, - "rank": 12 + "rank": 15 }, { "arena": "models", "category": "3d", - "elo": 1230, - "win_rate": 51.9, - "rank": 35 + "elo": 1223, + "win_rate": 51.6, + "rank": 42 }, { "arena": "models", "category": "asciiart", - "elo": 1289, - "win_rate": 62.4, - "rank": 5 + "elo": 1277, + "win_rate": 62.3, + "rank": 8 }, { "arena": "models", "category": "codecategories", - "elo": 1258, - "win_rate": 52.7, - "rank": 31 + "elo": 1255, + "win_rate": 52.5, + "rank": 39 }, { "arena": "models", "category": "dataviz", - "elo": 1245, - "win_rate": 53.1, - "rank": 32 + "elo": 1240, + "win_rate": 52.8, + "rank": 38 }, { "arena": "models", "category": "gamedev", - "elo": 1273, - "win_rate": 53.3, - "rank": 22 + "elo": 1264, + "win_rate": 52.7, + "rank": 30 }, { "arena": "models", "category": "svg", - "elo": 1194, - "win_rate": 51.7, - "rank": 26 + "elo": 1195, + "win_rate": 51.4, + "rank": 27 }, { "arena": "models", "category": "uicomponent", - "elo": 1264, - "win_rate": 53.5, - "rank": 33 + "elo": 1257, + "win_rate": 53, + "rank": 41 }, { "arena": "models", "category": "website", - "elo": 1262, - "win_rate": 53.1, - "rank": 33 + "elo": 1258, + "win_rate": 52.9, + "rank": 38 } ], "artificial_analysis": { @@ -4186,7 +4483,7 @@ "reasoning": { "mandatory": false, "default_enabled": false, - "supported_efforts": ["max", "xhigh", "high", "medium", "low"], + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], "default_effort": "high" } }, @@ -4228,7 +4525,6 @@ "response_format", "stop", "structured_outputs", - "temperature", "tool_choice", "tools", "verbosity" @@ -4246,20 +4542,20 @@ "arena": "agents", "category": "agenticgamedev", "elo": 1261, - "win_rate": 53.8, + "win_rate": 53.9, "rank": 2 }, { "arena": "agents", "category": "androidnative", - "elo": 1269, - "win_rate": 55.9, - "rank": 3 + "elo": 1257, + "win_rate": 56.1, + "rank": 4 }, { "arena": "agents", "category": "fullstack", - "elo": 1305, + "elo": 1306, "win_rate": 57.3, "rank": 4 }, @@ -4280,72 +4576,72 @@ { "arena": "agents", "category": "python-pptxslides", - "elo": 1267, - "win_rate": 54.4, + "elo": 1261, + "win_rate": 54.2, "rank": 5 }, { "arena": "agents", "category": "webapps", - "elo": 1259, - "win_rate": 54.5, - "rank": 7 + "elo": 1266, + "win_rate": 54.3, + "rank": 10 }, { "arena": "models", "category": "3d", - "elo": 1342, - "win_rate": 59.8, - "rank": 7 + "elo": 1335, + "win_rate": 59.7, + "rank": 13 }, { "arena": "models", "category": "asciiart", - "elo": 1362, - "win_rate": 67.5, + "elo": 1352, + "win_rate": 67.4, "rank": 1 }, { "arena": "models", "category": "codecategories", - "elo": 1329, - "win_rate": 57.6, - "rank": 5 + "elo": 1324, + "win_rate": 57.3, + "rank": 10 }, { "arena": "models", "category": "dataviz", - "elo": 1338, - "win_rate": 58.6, - "rank": 9 + "elo": 1329, + "win_rate": 58.2, + "rank": 10 }, { "arena": "models", "category": "gamedev", - "elo": 1348, - "win_rate": 59.2, - "rank": 5 + "elo": 1339, + "win_rate": 58.5, + "rank": 10 }, { "arena": "models", "category": "svg", - "elo": 1317, - "win_rate": 58.9, + "elo": 1311, + "win_rate": 58.2, "rank": 3 }, { "arena": "models", "category": "uicomponent", - "elo": 1350, - "win_rate": 60.5, + "elo": 1348, + "win_rate": 60.7, "rank": 5 }, { "arena": "models", "category": "website", - "elo": 1314, - "win_rate": 56.2, - "rank": 7 + "elo": 1309, + "win_rate": 55.9, + "rank": 12 } ], "artificial_analysis": { @@ -4357,7 +4653,7 @@ "reasoning": { "mandatory": false, "default_enabled": true, - "supported_efforts": ["max", "xhigh", "high", "medium", "low"], + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], "default_effort": "high" } }, @@ -4415,20 +4711,20 @@ "arena": "agents", "category": "agenticgamedev", "elo": 1261, - "win_rate": 53.8, + "win_rate": 53.9, "rank": 2 }, { "arena": "agents", "category": "androidnative", - "elo": 1269, - "win_rate": 55.9, - "rank": 3 + "elo": 1257, + "win_rate": 56.1, + "rank": 4 }, { "arena": "agents", "category": "fullstack", - "elo": 1305, + "elo": 1306, "win_rate": 57.3, "rank": 4 }, @@ -4449,72 +4745,72 @@ { "arena": "agents", "category": "python-pptxslides", - "elo": 1267, - "win_rate": 54.4, + "elo": 1261, + "win_rate": 54.2, "rank": 5 }, { "arena": "agents", "category": "webapps", - "elo": 1259, - "win_rate": 54.5, - "rank": 7 + "elo": 1266, + "win_rate": 54.3, + "rank": 10 }, { "arena": "models", "category": "3d", - "elo": 1342, - "win_rate": 59.8, - "rank": 7 + "elo": 1335, + "win_rate": 59.7, + "rank": 13 }, { "arena": "models", "category": "asciiart", - "elo": 1362, - "win_rate": 67.5, + "elo": 1352, + "win_rate": 67.4, "rank": 1 }, { "arena": "models", "category": "codecategories", - "elo": 1329, - "win_rate": 57.6, - "rank": 5 + "elo": 1324, + "win_rate": 57.3, + "rank": 10 }, { "arena": "models", "category": "dataviz", - "elo": 1338, - "win_rate": 58.6, - "rank": 9 + "elo": 1329, + "win_rate": 58.2, + "rank": 10 }, { "arena": "models", "category": "gamedev", - "elo": 1348, - "win_rate": 59.2, - "rank": 5 + "elo": 1339, + "win_rate": 58.5, + "rank": 10 }, { "arena": "models", "category": "svg", - "elo": 1317, - "win_rate": 58.9, + "elo": 1311, + "win_rate": 58.2, "rank": 3 }, { "arena": "models", "category": "uicomponent", - "elo": 1350, - "win_rate": 60.5, + "elo": 1348, + "win_rate": 60.7, "rank": 5 }, { "arena": "models", "category": "website", - "elo": 1314, - "win_rate": 56.2, - "rank": 7 + "elo": 1309, + "win_rate": 55.9, + "rank": 12 } ], "artificial_analysis": { @@ -4526,7 +4822,7 @@ "reasoning": { "mandatory": false, "default_enabled": true, - "supported_efforts": ["max", "xhigh", "high", "medium", "low"], + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], "default_effort": "high" } }, @@ -4568,7 +4864,6 @@ "response_format", "stop", "structured_outputs", - "temperature", "tool_choice", "tools", "verbosity" @@ -4585,57 +4880,71 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1328, - "win_rate": 64.3, + "elo": 1308, + "win_rate": 62, + "rank": 2 + }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1345, + "win_rate": 69.8, + "rank": 2 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1317, + "win_rate": 60.7, "rank": 2 }, { "arena": "models", "category": "3d", - "elo": 1491, - "win_rate": 72.3, + "elo": 1477, + "win_rate": 71.9, "rank": 1 }, { "arena": "models", "category": "codecategories", - "elo": 1410, - "win_rate": 65.4, + "elo": 1390, + "win_rate": 63.8, "rank": 1 }, { "arena": "models", "category": "dataviz", - "elo": 1406, - "win_rate": 64.8, + "elo": 1397, + "win_rate": 64.7, "rank": 1 }, { "arena": "models", "category": "gamedev", - "elo": 1466, - "win_rate": 72.3, - "rank": 1 + "elo": 1458, + "win_rate": 71.8, + "rank": 2 }, { "arena": "models", "category": "svg", - "elo": 1335, - "win_rate": 50.4, + "elo": 1331, + "win_rate": 52, "rank": 1 }, { "arena": "models", "category": "uicomponent", - "elo": 1395, - "win_rate": 65.6, - "rank": 2 + "elo": 1388, + "win_rate": 64.3, + "rank": 1 }, { "arena": "models", "category": "website", - "elo": 1339, - "win_rate": 57.2, + "elo": 1336, + "win_rate": 57.6, "rank": 3 } ], @@ -4704,57 +5013,71 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1328, - "win_rate": 64.3, + "elo": 1308, + "win_rate": 62, + "rank": 2 + }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1345, + "win_rate": 69.8, + "rank": 2 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1317, + "win_rate": 60.7, "rank": 2 }, { "arena": "models", "category": "3d", - "elo": 1491, - "win_rate": 72.3, + "elo": 1477, + "win_rate": 71.9, "rank": 1 }, { "arena": "models", "category": "codecategories", - "elo": 1410, - "win_rate": 65.4, + "elo": 1390, + "win_rate": 63.8, "rank": 1 }, { "arena": "models", "category": "dataviz", - "elo": 1406, - "win_rate": 64.8, + "elo": 1397, + "win_rate": 64.7, "rank": 1 }, { "arena": "models", "category": "gamedev", - "elo": 1466, - "win_rate": 72.3, - "rank": 1 + "elo": 1458, + "win_rate": 71.8, + "rank": 2 }, { "arena": "models", "category": "svg", - "elo": 1335, - "win_rate": 50.4, + "elo": 1331, + "win_rate": 52, "rank": 1 }, { "arena": "models", "category": "uicomponent", - "elo": 1395, - "win_rate": 65.6, - "rank": 2 + "elo": 1388, + "win_rate": 64.3, + "rank": 1 }, { "arena": "models", "category": "website", - "elo": 1339, - "win_rate": 57.2, + "elo": 1336, + "win_rate": 57.6, "rank": 3 } ], @@ -4771,16 +5094,16 @@ } }, { - "id": "anthropic/claude-sonnet-4", - "canonical_slug": "anthropic/claude-4-sonnet-20250522", + "id": "anthropic/claude-sonnet-4.5", + "canonical_slug": "anthropic/claude-4.5-sonnet-20250929", "hugging_face_id": "", - "name": "Anthropic: Claude Sonnet 4", - "created": 1747930371, - "description": "Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%),...", - "context_length": 200000, + "name": "Anthropic: Claude Sonnet 4.5", + "created": 1759161676, + "description": "Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...", + "context_length": 1000000, "architecture": { "modality": "text+image+file->text", - "input_modalities": ["image", "text", "file"], + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], "tokenizer": "Claude", "instruct_type": null @@ -4804,16 +5127,19 @@ ] }, "top_provider": { - "context_length": 200000, + "context_length": 1000000, "max_completion_tokens": 64000, "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "include_reasoning", + "max_completion_tokens", "max_tokens", "reasoning", + "response_format", "stop", + "structured_outputs", "temperature", "tool_choice", "tools", @@ -4821,8 +5147,8 @@ "top_p" ], "default_parameters": { - "temperature": null, - "top_p": null, + "temperature": 1, + "top_p": 1, "top_k": null, "frequency_penalty": null, "presence_penalty": null, @@ -4832,64 +5158,92 @@ "knowledge_cutoff": "2025-01-31", "expiration_date": null, "links": { - "details": "/api/v1/models/anthropic/claude-4-sonnet-20250522/endpoints" + "details": "/api/v1/models/anthropic/claude-4.5-sonnet-20250929/endpoints" }, "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1147, - "win_rate": 57.8, - "rank": 64 + "elo": 1158, + "win_rate": 51, + "rank": 66 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1205, + "win_rate": 56.1, + "rank": 23 }, { "arena": "models", "category": "codecategories", - "elo": 1147, - "win_rate": 53.4, - "rank": 78 + "elo": 1183, + "win_rate": 51.5, + "rank": 64 }, { "arena": "models", "category": "dataviz", - "elo": 1164, - "win_rate": 56.5, + "elo": 1167, + "win_rate": 47.4, "rank": 73 }, { "arena": "models", "category": "gamedev", - "elo": 1149, - "win_rate": 54.8, - "rank": 68 + "elo": 1166, + "win_rate": 51.1, + "rank": 69 }, { "arena": "models", "category": "svg", - "elo": 1077, - "win_rate": 51.1, - "rank": 66 + "elo": 1115, + "win_rate": 52.2, + "rank": 56 }, { "arena": "models", "category": "uicomponent", - "elo": 1135, - "win_rate": 57.9, - "rank": 78 + "elo": 1173, + "win_rate": 49.5, + "rank": 68 }, { "arena": "models", "category": "website", - "elo": 1152, - "win_rate": 52.4, - "rank": 83 + "elo": 1190, + "win_rate": 51.8, + "rank": 70 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1050, + "win_rate": 43.7, + "rank": 35 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1137, + "win_rate": 52.9, + "rank": 33 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1059, + "win_rate": 43.2, + "rank": 40 } ], "artificial_analysis": { - "intelligence_index": 18.9, - "coding_index": 37.6, - "agentic_index": null + "intelligence_index": 20.7, + "coding_index": 52.1, + "agentic_index": 15.8 } }, "reasoning": { @@ -4897,10 +5251,10 @@ } }, { - "id": "anthropic/claude-sonnet-4.5", + "id": "anthropic/claude-sonnet-4.5:batch", "canonical_slug": "anthropic/claude-4.5-sonnet-20250929", "hugging_face_id": "", - "name": "Anthropic: Claude Sonnet 4.5", + "name": "Anthropic: Claude Sonnet 4.5 (batch)", "created": 1759161676, "description": "Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...", "context_length": 1000000, @@ -4912,20 +5266,20 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000003", - "completion": "0.000015", + "prompt": "0.0000015", + "completion": "0.0000075", "web_search": "0.01", - "input_cache_read": "0.0000003", - "input_cache_write": "0.00000375", - "input_cache_write_1h": "0.000006", + "input_cache_read": "0.00000015", + "input_cache_write": "0.000001875", + "input_cache_write_1h": "0.000003", "overrides": [ { "min_prompt_tokens": 200000, - "prompt": "0.000006", - "completion": "0.0000225", - "input_cache_read": "0.0000006", - "input_cache_write": "0.0000075", - "input_cache_write_1h": "0.000012" + "prompt": "0.000003", + "completion": "0.00001125", + "input_cache_read": "0.0000003", + "input_cache_write": "0.00000375", + "input_cache_write_1h": "0.000006" } ] }, @@ -4937,7 +5291,6 @@ "per_request_limits": null, "supported_parameters": [ "include_reasoning", - "max_completion_tokens", "max_tokens", "reasoning", "response_format", @@ -4968,235 +5321,79 @@ { "arena": "models", "category": "3d", - "elo": 1165, - "win_rate": 51, - "rank": 58 - }, - { - "arena": "models", - "category": "asciiart", - "elo": 1213, - "win_rate": 56.1, - "rank": 21 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1187, - "win_rate": 51.5, - "rank": 55 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1174, - "win_rate": 47.4, - "rank": 65 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1177, - "win_rate": 51.1, - "rank": 59 - }, - { - "arena": "models", - "category": "svg", - "elo": 1114, - "win_rate": 52.2, - "rank": 55 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1178, - "win_rate": 49.5, - "rank": 62 - }, - { - "arena": "models", - "category": "website", - "elo": 1196, - "win_rate": 51.8, - "rank": 61 - }, - { - "arena": "agents", - "category": "fullstack", - "elo": 1049, - "win_rate": 43.7, - "rank": 35 - }, - { - "arena": "agents", - "category": "mobileapps", - "elo": 1134, - "win_rate": 52.9, - "rank": 31 - }, - { - "arena": "agents", - "category": "webapps", - "elo": 1053, - "win_rate": 43.2, - "rank": 36 - } - ], - "artificial_analysis": { - "intelligence_index": 20.7, - "coding_index": 52.1, - "agentic_index": 15.8 - } - }, - "reasoning": { - "mandatory": false - } - }, - { - "id": "anthropic/claude-sonnet-4.5:batch", - "canonical_slug": "anthropic/claude-4.5-sonnet-20250929", - "hugging_face_id": "", - "name": "Anthropic: Claude Sonnet 4.5 (batch)", - "created": 1759161676, - "description": "Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...", - "context_length": 1000000, - "architecture": { - "modality": "text+image+file->text", - "input_modalities": ["text", "image", "file"], - "output_modalities": ["text"], - "tokenizer": "Claude", - "instruct_type": null - }, - "pricing": { - "prompt": "0.0000015", - "completion": "0.0000075", - "web_search": "0.01", - "input_cache_read": "0.00000015", - "input_cache_write": "0.000001875", - "input_cache_write_1h": "0.000003", - "overrides": [ - { - "min_prompt_tokens": 200000, - "prompt": "0.000003", - "completion": "0.00001125", - "input_cache_read": "0.0000003", - "input_cache_write": "0.00000375", - "input_cache_write_1h": "0.000006" - } - ] - }, - "top_provider": { - "context_length": 1000000, - "max_completion_tokens": 64000, - "is_moderated": true - }, - "per_request_limits": null, - "supported_parameters": [ - "include_reasoning", - "max_tokens", - "reasoning", - "response_format", - "stop", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_k", - "top_p" - ], - "default_parameters": { - "temperature": 1, - "top_p": 1, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": "2025-01-31", - "expiration_date": null, - "links": { - "details": "/api/v1/models/anthropic/claude-4.5-sonnet-20250929/endpoints" - }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1165, + "elo": 1158, "win_rate": 51, - "rank": 58 + "rank": 66 }, { "arena": "models", "category": "asciiart", - "elo": 1213, + "elo": 1205, "win_rate": 56.1, - "rank": 21 + "rank": 23 }, { "arena": "models", "category": "codecategories", - "elo": 1187, + "elo": 1183, "win_rate": 51.5, - "rank": 55 + "rank": 64 }, { "arena": "models", "category": "dataviz", - "elo": 1174, + "elo": 1167, "win_rate": 47.4, - "rank": 65 + "rank": 73 }, { "arena": "models", "category": "gamedev", - "elo": 1177, + "elo": 1166, "win_rate": 51.1, - "rank": 59 + "rank": 69 }, { "arena": "models", "category": "svg", - "elo": 1114, + "elo": 1115, "win_rate": 52.2, - "rank": 55 + "rank": 56 }, { "arena": "models", "category": "uicomponent", - "elo": 1178, + "elo": 1173, "win_rate": 49.5, - "rank": 62 + "rank": 68 }, { "arena": "models", "category": "website", - "elo": 1196, + "elo": 1190, "win_rate": 51.8, - "rank": 61 + "rank": 70 }, { "arena": "agents", "category": "fullstack", - "elo": 1049, + "elo": 1050, "win_rate": 43.7, "rank": 35 }, { "arena": "agents", "category": "mobileapps", - "elo": 1134, + "elo": 1137, "win_rate": 52.9, - "rank": 31 + "rank": 33 }, { "arena": "agents", "category": "webapps", - "elo": 1053, + "elo": 1059, "win_rate": 43.2, - "rank": 36 + "rank": 40 } ], "artificial_analysis": { @@ -5273,14 +5470,14 @@ { "arena": "agents", "category": "androidnative", - "elo": 1211, - "win_rate": 62, - "rank": 13 + "elo": 1196, + "win_rate": 62.1, + "rank": 14 }, { "arena": "agents", "category": "fullstack", - "elo": 1211, + "elo": 1213, "win_rate": 64.3, "rank": 14 }, @@ -5294,72 +5491,72 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1209, + "elo": 1212, "win_rate": 63.6, - "rank": 14 + "rank": 15 }, { "arena": "agents", "category": "webapps", - "elo": 1183, + "elo": 1190, "win_rate": 57, - "rank": 23 + "rank": 27 }, { "arena": "models", "category": "3d", - "elo": 1242, + "elo": 1234, "win_rate": 57.6, - "rank": 32 + "rank": 39 }, { "arena": "models", "category": "asciiart", - "elo": 1244, + "elo": 1235, "win_rate": 60.1, - "rank": 18 + "rank": 19 }, { "arena": "models", "category": "codecategories", - "elo": 1280, + "elo": 1276, "win_rate": 59.4, - "rank": 22 + "rank": 24 }, { "arena": "models", "category": "dataviz", - "elo": 1285, - "win_rate": 58.2, - "rank": 17 + "elo": 1278, + "win_rate": 58.3, + "rank": 22 }, { "arena": "models", "category": "gamedev", - "elo": 1269, + "elo": 1259, "win_rate": 58.8, - "rank": 28 + "rank": 36 }, { "arena": "models", "category": "svg", - "elo": 1196, + "elo": 1197, "win_rate": 58.7, - "rank": 24 + "rank": 25 }, { "arena": "models", "category": "uicomponent", - "elo": 1278, + "elo": 1272, "win_rate": 58.3, - "rank": 26 + "rank": 32 }, { "arena": "models", "category": "website", - "elo": 1291, + "elo": 1285, "win_rate": 60, - "rank": 17 + "rank": 22 } ], "artificial_analysis": { @@ -5370,7 +5567,7 @@ }, "reasoning": { "mandatory": false, - "supported_efforts": ["max", "high", "medium", "low"], + "supported_efforts": ["max", "high", "medium", "low", "none"], "default_effort": "medium" } }, @@ -5436,14 +5633,14 @@ { "arena": "agents", "category": "androidnative", - "elo": 1211, - "win_rate": 62, - "rank": 13 + "elo": 1196, + "win_rate": 62.1, + "rank": 14 }, { "arena": "agents", "category": "fullstack", - "elo": 1211, + "elo": 1213, "win_rate": 64.3, "rank": 14 }, @@ -5457,72 +5654,72 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1209, + "elo": 1212, "win_rate": 63.6, - "rank": 14 + "rank": 15 }, { "arena": "agents", "category": "webapps", - "elo": 1183, + "elo": 1190, "win_rate": 57, - "rank": 23 + "rank": 27 }, { "arena": "models", "category": "3d", - "elo": 1242, + "elo": 1234, "win_rate": 57.6, - "rank": 32 + "rank": 39 }, { "arena": "models", "category": "asciiart", - "elo": 1244, + "elo": 1235, "win_rate": 60.1, - "rank": 18 + "rank": 19 }, { "arena": "models", "category": "codecategories", - "elo": 1280, + "elo": 1276, "win_rate": 59.4, - "rank": 22 + "rank": 24 }, { "arena": "models", "category": "dataviz", - "elo": 1285, - "win_rate": 58.2, - "rank": 17 + "elo": 1278, + "win_rate": 58.3, + "rank": 22 }, { "arena": "models", "category": "gamedev", - "elo": 1269, + "elo": 1259, "win_rate": 58.8, - "rank": 28 + "rank": 36 }, { "arena": "models", "category": "svg", - "elo": 1196, + "elo": 1197, "win_rate": 58.7, - "rank": 24 + "rank": 25 }, { "arena": "models", "category": "uicomponent", - "elo": 1278, + "elo": 1272, "win_rate": 58.3, - "rank": 26 + "rank": 32 }, { "arena": "models", "category": "website", - "elo": 1291, + "elo": 1285, "win_rate": 60, - "rank": 17 + "rank": 22 } ], "artificial_analysis": { @@ -5533,7 +5730,7 @@ }, "reasoning": { "mandatory": false, - "supported_efforts": ["max", "high", "medium", "low"], + "supported_efforts": ["max", "high", "medium", "low", "none"], "default_effort": "medium" } }, @@ -5591,21 +5788,28 @@ { "arena": "agents", "category": "agenticgamedev", - "elo": 1226, - "win_rate": 52.3, + "elo": 1227, + "win_rate": 52.2, "rank": 7 }, { "arena": "agents", "category": "androidnative", - "elo": 1237, - "win_rate": 54.4, + "elo": 1226, + "win_rate": 54.7, "rank": 9 }, + { + "arena": "agents", + "category": "blender3d", + "elo": 1200, + "win_rate": 40.3, + "rank": 1 + }, { "arena": "agents", "category": "fullstack", - "elo": 1248, + "elo": 1249, "win_rate": 53.7, "rank": 9 }, @@ -5619,86 +5823,93 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1217, + "elo": 1218, "win_rate": 53.7, "rank": 5 }, { "arena": "agents", "category": "mobileapps", - "elo": 1211, - "win_rate": 50.9, - "rank": 13 + "elo": 1215, + "win_rate": 51.2, + "rank": 14 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1216, - "win_rate": 50.1, + "elo": 1214, + "win_rate": 50.2, "rank": 13 }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1042, + "win_rate": 44.8, + "rank": 17 + }, { "arena": "agents", "category": "webapps", - "elo": 1237, - "win_rate": 53.3, - "rank": 10 + "elo": 1245, + "win_rate": 53.2, + "rank": 13 }, { "arena": "models", "category": "3d", - "elo": 1269, - "win_rate": 54.3, - "rank": 21 + "elo": 1261, + "win_rate": 53.9, + "rank": 28 }, { "arena": "models", "category": "asciiart", - "elo": 1218, - "win_rate": 51.7, - "rank": 20 + "elo": 1207, + "win_rate": 51.3, + "rank": 22 }, { "arena": "models", "category": "codecategories", - "elo": 1282, - "win_rate": 53.1, - "rank": 18 + "elo": 1276, + "win_rate": 52.5, + "rank": 25 }, { "arena": "models", "category": "dataviz", - "elo": 1254, - "win_rate": 52.8, - "rank": 30 + "elo": 1251, + "win_rate": 52.9, + "rank": 34 }, { "arena": "models", "category": "gamedev", - "elo": 1292, - "win_rate": 52.7, - "rank": 16 + "elo": 1278, + "win_rate": 51.6, + "rank": 24 }, { "arena": "models", "category": "svg", - "elo": 1193, - "win_rate": 49.9, - "rank": 28 + "elo": 1194, + "win_rate": 49.6, + "rank": 29 }, { "arena": "models", "category": "uicomponent", - "elo": 1286, - "win_rate": 54.1, - "rank": 22 + "elo": 1280, + "win_rate": 53.9, + "rank": 26 }, { "arena": "models", "category": "website", - "elo": 1281, - "win_rate": 52.8, - "rank": 21 + "elo": 1274, + "win_rate": 52.2, + "rank": 26 } ], "artificial_analysis": { @@ -5710,7 +5921,7 @@ "reasoning": { "mandatory": false, "default_enabled": true, - "supported_efforts": ["max", "xhigh", "high", "medium", "low"], + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], "default_effort": "high" } }, @@ -5767,21 +5978,28 @@ { "arena": "agents", "category": "agenticgamedev", - "elo": 1226, - "win_rate": 52.3, + "elo": 1227, + "win_rate": 52.2, "rank": 7 }, { "arena": "agents", "category": "androidnative", - "elo": 1237, - "win_rate": 54.4, + "elo": 1226, + "win_rate": 54.7, "rank": 9 }, + { + "arena": "agents", + "category": "blender3d", + "elo": 1200, + "win_rate": 40.3, + "rank": 1 + }, { "arena": "agents", "category": "fullstack", - "elo": 1248, + "elo": 1249, "win_rate": 53.7, "rank": 9 }, @@ -5795,86 +6013,93 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1217, + "elo": 1218, "win_rate": 53.7, "rank": 5 }, { "arena": "agents", "category": "mobileapps", - "elo": 1211, - "win_rate": 50.9, - "rank": 13 + "elo": 1215, + "win_rate": 51.2, + "rank": 14 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1216, - "win_rate": 50.1, + "elo": 1214, + "win_rate": 50.2, "rank": 13 }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1042, + "win_rate": 44.8, + "rank": 17 + }, { "arena": "agents", "category": "webapps", - "elo": 1237, - "win_rate": 53.3, - "rank": 10 + "elo": 1245, + "win_rate": 53.2, + "rank": 13 }, { "arena": "models", "category": "3d", - "elo": 1269, - "win_rate": 54.3, - "rank": 21 + "elo": 1261, + "win_rate": 53.9, + "rank": 28 }, { "arena": "models", "category": "asciiart", - "elo": 1218, - "win_rate": 51.7, - "rank": 20 + "elo": 1207, + "win_rate": 51.3, + "rank": 22 }, { "arena": "models", "category": "codecategories", - "elo": 1282, - "win_rate": 53.1, - "rank": 18 + "elo": 1276, + "win_rate": 52.5, + "rank": 25 }, { "arena": "models", "category": "dataviz", - "elo": 1254, - "win_rate": 52.8, - "rank": 30 + "elo": 1251, + "win_rate": 52.9, + "rank": 34 }, { "arena": "models", "category": "gamedev", - "elo": 1292, - "win_rate": 52.7, - "rank": 16 + "elo": 1278, + "win_rate": 51.6, + "rank": 24 }, { "arena": "models", "category": "svg", - "elo": 1193, - "win_rate": 49.9, - "rank": 28 + "elo": 1194, + "win_rate": 49.6, + "rank": 29 }, { "arena": "models", "category": "uicomponent", - "elo": 1286, - "win_rate": 54.1, - "rank": 22 + "elo": 1280, + "win_rate": 53.9, + "rank": 26 }, { "arena": "models", "category": "website", - "elo": 1281, - "win_rate": 52.8, - "rank": 21 + "elo": 1274, + "win_rate": 52.2, + "rank": 26 } ], "artificial_analysis": { @@ -5886,7 +6111,7 @@ "reasoning": { "mandatory": false, "default_enabled": true, - "supported_efforts": ["max", "xhigh", "high", "medium", "low"], + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], "default_effort": "high" } }, @@ -5909,14 +6134,14 @@ "prompt": "0.000002", "completion": "0.00001", "web_search": "0.01", - "input_cache_read": "0.0000002", + "input_cache_read": "0.0000001", "input_cache_write": "0.0000025", "input_cache_write_1h": "0.000004" }, "top_provider": { "context_length": 1000000, "max_completion_tokens": 128000, - "is_moderated": true + "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ @@ -5928,7 +6153,6 @@ "response_format", "stop", "structured_outputs", - "temperature", "tool_choice", "tools", "verbosity" @@ -5942,26 +6166,68 @@ }, "benchmarks": { "design_arena": [ + { + "arena": "agents", + "category": "mobileapps", + "elo": 1255, + "win_rate": 55.9, + "rank": 6 + }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1237, + "win_rate": 51.7, + "rank": 6 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1306, + "win_rate": 60.5, + "rank": 3 + }, + { + "arena": "models", + "category": "3d", + "elo": 1452, + "win_rate": 69.2, + "rank": 3 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1364, + "win_rate": 60.7, + "rank": 3 + }, { "arena": "models", "category": "dataviz", - "elo": 1351, - "win_rate": 63.6, - "rank": 5 + "elo": 1394, + "win_rate": 67.8, + "rank": 2 }, { "arena": "models", - "category": "uicomponent", - "elo": 1400, - "win_rate": 66.5, + "category": "gamedev", + "elo": 1471, + "win_rate": 72.5, "rank": 1 }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1364, + "win_rate": 61.5, + "rank": 3 + }, { "arena": "models", "category": "website", - "elo": 1322, - "win_rate": 53.2, - "rank": 4 + "elo": 1327, + "win_rate": 56.1, + "rank": 5 } ], "artificial_analysis": { @@ -5995,7 +6261,7 @@ "prompt": "0.000001", "completion": "0.000005", "web_search": "0.01", - "input_cache_read": "0.0000001", + "input_cache_read": "0.00000005", "input_cache_write": "0.00000125", "input_cache_write_1h": "0.000002" }, @@ -6026,26 +6292,68 @@ }, "benchmarks": { "design_arena": [ + { + "arena": "agents", + "category": "mobileapps", + "elo": 1255, + "win_rate": 55.9, + "rank": 6 + }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1237, + "win_rate": 51.7, + "rank": 6 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1306, + "win_rate": 60.5, + "rank": 3 + }, + { + "arena": "models", + "category": "3d", + "elo": 1452, + "win_rate": 69.2, + "rank": 3 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1364, + "win_rate": 60.7, + "rank": 3 + }, { "arena": "models", "category": "dataviz", - "elo": 1351, - "win_rate": 63.6, - "rank": 5 + "elo": 1394, + "win_rate": 67.8, + "rank": 2 }, { "arena": "models", - "category": "uicomponent", - "elo": 1400, - "win_rate": 66.5, + "category": "gamedev", + "elo": 1471, + "win_rate": 72.5, "rank": 1 }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1364, + "win_rate": 61.5, + "rank": 3 + }, { "arena": "models", "category": "website", - "elo": 1322, - "win_rate": 53.2, - "rank": 4 + "elo": 1327, + "win_rate": 56.1, + "rank": 5 } ], "artificial_analysis": { @@ -6060,59 +6368,6 @@ "default_effort": "high" } }, - { - "id": "apodex/apodex-1.1-mini:free", - "canonical_slug": "apodex/apodex-1.1-mini-20261001", - "hugging_face_id": null, - "name": "Apodex: Apodex 1.1 Mini (free)", - "created": 1790875335, - "description": "Apodex 1.1 Mini is a reasoning-first model from Apodex, built for complex, long-horizon research and forecasting tasks. It works directly with files, data, code, and tools to produce verifiable results,...", - "context_length": 262144, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Other", - "instruct_type": null - }, - "pricing": { - "prompt": "0", - "completion": "0" - }, - "top_provider": { - "context_length": 262144, - "max_completion_tokens": 235929, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "include_reasoning", - "max_tokens", - "presence_penalty", - "reasoning", - "repetition_penalty", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_k", - "top_p" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": null, - "links": { - "details": "/api/v1/models/apodex/apodex-1.1-mini-20261001/endpoints" - }, - "reasoning": { - "mandatory": false - } - }, { "id": "arcee-ai/trinity-large-thinking", "canonical_slug": "arcee-ai/trinity-large-thinking", @@ -6168,58 +6423,58 @@ { "arena": "models", "category": "3d", - "elo": 1089, + "elo": 1082, "win_rate": 41.3, - "rank": 86 + "rank": 93 }, { "arena": "models", "category": "asciiart", - "elo": 1050, + "elo": 1041, "win_rate": 37.1, - "rank": 66 + "rank": 68 }, { "arena": "models", "category": "codecategories", - "elo": 1121, + "elo": 1117, "win_rate": 40.1, - "rank": 86 + "rank": 97 }, { "arena": "models", "category": "dataviz", - "elo": 1104, + "elo": 1098, "win_rate": 39.3, - "rank": 93 + "rank": 100 }, { "arena": "models", "category": "gamedev", - "elo": 1089, + "elo": 1079, "win_rate": 38.4, - "rank": 93 + "rank": 106 }, { "arena": "models", "category": "svg", - "elo": 1015, + "elo": 1017, "win_rate": 35.2, - "rank": 81 + "rank": 82 }, { "arena": "models", "category": "uicomponent", - "elo": 1052, + "elo": 1045, "win_rate": 32.6, - "rank": 98 + "rank": 106 }, { "arena": "models", "category": "website", - "elo": 1142, + "elo": 1137, "win_rate": 41.3, - "rank": 87 + "rank": 98 } ], "artificial_analysis": { @@ -6232,55 +6487,6 @@ "mandatory": true } }, - { - "id": "baidu/ernie-4.5-vl-424b-a47b", - "canonical_slug": "baidu/ernie-4.5-vl-424b-a47b", - "hugging_face_id": "baidu/ERNIE-4.5-VL-424B-A47B-PT", - "name": "Baidu: ERNIE 4.5 VL 424B A47B ", - "created": 1751300903, - "description": "ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B active per token. It is trained jointly on text and image data...", - "context_length": 123000, - "architecture": { - "modality": "text+image->text", - "input_modalities": ["image", "text"], - "output_modalities": ["text"], - "tokenizer": "Other", - "instruct_type": null - }, - "pricing": { - "prompt": "0.00000042", - "completion": "0.00000125" - }, - "top_provider": { - "context_length": 123000, - "max_completion_tokens": 16000, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "include_reasoning", - "max_tokens", - "presence_penalty", - "reasoning", - "repetition_penalty", - "seed", - "stop", - "temperature", - "top_k", - "top_p" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": "2025-03-31", - "expiration_date": "2026-10-08", - "links": { - "details": "/api/v1/models/baidu/ernie-4.5-vl-424b-a47b/endpoints" - }, - "reasoning": { - "mandatory": false - } - }, { "id": "bytedance-seed/seed-1.6", "canonical_slug": "bytedance-seed/seed-1.6-20250625", @@ -6505,7 +6711,7 @@ }, "reasoning": { "mandatory": false, - "supported_efforts": ["high", "medium", "low"], + "supported_efforts": ["high", "medium", "low", "none"], "default_effort": "medium" } }, @@ -6571,7 +6777,7 @@ }, "reasoning": { "mandatory": false, - "supported_efforts": ["high", "medium", "low", "minimal"], + "supported_efforts": ["high", "medium", "low", "minimal", "none"], "default_effort": "medium" } }, @@ -6634,7 +6840,7 @@ }, "reasoning": { "mandatory": false, - "supported_efforts": ["high", "medium", "low", "minimal"], + "supported_efforts": ["high", "medium", "low", "minimal", "none"], "default_effort": "medium" } }, @@ -7093,51 +7299,51 @@ { "arena": "models", "category": "3d", - "elo": 1095, + "elo": 1087, "win_rate": 50.5, - "rank": 83 + "rank": 91 }, { "arena": "models", "category": "codecategories", - "elo": 1112, + "elo": 1108, "win_rate": 48.4, - "rank": 91 + "rank": 102 }, { "arena": "models", "category": "dataviz", - "elo": 1095, + "elo": 1089, "win_rate": 50, - "rank": 96 + "rank": 103 }, { "arena": "models", "category": "gamedev", - "elo": 1064, + "elo": 1053, "win_rate": 43.7, - "rank": 98 + "rank": 112 }, { "arena": "models", "category": "svg", - "elo": 975, + "elo": 977, "win_rate": 38.8, - "rank": 87 + "rank": 88 }, { "arena": "models", "category": "uicomponent", - "elo": 1100, + "elo": 1093, "win_rate": 52.7, - "rank": 89 + "rank": 97 }, { "arena": "models", "category": "website", - "elo": 1126, + "elo": 1120, "win_rate": 48.5, - "rank": 92 + "rank": 103 } ] } @@ -7257,51 +7463,51 @@ { "arena": "models", "category": "3d", - "elo": 1085, + "elo": 1077, "win_rate": 47.9, - "rank": 89 + "rank": 98 }, { "arena": "models", "category": "codecategories", - "elo": 1116, + "elo": 1112, "win_rate": 47.8, - "rank": 89 + "rank": 100 }, { "arena": "models", "category": "dataviz", - "elo": 1102, + "elo": 1096, "win_rate": 46.2, - "rank": 95 + "rank": 102 }, { "arena": "models", "category": "gamedev", - "elo": 1094, + "elo": 1084, "win_rate": 47.1, - "rank": 89 + "rank": 103 }, { "arena": "models", "category": "svg", - "elo": 966, + "elo": 967, "win_rate": 38.2, - "rank": 88 + "rank": 89 }, { "arena": "models", "category": "uicomponent", - "elo": 1092, + "elo": 1085, "win_rate": 47.1, - "rank": 91 + "rank": 100 }, { "arena": "models", "category": "website", - "elo": 1129, + "elo": 1122, "win_rate": 48, - "rank": 90 + "rank": 102 } ], "artificial_analysis": { @@ -7314,73 +7520,6 @@ "mandatory": false } }, - { - "id": "deepseek/deepseek-r1", - "canonical_slug": "deepseek/deepseek-r1", - "hugging_face_id": "deepseek-ai/DeepSeek-R1", - "name": "DeepSeek: R1", - "created": 1737381095, - "description": "DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass....", - "context_length": 64000, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "DeepSeek", - "instruct_type": "deepseek-r1" - }, - "pricing": { - "prompt": "0.0000007", - "completion": "0.0000025" - }, - "top_provider": { - "context_length": 64000, - "max_completion_tokens": 16000, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "include_reasoning", - "max_tokens", - "presence_penalty", - "reasoning", - "repetition_penalty", - "response_format", - "seed", - "stop", - "temperature", - "tool_choice", - "tools", - "top_k", - "top_p" - ], - "default_parameters": { - "temperature": null, - "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": "2024-07-31", - "expiration_date": null, - "links": { - "details": "/api/v1/models/deepseek/deepseek-r1/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 11.4, - "coding_index": 24.6, - "agentic_index": 1.1 - } - }, - "reasoning": { - "mandatory": true - } - }, { "id": "deepseek/deepseek-r1-0528", "canonical_slug": "deepseek/deepseek-r1-0528", @@ -7444,51 +7583,51 @@ { "arena": "models", "category": "3d", - "elo": 1119, + "elo": 1111, "win_rate": 53.3, - "rank": 78 + "rank": 86 }, { "arena": "models", "category": "codecategories", - "elo": 1144, + "elo": 1139, "win_rate": 52.6, - "rank": 81 + "rank": 93 }, { "arena": "models", "category": "dataviz", - "elo": 1188, + "elo": 1182, "win_rate": 60.9, - "rank": 57 + "rank": 64 }, { "arena": "models", "category": "gamedev", - "elo": 1108, + "elo": 1097, "win_rate": 49.3, - "rank": 84 + "rank": 98 }, { "arena": "models", "category": "svg", - "elo": 1038, + "elo": 1039, "win_rate": 48.7, - "rank": 74 + "rank": 75 }, { "arena": "models", "category": "uicomponent", - "elo": 1109, + "elo": 1103, "win_rate": 54.9, - "rank": 84 + "rank": 93 }, { "arena": "models", "category": "website", - "elo": 1154, + "elo": 1149, "win_rate": 52.7, - "rank": 81 + "rank": 92 } ], "artificial_analysis": { @@ -7556,51 +7695,51 @@ { "arena": "models", "category": "3d", - "elo": 1148, + "elo": 1141, "win_rate": 56, - "rank": 62 + "rank": 70 }, { "arena": "models", "category": "codecategories", - "elo": 1179, + "elo": 1175, "win_rate": 56, - "rank": 61 + "rank": 70 }, { "arena": "models", "category": "dataviz", - "elo": 1174, + "elo": 1168, "win_rate": 53.4, - "rank": 66 + "rank": 72 }, { "arena": "models", "category": "gamedev", - "elo": 1141, + "elo": 1131, "win_rate": 52.5, - "rank": 76 + "rank": 88 }, { "arena": "models", "category": "svg", - "elo": 1064, + "elo": 1065, "win_rate": 50.1, "rank": 70 }, { "arena": "models", "category": "uicomponent", - "elo": 1189, + "elo": 1182, "win_rate": 59.5, - "rank": 57 + "rank": 64 }, { "arena": "models", "category": "website", - "elo": 1193, + "elo": 1187, "win_rate": 56.4, - "rank": 63 + "rank": 71 } ], "artificial_analysis": { @@ -7679,58 +7818,58 @@ { "arena": "models", "category": "3d", - "elo": 1140, + "elo": 1133, "win_rate": 49.4, - "rank": 66 + "rank": 74 }, { "arena": "models", "category": "asciiart", - "elo": 1091, + "elo": 1083, "win_rate": 40.5, - "rank": 63 + "rank": 65 }, { "arena": "models", "category": "codecategories", - "elo": 1168, + "elo": 1164, "win_rate": 49.3, - "rank": 70 + "rank": 79 }, { "arena": "models", "category": "dataviz", - "elo": 1165, + "elo": 1158, "win_rate": 48.2, - "rank": 71 + "rank": 79 }, { "arena": "models", "category": "gamedev", - "elo": 1142, + "elo": 1132, "win_rate": 46.5, - "rank": 74 + "rank": 87 }, { "arena": "models", "category": "svg", - "elo": 1031, + "elo": 1033, "win_rate": 40.8, - "rank": 76 + "rank": 77 }, { "arena": "models", "category": "uicomponent", - "elo": 1156, + "elo": 1149, "win_rate": 46.8, - "rank": 70 + "rank": 78 }, { "arena": "models", "category": "website", - "elo": 1181, + "elo": 1175, "win_rate": 50.2, - "rank": 70 + "rank": 79 } ], "artificial_analysis": { @@ -7798,51 +7937,51 @@ { "arena": "models", "category": "3d", - "elo": 1156, + "elo": 1148, "win_rate": 56.4, - "rank": 61 + "rank": 68 }, { "arena": "models", "category": "codecategories", - "elo": 1175, + "elo": 1171, "win_rate": 54.2, - "rank": 63 + "rank": 72 }, { "arena": "models", "category": "dataviz", - "elo": 1159, + "elo": 1152, "win_rate": 50.6, - "rank": 74 + "rank": 81 }, { "arena": "models", "category": "gamedev", - "elo": 1155, + "elo": 1144, "win_rate": 53, - "rank": 65 + "rank": 77 }, { "arena": "models", "category": "svg", - "elo": 1031, + "elo": 1032, "win_rate": 42, - "rank": 77 + "rank": 78 }, { "arena": "models", "category": "uicomponent", - "elo": 1173, + "elo": 1167, "win_rate": 53.3, - "rank": 63 + "rank": 70 }, { "arena": "models", "category": "website", - "elo": 1185, + "elo": 1179, "win_rate": 54.3, - "rank": 67 + "rank": 76 } ], "artificial_analysis": { @@ -7871,13 +8010,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000003", - "completion": "0.00000128", - "input_cache_read": "0.00000003" + "prompt": "0.000000091", + "completion": "0.000000182", + "input_cache_read": "0.0000000182" }, "top_provider": { - "context_length": 1048576, - "max_completion_tokens": 943718, + "context_length": 1048575, + "max_completion_tokens": 943717, "is_moderated": false }, "per_request_limits": null, @@ -7917,58 +8056,58 @@ { "arena": "models", "category": "3d", - "elo": 1196, + "elo": 1189, "win_rate": 49.3, - "rank": 47 + "rank": 55 }, { "arena": "models", "category": "asciiart", - "elo": 1119, - "win_rate": 42.8, - "rank": 56 + "elo": 1109, + "win_rate": 42.7, + "rank": 58 }, { "arena": "models", "category": "codecategories", - "elo": 1211, + "elo": 1205, "win_rate": 48.9, - "rank": 49 + "rank": 59 }, { "arena": "models", "category": "dataviz", - "elo": 1134, + "elo": 1127, "win_rate": 40.7, - "rank": 84 + "rank": 92 }, { "arena": "models", "category": "gamedev", - "elo": 1207, + "elo": 1197, "win_rate": 50.2, - "rank": 46 + "rank": 57 }, { "arena": "models", "category": "svg", - "elo": 1155, + "elo": 1156, "win_rate": 48.4, - "rank": 40 + "rank": 41 }, { "arena": "models", "category": "uicomponent", - "elo": 1171, + "elo": 1165, "win_rate": 44.7, - "rank": 66 + "rank": 73 }, { "arena": "models", "category": "website", - "elo": 1214, + "elo": 1208, "win_rate": 49.1, - "rank": 52 + "rank": 62 } ], "artificial_analysis": { @@ -7979,7 +8118,7 @@ }, "reasoning": { "mandatory": false, - "supported_efforts": ["xhigh", "high"], + "supported_efforts": ["xhigh", "high", "none"], "default_effort": "high" } }, @@ -7999,13 +8138,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000000018", - "completion": "0.00000128", - "input_cache_read": "0.000000018" + "prompt": "0.00000044", + "completion": "0.00000132", + "input_cache_read": "0.000000014" }, "top_provider": { "context_length": 1048576, - "max_completion_tokens": 943718, + "max_completion_tokens": 131072, "is_moderated": false }, "per_request_limits": null, @@ -8045,58 +8184,58 @@ { "arena": "models", "category": "3d", - "elo": 1216, - "win_rate": 48.6, - "rank": 39 + "elo": 1209, + "win_rate": 48.7, + "rank": 45 }, { "arena": "models", "category": "asciiart", - "elo": 1097, + "elo": 1090, "win_rate": 33.3, - "rank": 62 + "rank": 63 }, { "arena": "models", "category": "codecategories", - "elo": 1234, + "elo": 1230, "win_rate": 46.4, - "rank": 42 + "rank": 51 }, { "arena": "models", "category": "dataviz", - "elo": 1188, + "elo": 1180, "win_rate": 41.1, - "rank": 58 + "rank": 65 }, { "arena": "models", "category": "gamedev", - "elo": 1218, + "elo": 1208, "win_rate": 44.6, - "rank": 43 + "rank": 53 }, { "arena": "models", "category": "svg", - "elo": 1186, + "elo": 1185, "win_rate": 45.1, - "rank": 30 + "rank": 31 }, { "arena": "models", "category": "uicomponent", - "elo": 1242, + "elo": 1235, "win_rate": 46.8, - "rank": 41 + "rank": 48 }, { "arena": "models", "category": "website", - "elo": 1243, + "elo": 1238, "win_rate": 46.7, - "rank": 41 + "rank": 51 } ], "artificial_analysis": { @@ -8108,7 +8247,7 @@ "reasoning": { "mandatory": false, "default_enabled": true, - "supported_efforts": ["max", "high", "low"], + "supported_efforts": ["max", "high", "low", "none"], "default_effort": "high" } }, @@ -8178,7 +8317,7 @@ "reasoning": { "mandatory": false, "default_enabled": true, - "supported_efforts": ["max", "high", "low"], + "supported_efforts": ["max", "high", "low", "none"], "default_effort": "high" } }, @@ -8198,9 +8337,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000002088", - "completion": "0.0000004176", - "input_cache_read": "0.0000000174" + "prompt": "0.00000095526", + "completion": "0.00000191052", + "input_cache_read": "0.000000079605" }, "top_provider": { "context_length": 1024000, @@ -8262,63 +8401,63 @@ "category": "webapps", "elo": 1000, "win_rate": 26.4, - "rank": 41 + "rank": 45 }, { "arena": "models", "category": "3d", - "elo": 1262, + "elo": 1254, "win_rate": 56.8, - "rank": 24 + "rank": 31 }, { "arena": "models", "category": "asciiart", - "elo": 1157, + "elo": 1149, "win_rate": 46.4, - "rank": 40 + "rank": 44 }, { "arena": "models", "category": "codecategories", - "elo": 1246, + "elo": 1240, "win_rate": 51.9, - "rank": 37 + "rank": 45 }, { "arena": "models", "category": "dataviz", - "elo": 1210, + "elo": 1203, "win_rate": 48.7, - "rank": 50 + "rank": 58 }, { "arena": "models", "category": "gamedev", - "elo": 1239, + "elo": 1229, "win_rate": 52.3, - "rank": 36 + "rank": 43 }, { "arena": "models", "category": "svg", - "elo": 1139, + "elo": 1140, "win_rate": 45.4, - "rank": 48 + "rank": 49 }, { "arena": "models", "category": "uicomponent", - "elo": 1228, + "elo": 1222, "win_rate": 50.6, - "rank": 45 + "rank": 52 }, { "arena": "models", "category": "website", - "elo": 1241, + "elo": 1235, "win_rate": 50.5, - "rank": 42 + "rank": 53 } ], "artificial_analysis": { @@ -8329,7 +8468,7 @@ }, "reasoning": { "mandatory": false, - "supported_efforts": ["xhigh", "high"], + "supported_efforts": ["xhigh", "high", "none"], "default_effort": "high" } }, @@ -8449,7 +8588,7 @@ }, "reasoning": { "mandatory": false, - "supported_efforts": ["max", "high", "low"], + "supported_efforts": ["max", "high", "low", "none"], "default_effort": "high" } }, @@ -8469,9 +8608,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000005", + "prompt": "0.0000003", "completion": "0.0000012", - "input_cache_read": "0.00000002" + "input_cache_read": "0.000000006" }, "top_provider": { "context_length": 1048576, @@ -8510,6 +8649,183 @@ }, "benchmarks": { "design_arena": [], + "artificial_analysis": { + "intelligence_index": 24.7, + "coding_index": null, + "agentic_index": null + } + }, + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["max", "high", "low", "none"], + "default_effort": "high" + } + }, + { + "id": "deepseek/deepseek-v4.1-flash-1017", + "canonical_slug": "deepseek/deepseek-v4.1-flash-20261017", + "hugging_face_id": "deepseek-ai/DeepSeek-V4.1-Flash-1017", + "name": "DeepSeek: DeepSeek V4.1 Flash 1017", + "created": 1792225624, + "description": "DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...", + "context_length": 1048576, + "architecture": { + "modality": "text+image->text", + "input_modalities": ["text", "image"], + "output_modalities": ["text"], + "tokenizer": "DeepSeek", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000015", + "completion": "0.0000006", + "input_cache_read": "0.000000003", + "overrides": [ + { + "utc_days": ["saturday", "sunday"], + "prompt": "0.00000015", + "completion": "0.0000006", + "input_cache_read": "0.000000003" + }, + { + "utc_days": ["monday", "tuesday", "wednesday", "thursday", "friday"], + "utc_start": 0, + "utc_end": 100, + "prompt": "0.00000015", + "completion": "0.0000006", + "input_cache_read": "0.000000003" + }, + { + "utc_days": ["monday", "tuesday", "wednesday", "thursday", "friday"], + "utc_start": 100, + "utc_end": 400, + "prompt": "0.0000003", + "completion": "0.0000012", + "input_cache_read": "0.000000006" + }, + { + "utc_days": ["monday", "tuesday", "wednesday", "thursday", "friday"], + "utc_start": 400, + "utc_end": 600, + "prompt": "0.00000015", + "completion": "0.0000006", + "input_cache_read": "0.000000003" + }, + { + "utc_days": ["monday", "tuesday", "wednesday", "thursday", "friday"], + "utc_start": 600, + "utc_end": 1000, + "prompt": "0.0000003", + "completion": "0.0000012", + "input_cache_read": "0.000000006" + }, + { + "utc_days": ["monday", "tuesday", "wednesday", "thursday", "friday"], + "utc_start": 1000, + "utc_end": 0, + "prompt": "0.00000015", + "completion": "0.0000006", + "input_cache_read": "0.000000003" + } + ] + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 393216, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_completion_tokens", + "max_tokens", + "min_p", + "parallel_tool_calls", + "presence_penalty", + "reasoning", + "reasoning_effort", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/deepseek/deepseek-v4.1-flash-20261017/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1224, + "win_rate": 51.2, + "rank": 8 + }, + { + "arena": "models", + "category": "3d", + "elo": 1373, + "win_rate": 60.8, + "rank": 9 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1243, + "win_rate": 55, + "rank": 18 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1333, + "win_rate": 58.6, + "rank": 8 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1325, + "win_rate": 57.7, + "rank": 11 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1361, + "win_rate": 61.8, + "rank": 7 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1300, + "win_rate": 54.1, + "rank": 16 + }, + { + "arena": "models", + "category": "website", + "elo": 1312, + "win_rate": 56.2, + "rank": 11 + } + ], "artificial_analysis": { "intelligence_index": 39.5, "coding_index": null, @@ -8519,7 +8835,7 @@ "reasoning": { "mandatory": false, "default_enabled": true, - "supported_efforts": ["max", "high", "low"], + "supported_efforts": ["max", "high", "low", "none"], "default_effort": "high" } }, @@ -8539,13 +8855,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000000112", - "completion": "0.000000336", - "input_cache_read": "0.00000000336" + "prompt": "0.00000005", + "completion": "0.00000015", + "input_cache_read": "0.000000004" }, "top_provider": { "context_length": 1048576, - "max_completion_tokens": 131072, + "max_completion_tokens": 384000, "is_moderated": false }, "per_request_limits": null, @@ -8553,6 +8869,7 @@ "frequency_penalty", "include_reasoning", "logit_bias", + "logprobs", "max_tokens", "min_p", "presence_penalty", @@ -8567,6 +8884,7 @@ "tool_choice", "tools", "top_k", + "top_logprobs", "top_p" ], "default_parameters": {}, @@ -8579,7 +8897,7 @@ "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 39.5, + "intelligence_index": 24.7, "coding_index": null, "agentic_index": null } @@ -8587,7 +8905,7 @@ "reasoning": { "mandatory": false, "default_enabled": true, - "supported_efforts": ["max", "high", "low"], + "supported_efforts": ["max", "high", "low", "none"], "default_effort": "high" } }, @@ -8638,6 +8956,63 @@ "mandatory": false } }, + { + "id": "elorian/glimpse", + "canonical_slug": "elorian/glimpse-20261016", + "hugging_face_id": null, + "name": "Elorian: Glimpse", + "created": 1792206629, + "description": "Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than...", + "context_length": 262144, + "architecture": { + "modality": "text+image+video->text", + "input_modalities": ["text", "image", "video"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000006", + "completion": "0.000003", + "input_cache_read": "0.00000006" + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 256000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/elorian/glimpse-20261016/endpoints" + }, + "reasoning": { + "mandatory": false + } + }, { "id": "fireworks/ember-1", "canonical_slug": "fireworks/ember-1-20260923", @@ -8694,7 +9069,7 @@ "reasoning": { "mandatory": false, "default_enabled": true, - "supported_efforts": ["max", "high", "low"], + "supported_efforts": ["max", "high", "low", "none"], "default_effort": "max" } }, @@ -8753,7 +9128,7 @@ }, "supported_voices": null, "knowledge_cutoff": "2025-01-31", - "expiration_date": "2026-10-20", + "expiration_date": null, "links": { "details": "/api/v1/models/google/gemini-2.5-flash/endpoints" }, @@ -8762,51 +9137,51 @@ { "arena": "models", "category": "3d", - "elo": 1079, + "elo": 1071, "win_rate": 47.4, - "rank": 92 + "rank": 101 }, { "arena": "models", "category": "codecategories", - "elo": 1108, + "elo": 1104, "win_rate": 46.9, - "rank": 92 + "rank": 103 }, { "arena": "models", "category": "dataviz", - "elo": 1140, + "elo": 1134, "win_rate": 49.1, - "rank": 82 + "rank": 89 }, { "arena": "models", "category": "gamedev", - "elo": 1076, + "elo": 1066, "win_rate": 44.3, - "rank": 96 + "rank": 110 }, { "arena": "models", "category": "uicomponent", - "elo": 1098, + "elo": 1093, "win_rate": 48.9, - "rank": 90 + "rank": 98 }, { "arena": "models", "category": "website", - "elo": 1120, + "elo": 1115, "win_rate": 47.1, - "rank": 94 + "rank": 105 }, { "arena": "models", "category": "svg", - "elo": 1019, + "elo": 1020, "win_rate": 43.1, - "rank": 80 + "rank": 81 } ], "artificial_analysis": { @@ -8877,21 +9252,21 @@ { "arena": "models", "category": "graphicdesign", - "elo": 1166, + "elo": 1167, "win_rate": 56.9, "rank": 10 }, { "arena": "models", "category": "image", - "elo": 1187, + "elo": 1186, "win_rate": 55.6, "rank": 10 }, { "arena": "models", "category": "logo", - "elo": 1170, + "elo": 1169, "win_rate": 51.4, "rank": 11 } @@ -8950,73 +9325,6 @@ }, "supported_voices": null, "knowledge_cutoff": "2025-01-31", - "expiration_date": "2026-10-20", - "links": { - "details": "/api/v1/models/google/gemini-2.5-flash-lite/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 10.4, - "coding_index": null, - "agentic_index": null - } - }, - "reasoning": { - "mandatory": false - } - }, - { - "id": "google/gemini-2.5-flash-lite:batch", - "canonical_slug": "google/gemini-2.5-flash-lite", - "hugging_face_id": "", - "name": "Google: Gemini 2.5 Flash Lite (batch)", - "created": 1753200276, - "description": "Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...", - "context_length": 1048576, - "architecture": { - "modality": "text+image+file+audio+video->text", - "input_modalities": ["text", "image", "file", "audio", "video"], - "output_modalities": ["text"], - "tokenizer": "Gemini", - "instruct_type": null - }, - "pricing": { - "prompt": "0.00000005", - "completion": "0.0000002", - "image": "0.00000005", - "audio": "0.00000015", - "input_audio_cache": "0.00000003", - "web_search": "0.014", - "internal_reasoning": "0.0000002", - "input_cache_read": "0.00000001" - }, - "top_provider": { - "context_length": 1048576, - "max_completion_tokens": 65535, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "include_reasoning", - "max_tokens", - "reasoning", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_p" - ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": "2025-01-31", "expiration_date": null, "links": { "details": "/api/v1/models/google/gemini-2.5-flash-lite/endpoints" @@ -9033,126 +9341,6 @@ "mandatory": false } }, - { - "id": "google/gemini-2.5-flash:batch", - "canonical_slug": "google/gemini-2.5-flash", - "hugging_face_id": "", - "name": "Google: Gemini 2.5 Flash (batch)", - "created": 1750172488, - "description": "Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater...", - "context_length": 1048576, - "architecture": { - "modality": "text+image+file+audio+video->text", - "input_modalities": ["file", "image", "text", "audio", "video"], - "output_modalities": ["text"], - "tokenizer": "Gemini", - "instruct_type": null - }, - "pricing": { - "prompt": "0.00000015", - "completion": "0.00000125", - "image": "0.00000015", - "audio": "0.0000005", - "input_audio_cache": "0.0000001", - "web_search": "0.014", - "internal_reasoning": "0.00000125", - "input_cache_read": "0.00000003" - }, - "top_provider": { - "context_length": 1048576, - "max_completion_tokens": 65535, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "include_reasoning", - "max_tokens", - "reasoning", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_p" - ], - "default_parameters": { - "temperature": null, - "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": "2025-01-31", - "expiration_date": "2026-10-20", - "links": { - "details": "/api/v1/models/google/gemini-2.5-flash/endpoints" - }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1079, - "win_rate": 47.4, - "rank": 92 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1108, - "win_rate": 46.9, - "rank": 92 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1140, - "win_rate": 49.1, - "rank": 82 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1076, - "win_rate": 44.3, - "rank": 96 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1098, - "win_rate": 48.9, - "rank": 90 - }, - { - "arena": "models", - "category": "website", - "elo": 1120, - "win_rate": 47.1, - "rank": 94 - }, - { - "arena": "models", - "category": "svg", - "elo": 1019, - "win_rate": 43.1, - "rank": 80 - } - ], - "artificial_analysis": { - "intelligence_index": 15.5, - "coding_index": null, - "agentic_index": null - } - }, - "reasoning": { - "mandatory": false - } - }, { "id": "google/gemini-2.5-pro", "canonical_slug": "google/gemini-2.5-pro", @@ -9201,7 +9389,6 @@ "reasoning", "response_format", "seed", - "stop", "structured_outputs", "temperature", "tool_choice", @@ -9215,7 +9402,7 @@ }, "supported_voices": null, "knowledge_cutoff": "2025-01-31", - "expiration_date": "2026-10-20", + "expiration_date": null, "links": { "details": "/api/v1/models/google/gemini-2.5-pro/endpoints" }, @@ -9224,44 +9411,44 @@ { "arena": "models", "category": "3d", - "elo": 1088, + "elo": 1081, "win_rate": 50.6, - "rank": 87 + "rank": 94 }, { "arena": "models", "category": "codecategories", - "elo": 1156, + "elo": 1152, "win_rate": 57.5, - "rank": 73 + "rank": 84 }, { "arena": "models", "category": "dataviz", - "elo": 1227, + "elo": 1222, "win_rate": 68.2, - "rank": 45 + "rank": 50 }, { "arena": "models", "category": "gamedev", - "elo": 1122, + "elo": 1111, "win_rate": 54.2, - "rank": 81 + "rank": 92 }, { "arena": "models", "category": "uicomponent", - "elo": 1146, + "elo": 1140, "win_rate": 57.5, - "rank": 74 + "rank": 82 }, { "arena": "models", "category": "website", - "elo": 1172, + "elo": 1167, "win_rate": 58.4, - "rank": 73 + "rank": 83 } ], "artificial_analysis": { @@ -9340,126 +9527,6 @@ "mandatory": true } }, - { - "id": "google/gemini-2.5-pro:batch", - "canonical_slug": "google/gemini-2.5-pro", - "hugging_face_id": "", - "name": "Google: Gemini 2.5 Pro (batch)", - "created": 1750169544, - "description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...", - "context_length": 1048576, - "architecture": { - "modality": "text+image+file+audio+video->text", - "input_modalities": ["text", "image", "file", "audio", "video"], - "output_modalities": ["text"], - "tokenizer": "Gemini", - "instruct_type": null - }, - "pricing": { - "prompt": "0.000000625", - "completion": "0.000005", - "image": "0.000000625", - "audio": "0.000000625", - "input_audio_cache": "0.000000125", - "web_search": "0.014", - "internal_reasoning": "0.000005", - "input_cache_read": "0.000000125", - "overrides": [ - { - "min_prompt_tokens": 200000, - "prompt": "0.00000125", - "completion": "0.0000075", - "audio": "0.00000125", - "input_audio_cache": "0.00000025", - "input_cache_read": "0.00000025" - } - ] - }, - "top_provider": { - "context_length": 1048576, - "max_completion_tokens": 65536, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "include_reasoning", - "max_tokens", - "reasoning", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_p" - ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": "2025-01-31", - "expiration_date": "2026-10-20", - "links": { - "details": "/api/v1/models/google/gemini-2.5-pro/endpoints" - }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1088, - "win_rate": 50.6, - "rank": 87 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1156, - "win_rate": 57.5, - "rank": 73 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1227, - "win_rate": 68.2, - "rank": 45 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1122, - "win_rate": 54.2, - "rank": 81 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1146, - "win_rate": 57.5, - "rank": 74 - }, - { - "arena": "models", - "category": "website", - "elo": 1172, - "win_rate": 58.4, - "rank": 73 - } - ], - "artificial_analysis": { - "intelligence_index": 16.1, - "coding_index": 33.3, - "agentic_index": 1.6 - } - }, - "reasoning": { - "mandatory": true - } - }, { "id": "google/gemini-3-flash-preview", "canonical_slug": "google/gemini-3-flash-preview-20251217", @@ -9539,14 +9606,14 @@ { "arena": "agents", "category": "androidnative", - "elo": 1065, + "elo": 1050, "win_rate": 48.1, - "rank": 33 + "rank": 34 }, { "arena": "agents", "category": "fullstack", - "elo": 1061, + "elo": 1063, "win_rate": 47.4, "rank": 33 }, @@ -9560,9 +9627,9 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1087, + "elo": 1090, "win_rate": 46.6, - "rank": 39 + "rank": 41 }, { "arena": "agents", @@ -9574,37 +9641,37 @@ { "arena": "agents", "category": "webapps", - "elo": 1103, + "elo": 1110, "win_rate": 48.5, - "rank": 33 + "rank": 37 }, { "arena": "models", "category": "3d", - "elo": 1192, + "elo": 1184, "win_rate": 62.7, - "rank": 49 + "rank": 56 }, { "arena": "models", "category": "codecategories", - "elo": 1193, + "elo": 1189, "win_rate": 57.6, - "rank": 53 + "rank": 62 }, { "arena": "models", "category": "gamedev", - "elo": 1176, + "elo": 1166, "win_rate": 58.3, - "rank": 60 + "rank": 70 }, { "arena": "models", "category": "website", - "elo": 1201, + "elo": 1196, "win_rate": 57, - "rank": 56 + "rank": 64 } ], "artificial_analysis": { @@ -9615,7 +9682,7 @@ }, "reasoning": { "mandatory": false, - "supported_efforts": ["high", "medium", "low", "minimal"], + "supported_efforts": ["high", "medium", "low", "minimal", "none"], "default_effort": "medium" } }, @@ -9695,14 +9762,14 @@ { "arena": "agents", "category": "androidnative", - "elo": 1065, + "elo": 1050, "win_rate": 48.1, - "rank": 33 + "rank": 34 }, { "arena": "agents", "category": "fullstack", - "elo": 1061, + "elo": 1063, "win_rate": 47.4, "rank": 33 }, @@ -9716,9 +9783,9 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1087, + "elo": 1090, "win_rate": 46.6, - "rank": 39 + "rank": 41 }, { "arena": "agents", @@ -9730,37 +9797,37 @@ { "arena": "agents", "category": "webapps", - "elo": 1103, + "elo": 1110, "win_rate": 48.5, - "rank": 33 + "rank": 37 }, { "arena": "models", "category": "3d", - "elo": 1192, + "elo": 1184, "win_rate": 62.7, - "rank": 49 + "rank": 56 }, { "arena": "models", "category": "codecategories", - "elo": 1193, + "elo": 1189, "win_rate": 57.6, - "rank": 53 + "rank": 62 }, { "arena": "models", "category": "gamedev", - "elo": 1176, + "elo": 1166, "win_rate": 58.3, - "rank": 60 + "rank": 70 }, { "arena": "models", "category": "website", - "elo": 1201, + "elo": 1196, "win_rate": 57, - "rank": 56 + "rank": 64 } ], "artificial_analysis": { @@ -9771,7 +9838,7 @@ }, "reasoning": { "mandatory": false, - "supported_efforts": ["high", "medium", "low", "minimal"], + "supported_efforts": ["high", "medium", "low", "minimal", "none"], "default_effort": "medium" } }, @@ -9892,7 +9959,7 @@ { "arena": "models", "category": "graphicdesign", - "elo": 1250, + "elo": 1251, "win_rate": 65.8, "rank": 5 }, @@ -9906,14 +9973,14 @@ { "arena": "models", "category": "logo", - "elo": 1242, + "elo": 1241, "win_rate": 61, "rank": 6 }, { "arena": "models", "category": "imageediting", - "elo": 1254, + "elo": 1248, "win_rate": 66, "rank": 3 } @@ -9971,7 +10038,7 @@ "reasoning": { "mandatory": false, "default_enabled": true, - "supported_efforts": ["high", "minimal"], + "supported_efforts": ["high", "minimal", "none"], "default_effort": "minimal" } }, @@ -10032,21 +10099,21 @@ { "arena": "models", "category": "graphicdesign", - "elo": 1260, + "elo": 1261, "win_rate": 66.3, "rank": 4 }, { "arena": "models", "category": "image", - "elo": 1277, + "elo": 1276, "win_rate": 65.1, "rank": 4 }, { "arena": "models", "category": "logo", - "elo": 1264, + "elo": 1263, "win_rate": 62.9, "rank": 4 } @@ -10055,7 +10122,7 @@ "reasoning": { "mandatory": false, "default_enabled": true, - "supported_efforts": ["high", "minimal"], + "supported_efforts": ["high", "minimal", "none"], "default_effort": "minimal" } }, @@ -10122,7 +10189,7 @@ "reasoning": { "mandatory": false, "default_enabled": true, - "supported_efforts": ["high", "medium", "low", "minimal"], + "supported_efforts": ["high", "medium", "low", "minimal", "none"], "default_effort": "minimal" } }, @@ -10173,7 +10240,7 @@ "reasoning": { "mandatory": false, "default_enabled": true, - "supported_efforts": ["high", "minimal"], + "supported_efforts": ["high", "minimal", "none"], "default_effort": "minimal" } }, @@ -10241,58 +10308,58 @@ { "arena": "models", "category": "3d", - "elo": 1056, + "elo": 1048, "win_rate": 38.8, - "rank": 97 + "rank": 105 }, { "arena": "models", "category": "asciiart", - "elo": 1175, - "win_rate": 50.7, - "rank": 30 + "elo": 1167, + "win_rate": 50.8, + "rank": 32 }, { "arena": "models", "category": "codecategories", - "elo": 1076, + "elo": 1072, "win_rate": 36.5, - "rank": 98 + "rank": 109 }, { "arena": "models", "category": "dataviz", - "elo": 1051, + "elo": 1045, "win_rate": 33.3, - "rank": 103 + "rank": 110 }, { "arena": "models", "category": "gamedev", - "elo": 1040, + "elo": 1029, "win_rate": 33.7, - "rank": 105 + "rank": 119 }, { "arena": "models", "category": "svg", - "elo": 1051, + "elo": 1053, "win_rate": 42.5, - "rank": 71 + "rank": 72 }, { "arena": "models", "category": "uicomponent", - "elo": 1078, + "elo": 1072, "win_rate": 37.7, - "rank": 95 + "rank": 103 }, { "arena": "models", "category": "website", - "elo": 1089, + "elo": 1083, "win_rate": 36.6, - "rank": 102 + "rank": 113 } ], "artificial_analysis": { @@ -10304,7 +10371,7 @@ "reasoning": { "mandatory": false, "default_enabled": true, - "supported_efforts": ["high", "medium", "low", "minimal"], + "supported_efforts": ["high", "medium", "low", "minimal", "none"], "default_effort": "minimal" } }, @@ -10370,7 +10437,7 @@ "reasoning": { "mandatory": false, "default_enabled": true, - "supported_efforts": ["high", "medium", "low", "minimal"], + "supported_efforts": ["high", "medium", "low", "minimal", "none"], "default_effort": "minimal" } }, @@ -10449,8 +10516,8 @@ { "arena": "agents", "category": "agenticgamedev", - "elo": 1114, - "win_rate": 44.2, + "elo": 1113, + "win_rate": 44.1, "rank": 22 }, { @@ -10484,14 +10551,14 @@ { "arena": "agents", "category": "androidnative", - "elo": 1064, + "elo": 1049, "win_rate": 41.3, - "rank": 34 + "rank": 35 }, { "arena": "agents", "category": "fullstack", - "elo": 1067, + "elo": 1068, "win_rate": 40.8, "rank": 32 }, @@ -10505,16 +10572,16 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1153, + "elo": 1154, "win_rate": 48.6, "rank": 16 }, { "arena": "agents", "category": "mobileapps", - "elo": 1090, - "win_rate": 43.2, - "rank": 38 + "elo": 1094, + "win_rate": 43, + "rank": 39 }, { "arena": "agents", @@ -10533,65 +10600,65 @@ { "arena": "agents", "category": "webapps", - "elo": 1119, - "win_rate": 44.6, - "rank": 30 + "elo": 1125, + "win_rate": 44.3, + "rank": 34 }, { "arena": "models", "category": "3d", - "elo": 1242, + "elo": 1234, "win_rate": 58.4, - "rank": 33 + "rank": 40 }, { "arena": "models", "category": "asciiart", - "elo": 1278, + "elo": 1270, "win_rate": 63.5, - "rank": 10 + "rank": 11 }, { "arena": "models", "category": "codecategories", - "elo": 1248, + "elo": 1244, "win_rate": 64.4, - "rank": 35 + "rank": 43 }, { "arena": "models", "category": "dataviz", - "elo": 1245, + "elo": 1239, "win_rate": 61.8, - "rank": 33 + "rank": 39 }, { "arena": "models", "category": "gamedev", - "elo": 1213, - "win_rate": 52.1, - "rank": 45 + "elo": 1203, + "win_rate": 52.2, + "rank": 56 }, { "arena": "models", "category": "svg", "elo": 1285, "win_rate": 67.8, - "rank": 12 + "rank": 9 }, { "arena": "models", "category": "uicomponent", - "elo": 1285, + "elo": 1280, "win_rate": 69.4, - "rank": 24 + "rank": 27 }, { "arena": "models", "category": "website", - "elo": 1259, + "elo": 1253, "win_rate": 64.4, - "rank": 35 + "rank": 43 } ], "artificial_analysis": { @@ -10748,8 +10815,8 @@ { "arena": "agents", "category": "agenticgamedev", - "elo": 1114, - "win_rate": 44.2, + "elo": 1113, + "win_rate": 44.1, "rank": 22 }, { @@ -10783,14 +10850,14 @@ { "arena": "agents", "category": "androidnative", - "elo": 1064, + "elo": 1049, "win_rate": 41.3, - "rank": 34 + "rank": 35 }, { "arena": "agents", "category": "fullstack", - "elo": 1067, + "elo": 1068, "win_rate": 40.8, "rank": 32 }, @@ -10804,16 +10871,16 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1153, + "elo": 1154, "win_rate": 48.6, "rank": 16 }, { "arena": "agents", "category": "mobileapps", - "elo": 1090, - "win_rate": 43.2, - "rank": 38 + "elo": 1094, + "win_rate": 43, + "rank": 39 }, { "arena": "agents", @@ -10832,65 +10899,65 @@ { "arena": "agents", "category": "webapps", - "elo": 1119, - "win_rate": 44.6, - "rank": 30 + "elo": 1125, + "win_rate": 44.3, + "rank": 34 }, { "arena": "models", "category": "3d", - "elo": 1242, + "elo": 1234, "win_rate": 58.4, - "rank": 33 + "rank": 40 }, { "arena": "models", "category": "asciiart", - "elo": 1278, + "elo": 1270, "win_rate": 63.5, - "rank": 10 + "rank": 11 }, { "arena": "models", "category": "codecategories", - "elo": 1248, + "elo": 1244, "win_rate": 64.4, - "rank": 35 + "rank": 43 }, { "arena": "models", "category": "dataviz", - "elo": 1245, + "elo": 1239, "win_rate": 61.8, - "rank": 33 + "rank": 39 }, { "arena": "models", "category": "gamedev", - "elo": 1213, - "win_rate": 52.1, - "rank": 45 + "elo": 1203, + "win_rate": 52.2, + "rank": 56 }, { "arena": "models", "category": "svg", "elo": 1285, "win_rate": 67.8, - "rank": 12 + "rank": 9 }, { "arena": "models", "category": "uicomponent", - "elo": 1285, + "elo": 1280, "win_rate": 69.4, - "rank": 24 + "rank": 27 }, { "arena": "models", "category": "website", - "elo": 1259, + "elo": 1253, "win_rate": 64.4, - "rank": 35 + "rank": 43 } ], "artificial_analysis": { @@ -11005,16 +11072,16 @@ { "arena": "agents", "category": "androidnative", - "elo": 1199, + "elo": 1184, "win_rate": 57.7, - "rank": 14 + "rank": 15 }, { "arena": "agents", "category": "fullstack", - "elo": 1195, + "elo": 1197, "win_rate": 56.2, - "rank": 19 + "rank": 18 }, { "arena": "agents", @@ -11026,16 +11093,16 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1142, + "elo": 1143, "win_rate": 46.5, "rank": 19 }, { "arena": "agents", "category": "mobileapps", - "elo": 1173, - "win_rate": 51.2, - "rank": 21 + "elo": 1174, + "win_rate": 50.6, + "rank": 24 }, { "arena": "agents", @@ -11054,65 +11121,65 @@ { "arena": "agents", "category": "webapps", - "elo": 1196, - "win_rate": 52.6, - "rank": 20 + "elo": 1202, + "win_rate": 52.2, + "rank": 23 }, { "arena": "models", "category": "3d", - "elo": 1252, - "win_rate": 56.2, - "rank": 28 + "elo": 1244, + "win_rate": 55.8, + "rank": 35 }, { "arena": "models", "category": "asciiart", - "elo": 1262, - "win_rate": 58.9, - "rank": 14 + "elo": 1254, + "win_rate": 59, + "rank": 17 }, { "arena": "models", "category": "codecategories", - "elo": 1270, - "win_rate": 54.3, - "rank": 27 + "elo": 1266, + "win_rate": 54, + "rank": 33 }, { "arena": "models", "category": "dataviz", - "elo": 1241, - "win_rate": 53, - "rank": 35 + "elo": 1236, + "win_rate": 52.9, + "rank": 40 }, { "arena": "models", "category": "gamedev", - "elo": 1272, - "win_rate": 53, - "rank": 25 + "elo": 1263, + "win_rate": 52.7, + "rank": 32 }, { "arena": "models", "category": "svg", "elo": 1254, - "win_rate": 58.6, + "win_rate": 58.3, "rank": 13 }, { "arena": "models", "category": "uicomponent", - "elo": 1279, - "win_rate": 54.8, - "rank": 25 + "elo": 1273, + "win_rate": 54.3, + "rank": 31 }, { "arena": "models", "category": "website", - "elo": 1271, - "win_rate": 53.9, - "rank": 28 + "elo": 1268, + "win_rate": 53.7, + "rank": 32 } ], "artificial_analysis": { @@ -11374,16 +11441,16 @@ { "arena": "agents", "category": "androidnative", - "elo": 1199, + "elo": 1184, "win_rate": 57.7, - "rank": 14 + "rank": 15 }, { "arena": "agents", "category": "fullstack", - "elo": 1195, + "elo": 1197, "win_rate": 56.2, - "rank": 19 + "rank": 18 }, { "arena": "agents", @@ -11395,16 +11462,16 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1142, + "elo": 1143, "win_rate": 46.5, "rank": 19 }, { "arena": "agents", "category": "mobileapps", - "elo": 1173, - "win_rate": 51.2, - "rank": 21 + "elo": 1174, + "win_rate": 50.6, + "rank": 24 }, { "arena": "agents", @@ -11423,65 +11490,65 @@ { "arena": "agents", "category": "webapps", - "elo": 1196, - "win_rate": 52.6, - "rank": 20 + "elo": 1202, + "win_rate": 52.2, + "rank": 23 }, { "arena": "models", "category": "3d", - "elo": 1252, - "win_rate": 56.2, - "rank": 28 + "elo": 1244, + "win_rate": 55.8, + "rank": 35 }, { "arena": "models", "category": "asciiart", - "elo": 1262, - "win_rate": 58.9, - "rank": 14 + "elo": 1254, + "win_rate": 59, + "rank": 17 }, { "arena": "models", "category": "codecategories", - "elo": 1270, - "win_rate": 54.3, - "rank": 27 + "elo": 1266, + "win_rate": 54, + "rank": 33 }, { "arena": "models", "category": "dataviz", - "elo": 1241, - "win_rate": 53, - "rank": 35 + "elo": 1236, + "win_rate": 52.9, + "rank": 40 }, { "arena": "models", "category": "gamedev", - "elo": 1272, - "win_rate": 53, - "rank": 25 + "elo": 1263, + "win_rate": 52.7, + "rank": 32 }, { "arena": "models", "category": "svg", "elo": 1254, - "win_rate": 58.6, + "win_rate": 58.3, "rank": 13 }, { "arena": "models", "category": "uicomponent", - "elo": 1279, - "win_rate": 54.8, - "rank": 25 + "elo": 1273, + "win_rate": 54.3, + "rank": 31 }, { "arena": "models", "category": "website", - "elo": 1271, - "win_rate": 53.9, - "rank": 28 + "elo": 1268, + "win_rate": 53.7, + "rank": 32 } ], "artificial_analysis": { @@ -11563,99 +11630,106 @@ "arena": "agents", "category": "agenticgamedev", "elo": 1180, - "win_rate": 47.8, + "win_rate": 47.6, "rank": 13 }, { "arena": "agents", "category": "androidnative", - "elo": 1217, - "win_rate": 53.7, + "elo": 1203, + "win_rate": 53.5, "rank": 11 }, { "arena": "agents", "category": "fullstack", - "elo": 1179, + "elo": 1181, "win_rate": 44.3, "rank": 21 }, { "arena": "agents", "category": "htmlslides", - "elo": 1148, + "elo": 1149, "win_rate": 41.9, "rank": 17 }, { "arena": "agents", "category": "mobileapps", - "elo": 1195, - "win_rate": 50.2, - "rank": 16 + "elo": 1199, + "win_rate": 50.1, + "rank": 18 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1146, - "win_rate": 38.8, + "elo": 1144, + "win_rate": 38.9, "rank": 24 }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1072, + "win_rate": 43.1, + "rank": 11 + }, { "arena": "agents", "category": "webapps", - "elo": 1187, - "win_rate": 45.4, - "rank": 22 + "elo": 1197, + "win_rate": 45.6, + "rank": 25 }, { "arena": "models", "category": "3d", - "elo": 1282, - "win_rate": 53.2, - "rank": 18 + "elo": 1272, + "win_rate": 52.9, + "rank": 24 }, { "arena": "models", "category": "asciiart", - "elo": 1287, - "win_rate": 56.9, - "rank": 7 + "elo": 1281, + "win_rate": 57.3, + "rank": 5 }, { "arena": "models", "category": "codecategories", - "elo": 1294, + "elo": 1290, "win_rate": 53.4, - "rank": 14 + "rank": 19 }, { "arena": "models", "category": "dataviz", - "elo": 1297, - "win_rate": 52.4, - "rank": 12 + "elo": 1289, + "win_rate": 52.3, + "rank": 16 }, { "arena": "models", "category": "gamedev", - "elo": 1273, - "win_rate": 51.1, - "rank": 23 + "elo": 1263, + "win_rate": 51, + "rank": 33 }, { "arena": "models", "category": "uicomponent", - "elo": 1300, - "win_rate": 53.6, - "rank": 15 + "elo": 1297, + "win_rate": 53.8, + "rank": 19 }, { "arena": "models", "category": "website", - "elo": 1304, + "elo": 1300, "win_rate": 55.4, - "rank": 12 + "rank": 16 } ], "artificial_analysis": { @@ -11735,99 +11809,106 @@ "arena": "agents", "category": "agenticgamedev", "elo": 1180, - "win_rate": 47.8, + "win_rate": 47.6, "rank": 13 }, { "arena": "agents", "category": "androidnative", - "elo": 1217, - "win_rate": 53.7, + "elo": 1203, + "win_rate": 53.5, "rank": 11 }, { "arena": "agents", "category": "fullstack", - "elo": 1179, + "elo": 1181, "win_rate": 44.3, "rank": 21 }, { "arena": "agents", "category": "htmlslides", - "elo": 1148, + "elo": 1149, "win_rate": 41.9, "rank": 17 }, { "arena": "agents", "category": "mobileapps", - "elo": 1195, - "win_rate": 50.2, - "rank": 16 + "elo": 1199, + "win_rate": 50.1, + "rank": 18 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1146, - "win_rate": 38.8, + "elo": 1144, + "win_rate": 38.9, "rank": 24 }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1072, + "win_rate": 43.1, + "rank": 11 + }, { "arena": "agents", "category": "webapps", - "elo": 1187, - "win_rate": 45.4, - "rank": 22 + "elo": 1197, + "win_rate": 45.6, + "rank": 25 }, { "arena": "models", "category": "3d", - "elo": 1282, - "win_rate": 53.2, - "rank": 18 + "elo": 1272, + "win_rate": 52.9, + "rank": 24 }, { "arena": "models", "category": "asciiart", - "elo": 1287, - "win_rate": 56.9, - "rank": 7 + "elo": 1281, + "win_rate": 57.3, + "rank": 5 }, { "arena": "models", "category": "codecategories", - "elo": 1294, + "elo": 1290, "win_rate": 53.4, - "rank": 14 + "rank": 19 }, { "arena": "models", "category": "dataviz", - "elo": 1297, - "win_rate": 52.4, - "rank": 12 + "elo": 1289, + "win_rate": 52.3, + "rank": 16 }, { "arena": "models", "category": "gamedev", - "elo": 1273, - "win_rate": 51.1, - "rank": 23 + "elo": 1263, + "win_rate": 51, + "rank": 33 }, { "arena": "models", "category": "uicomponent", - "elo": 1300, - "win_rate": 53.6, - "rank": 15 + "elo": 1297, + "win_rate": 53.8, + "rank": 19 }, { "arena": "models", "category": "website", - "elo": 1304, + "elo": 1300, "win_rate": 55.4, - "rank": 12 + "rank": 16 } ], "artificial_analysis": { @@ -11902,20 +11983,20 @@ "arena": "agents", "category": "agenticgamedev", "elo": 1235, - "win_rate": 52.1, - "rank": 5 + "win_rate": 52, + "rank": 6 }, { "arena": "agents", "category": "androidnative", - "elo": 1255, + "elo": 1242, "win_rate": 53.3, "rank": 6 }, { "arena": "agents", "category": "fullstack", - "elo": 1207, + "elo": 1208, "win_rate": 43.5, "rank": 16 }, @@ -11929,72 +12010,79 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1227, - "win_rate": 52.9, - "rank": 8 + "elo": 1231, + "win_rate": 52.6, + "rank": 9 + }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1071, + "win_rate": 46.5, + "rank": 12 }, { "arena": "agents", "category": "webapps", - "elo": 1214, - "win_rate": 46.6, - "rank": 15 + "elo": 1223, + "win_rate": 47.3, + "rank": 16 }, { "arena": "models", "category": "3d", - "elo": 1316, - "win_rate": 53.8, - "rank": 12 + "elo": 1308, + "win_rate": 53.7, + "rank": 18 }, { "arena": "models", "category": "asciiart", - "elo": 1287, - "win_rate": 56.4, - "rank": 8 + "elo": 1276, + "win_rate": 55.2, + "rank": 9 }, { "arena": "models", "category": "codecategories", - "elo": 1314, - "win_rate": 54, - "rank": 10 + "elo": 1308, + "win_rate": 53.9, + "rank": 14 }, { "arena": "models", "category": "dataviz", - "elo": 1325, - "win_rate": 55.5, - "rank": 10 + "elo": 1315, + "win_rate": 55.2, + "rank": 13 }, { "arena": "models", "category": "gamedev", - "elo": 1331, - "win_rate": 53.7, - "rank": 7 + "elo": 1318, + "win_rate": 53.5, + "rank": 12 }, { "arena": "models", "category": "svg", - "elo": 1289, - "win_rate": 53.5, - "rank": 11 + "elo": 1284, + "win_rate": 54, + "rank": 12 }, { "arena": "models", "category": "uicomponent", - "elo": 1307, - "win_rate": 52.3, - "rank": 13 + "elo": 1298, + "win_rate": 52, + "rank": 18 }, { "arena": "models", "category": "website", - "elo": 1310, + "elo": 1304, "win_rate": 54, - "rank": 9 + "rank": 14 } ], "artificial_analysis": { @@ -12067,20 +12155,20 @@ "arena": "agents", "category": "agenticgamedev", "elo": 1235, - "win_rate": 52.1, - "rank": 5 + "win_rate": 52, + "rank": 6 }, { "arena": "agents", "category": "androidnative", - "elo": 1255, + "elo": 1242, "win_rate": 53.3, "rank": 6 }, { "arena": "agents", "category": "fullstack", - "elo": 1207, + "elo": 1208, "win_rate": 43.5, "rank": 16 }, @@ -12094,72 +12182,79 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1227, - "win_rate": 52.9, - "rank": 8 + "elo": 1231, + "win_rate": 52.6, + "rank": 9 + }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1071, + "win_rate": 46.5, + "rank": 12 }, { "arena": "agents", "category": "webapps", - "elo": 1214, - "win_rate": 46.6, - "rank": 15 + "elo": 1223, + "win_rate": 47.3, + "rank": 16 }, { "arena": "models", "category": "3d", - "elo": 1316, - "win_rate": 53.8, - "rank": 12 + "elo": 1308, + "win_rate": 53.7, + "rank": 18 }, { "arena": "models", "category": "asciiart", - "elo": 1287, - "win_rate": 56.4, - "rank": 8 + "elo": 1276, + "win_rate": 55.2, + "rank": 9 }, { "arena": "models", "category": "codecategories", - "elo": 1314, - "win_rate": 54, - "rank": 10 + "elo": 1308, + "win_rate": 53.9, + "rank": 14 }, { "arena": "models", "category": "dataviz", - "elo": 1325, - "win_rate": 55.5, - "rank": 10 + "elo": 1315, + "win_rate": 55.2, + "rank": 13 }, { "arena": "models", "category": "gamedev", - "elo": 1331, - "win_rate": 53.7, - "rank": 7 + "elo": 1318, + "win_rate": 53.5, + "rank": 12 }, { "arena": "models", "category": "svg", - "elo": 1289, - "win_rate": 53.5, - "rank": 11 + "elo": 1284, + "win_rate": 54, + "rank": 12 }, { "arena": "models", "category": "uicomponent", - "elo": 1307, - "win_rate": 52.3, - "rank": 13 + "elo": 1298, + "win_rate": 52, + "rank": 18 }, { "arena": "models", "category": "website", - "elo": 1310, + "elo": 1304, "win_rate": 54, - "rank": 9 + "rank": 14 } ], "artificial_analysis": { @@ -12191,14 +12286,14 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000075", - "completion": "0.00000375", - "image": "0.00000075", - "audio": "0.00000075", - "input_audio_cache": "0.000000075", + "prompt": "0.000000825", + "completion": "0.000004125", + "image": "0.000000825", + "audio": "0.000000825", + "input_audio_cache": "0.0000000825", "web_search": "0.014", - "internal_reasoning": "0.00000375", - "input_cache_read": "0.000000075", + "internal_reasoning": "0.000004125", + "input_cache_read": "0.0000000825", "input_cache_write": "0.0000000416666666666667" }, "top_provider": { @@ -12233,14 +12328,14 @@ { "arena": "agents", "category": "androidnative", - "elo": 1077, - "win_rate": 33.2, - "rank": 31 + "elo": 1075, + "win_rate": 32.8, + "rank": 32 }, { "arena": "agents", "category": "fullstack", - "elo": 1242, + "elo": 1244, "win_rate": 48.1, "rank": 11 }, @@ -12254,79 +12349,86 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1233, - "win_rate": 54.3, - "rank": 6 + "elo": 1236, + "win_rate": 54.4, + "rank": 7 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1178, - "win_rate": 39.8, + "elo": 1174, + "win_rate": 39.9, "rank": 19 }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1056, + "win_rate": 39.8, + "rank": 14 + }, { "arena": "agents", "category": "webapps", - "elo": 1230, - "win_rate": 46.1, - "rank": 11 + "elo": 1238, + "win_rate": 46.7, + "rank": 14 }, { "arena": "models", "category": "3d", - "elo": 1303, - "win_rate": 49.8, - "rank": 14 + "elo": 1295, + "win_rate": 50, + "rank": 20 }, { "arena": "models", "category": "asciiart", - "elo": 1278, - "win_rate": 53.9, - "rank": 11 + "elo": 1262, + "win_rate": 51.1, + "rank": 13 }, { "arena": "models", "category": "codecategories", - "elo": 1310, - "win_rate": 50.3, - "rank": 11 + "elo": 1304, + "win_rate": 50.4, + "rank": 16 }, { "arena": "models", "category": "dataviz", - "elo": 1272, - "win_rate": 50.8, - "rank": 21 + "elo": 1270, + "win_rate": 51, + "rank": 26 }, { "arena": "models", "category": "gamedev", - "elo": 1317, + "elo": 1305, "win_rate": 51, - "rank": 11 + "rank": 18 }, { "arena": "models", "category": "svg", - "elo": 1297, - "win_rate": 54.6, - "rank": 8 + "elo": 1296, + "win_rate": 54.8, + "rank": 7 }, { "arena": "models", "category": "uicomponent", - "elo": 1322, - "win_rate": 53.6, - "rank": 12 + "elo": 1318, + "win_rate": 53.8, + "rank": 13 }, { "arena": "models", "category": "website", - "elo": 1307, + "elo": 1301, "win_rate": 50, - "rank": 10 + "rank": 15 } ], "artificial_analysis": { @@ -12398,14 +12500,14 @@ { "arena": "agents", "category": "androidnative", - "elo": 1077, - "win_rate": 33.2, - "rank": 31 + "elo": 1075, + "win_rate": 32.8, + "rank": 32 }, { "arena": "agents", "category": "fullstack", - "elo": 1242, + "elo": 1244, "win_rate": 48.1, "rank": 11 }, @@ -12419,79 +12521,86 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1233, - "win_rate": 54.3, - "rank": 6 + "elo": 1236, + "win_rate": 54.4, + "rank": 7 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1178, - "win_rate": 39.8, + "elo": 1174, + "win_rate": 39.9, "rank": 19 }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1056, + "win_rate": 39.8, + "rank": 14 + }, { "arena": "agents", "category": "webapps", - "elo": 1230, - "win_rate": 46.1, - "rank": 11 + "elo": 1238, + "win_rate": 46.7, + "rank": 14 }, { "arena": "models", "category": "3d", - "elo": 1303, - "win_rate": 49.8, - "rank": 14 + "elo": 1295, + "win_rate": 50, + "rank": 20 }, { "arena": "models", "category": "asciiart", - "elo": 1278, - "win_rate": 53.9, - "rank": 11 + "elo": 1262, + "win_rate": 51.1, + "rank": 13 }, { "arena": "models", "category": "codecategories", - "elo": 1310, - "win_rate": 50.3, - "rank": 11 + "elo": 1304, + "win_rate": 50.4, + "rank": 16 }, { "arena": "models", "category": "dataviz", - "elo": 1272, - "win_rate": 50.8, - "rank": 21 + "elo": 1270, + "win_rate": 51, + "rank": 26 }, { "arena": "models", "category": "gamedev", - "elo": 1317, + "elo": 1305, "win_rate": 51, - "rank": 11 + "rank": 18 }, { "arena": "models", "category": "svg", - "elo": 1297, - "win_rate": 54.6, - "rank": 8 + "elo": 1296, + "win_rate": 54.8, + "rank": 7 }, { "arena": "models", "category": "uicomponent", - "elo": 1322, - "win_rate": 53.6, - "rank": 12 + "elo": 1318, + "win_rate": 53.8, + "rank": 13 }, { "arena": "models", "category": "website", - "elo": 1307, + "elo": 1301, "win_rate": 50, - "rank": 10 + "rank": 15 } ], "artificial_analysis": { @@ -12507,6 +12616,254 @@ "default_effort": "medium" } }, + { + "id": "google/gemini-4-argon", + "canonical_slug": "google/gemini-4-argon-20261013", + "hugging_face_id": null, + "name": "Google: Gemini 4 Argon", + "created": 1791907477, + "description": "Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...", + "context_length": 1048576, + "architecture": { + "modality": "text+image+file+audio+video->text", + "input_modalities": ["audio", "file", "image", "text", "video"], + "output_modalities": ["text"], + "tokenizer": "Gemini", + "instruct_type": null + }, + "pricing": { + "prompt": "0.000002", + "completion": "0.00001", + "image": "0.000002", + "audio": "0.000002", + "input_audio_cache": "0.0000001", + "web_search": "0.014", + "internal_reasoning": "0.00001", + "input_cache_read": "0.0000001", + "input_cache_write": "0.0000001875" + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 943718, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "reasoning_effort", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/google/gemini-4-argon-20261013/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1134, + "win_rate": 32.8, + "rank": 10 + }, + { + "arena": "models", + "category": "3d", + "elo": 1389, + "win_rate": 64.7, + "rank": 7 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1329, + "win_rate": 57.7, + "rank": 9 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1334, + "win_rate": 60.7, + "rank": 8 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1376, + "win_rate": 63.1, + "rank": 6 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1330, + "win_rate": 57.6, + "rank": 10 + }, + { + "arena": "models", + "category": "website", + "elo": 1315, + "win_rate": 56.3, + "rank": 8 + } + ], + "artificial_analysis": { + "intelligence_index": 52.6, + "coding_index": null, + "agentic_index": null + } + }, + "reasoning": { + "mandatory": true, + "supported_efforts": ["high", "medium", "low"], + "default_effort": "medium" + } + }, + { + "id": "google/gemini-4-argon:batch", + "canonical_slug": "google/gemini-4-argon-20261013", + "hugging_face_id": null, + "name": "Google: Gemini 4 Argon (batch)", + "created": 1791907477, + "description": "Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...", + "context_length": 1048576, + "architecture": { + "modality": "text+image+file+audio+video->text", + "input_modalities": ["audio", "file", "image", "text", "video"], + "output_modalities": ["text"], + "tokenizer": "Gemini", + "instruct_type": null + }, + "pricing": { + "prompt": "0.000001", + "completion": "0.000005", + "image": "0.000001", + "audio": "0.000001", + "input_audio_cache": "0.00000005", + "web_search": "0.014", + "internal_reasoning": "0.000005", + "input_cache_read": "0.00000005", + "input_cache_write": "0.0000001875" + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 943718, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "reasoning_effort", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/google/gemini-4-argon-20261013/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1134, + "win_rate": 32.8, + "rank": 10 + }, + { + "arena": "models", + "category": "3d", + "elo": 1389, + "win_rate": 64.7, + "rank": 7 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1329, + "win_rate": 57.7, + "rank": 9 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1334, + "win_rate": 60.7, + "rank": 8 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1376, + "win_rate": 63.1, + "rank": 6 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1330, + "win_rate": 57.6, + "rank": 10 + }, + { + "arena": "models", + "category": "website", + "elo": 1315, + "win_rate": 56.3, + "rank": 8 + } + ], + "artificial_analysis": { + "intelligence_index": 52.6, + "coding_index": null, + "agentic_index": null + } + }, + "reasoning": { + "mandatory": true, + "supported_efforts": ["high", "medium", "low"], + "default_effort": "medium" + } + }, { "id": "google/gemini-nano-banana-2.1", "canonical_slug": "google/gemini-nano-banana-2.1-20261006", @@ -12557,7 +12914,7 @@ "reasoning": { "mandatory": false, "default_enabled": true, - "supported_efforts": ["high", "minimal"], + "supported_efforts": ["high", "minimal", "none"], "default_effort": "minimal" } }, @@ -12681,7 +13038,7 @@ }, "pricing": { "prompt": "0.00000008", - "completion": "0.00000045", + "completion": "0.00000035", "input_cache_read": "0.00000004" }, "top_provider": { @@ -12745,18 +13102,20 @@ "instruct_type": "gemma" }, "pricing": { - "prompt": "0.00000005", - "completion": "0.0000001" + "prompt": "0.00000004", + "completion": "0.00000005", + "input_cache_read": "0.00000002" }, "top_provider": { "context_length": 131072, - "max_completion_tokens": 16384, + "max_completion_tokens": 117964, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", "logit_bias", + "logprobs", "max_tokens", "min_p", "presence_penalty", @@ -12767,6 +13126,7 @@ "structured_outputs", "temperature", "top_k", + "top_logprobs", "top_p" ], "default_parameters": {}, @@ -12932,9 +13292,8 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000009", - "completion": "0.00000034", - "input_cache_read": "0.00000005" + "prompt": "0.0000002", + "completion": "0.0000004" }, "top_provider": { "context_length": 262144, @@ -13389,62 +13748,62 @@ { "arena": "models", "category": "3d", - "elo": 987, + "elo": 983, "win_rate": 21.9, - "rank": 107 + "rank": 115 }, { "arena": "models", "category": "asciiart", - "elo": 996, - "win_rate": 25, - "rank": 69 + "elo": 989, + "win_rate": 24.4, + "rank": 71 }, { "arena": "models", "category": "codecategories", "elo": 1022, - "win_rate": 21.3, - "rank": 111 + "win_rate": 21.4, + "rank": 121 }, { "arena": "models", "category": "dataviz", - "elo": 1015, - "win_rate": 22.4, - "rank": 108 + "elo": 1009, + "win_rate": 22.3, + "rank": 115 }, { "arena": "models", "category": "gamedev", - "elo": 997, - "win_rate": 19.5, - "rank": 112 + "elo": 985, + "win_rate": 18.9, + "rank": 125 }, { "arena": "models", "category": "svg", - "elo": 997, - "win_rate": 24.8, - "rank": 83 + "elo": 999, + "win_rate": 24.6, + "rank": 84 }, { "arena": "models", "category": "uicomponent", - "elo": 999, - "win_rate": 19.4, - "rank": 108 + "elo": 998, + "win_rate": 19.6, + "rank": 116 }, { "arena": "models", "category": "website", - "elo": 1035, - "win_rate": 21.8, - "rank": 114 + "elo": 1036, + "win_rate": 22.1, + "rank": 125 } ], "artificial_analysis": { - "intelligence_index": 13.8, + "intelligence_index": 10.8, "coding_index": 31.1, "agentic_index": 1.6 } @@ -13517,13 +13876,13 @@ } }, { - "id": "inclusionai/ling-3.0-flash", - "canonical_slug": "inclusionai/ling-3.0-flash-20260723", - "hugging_face_id": "inclusionAI/Ling-3.0-flash", - "name": "inclusionAI: Ling 3.0 Flash", - "created": 1784818580, - "description": "*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...", - "context_length": 262144, + "id": "inception/mercury-3", + "canonical_slug": "inception/mercury-3-20261019", + "hugging_face_id": null, + "name": "Inception: Mercury 3", + "created": 1792158337, + "description": "Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date. It is suited for agentic workflows and real-time applications where latency compounds, such...", + "context_length": 1000000, "architecture": { "modality": "text->text", "input_modalities": ["text"], @@ -13532,63 +13891,88 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000000021", - "completion": "0.000000063", - "input_cache_read": "0.0000000042" + "prompt": "0.0000001", + "completion": "0.00000035", + "input_cache_read": "0.00000001" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 32768, + "context_length": 1000000, + "max_completion_tokens": 131072, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", "include_reasoning", - "logit_bias", - "logprobs", "max_tokens", - "min_p", - "presence_penalty", "reasoning", - "repetition_penalty", + "reasoning_effort", "response_format", - "seed", "stop", + "structured_outputs", "temperature", "tool_choice", - "tools", - "top_k", - "top_logprobs", - "top_p" + "tools" ], "default_parameters": {}, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/inclusionai/ling-3.0-flash-20260723/endpoints" + "details": "/api/v1/models/inception/mercury-3-20261019/endpoints" }, "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 20.1, - "coding_index": 50.6, - "agentic_index": 19.3 - } + "design_arena": [ + { + "arena": "models", + "category": "codecategories", + "elo": 1239, + "win_rate": 46.3, + "rank": 46 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1207, + "win_rate": 45.6, + "rank": 55 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1227, + "win_rate": 44.4, + "rank": 44 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1266, + "win_rate": 47.6, + "rank": 35 + }, + { + "arena": "models", + "category": "website", + "elo": 1242, + "win_rate": 47.2, + "rank": 50 + } + ] }, "reasoning": { "mandatory": false, - "default_enabled": true + "default_enabled": true, + "supported_efforts": ["high", "medium", "low", "none"], + "default_effort": "medium" } }, { - "id": "inclusionai/ling-3.0-flash-fin", - "canonical_slug": "inclusionai/ling-3.0-flash-fin-20260827", - "hugging_face_id": null, - "name": "inclusionAI: Ling 3.0 Flash Fin", - "created": 1787846290, - "description": "Ling 3.0 Flash Fin is a finance-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters out of 124B total. It is designed for real-world investment...", + "id": "inclusionai/ling-3.0-flash", + "canonical_slug": "inclusionai/ling-3.0-flash-20260723", + "hugging_face_id": "inclusionAI/Ling-3.0-flash", + "name": "inclusionAI: Ling 3.0 Flash", + "created": 1784818580, + "description": "*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...", "context_length": 262144, "architecture": { "modality": "text->text", @@ -13598,9 +13982,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000000042", - "completion": "0.0000001232", - "input_cache_read": "0.0000000084" + "prompt": "0.000000021", + "completion": "0.000000063", + "input_cache_read": "0.0000000042" }, "top_provider": { "context_length": 262144, @@ -13618,9 +14002,9 @@ "presence_penalty", "reasoning", "repetition_penalty", + "response_format", "seed", "stop", - "structured_outputs", "temperature", "tool_choice", "tools", @@ -13633,14 +14017,14 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/inclusionai/ling-3.0-flash-fin-20260827/endpoints" + "details": "/api/v1/models/inclusionai/ling-3.0-flash-20260723/endpoints" }, "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 22.6, - "coding_index": 55.6, - "agentic_index": 27.9 + "intelligence_index": 20.1, + "coding_index": 50.6, + "agentic_index": 19.3 } }, "reasoning": { @@ -13648,60 +14032,6 @@ "default_enabled": true } }, - { - "id": "inclusionai/ling-3.0-flash-sante:free", - "canonical_slug": "inclusionai/ling-3.0-flash-sante-20260904", - "hugging_face_id": null, - "name": "inclusionAI: Ling 3.0 Flash Sante (free)", - "created": 1788545946, - "description": "Ling 3.0 Flash Sante is a health and medicine-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters out of 124B total. It is designed for...", - "context_length": 262144, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Other", - "instruct_type": null - }, - "pricing": { - "prompt": "0", - "completion": "0" - }, - "top_provider": { - "context_length": 262144, - "max_completion_tokens": 32768, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "include_reasoning", - "logprobs", - "max_tokens", - "presence_penalty", - "reasoning", - "repetition_penalty", - "seed", - "stop", - "temperature", - "tool_choice", - "tools", - "top_k", - "top_logprobs", - "top_p" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": null, - "links": { - "details": "/api/v1/models/inclusionai/ling-3.0-flash-sante-20260904/endpoints" - }, - "reasoning": { - "mandatory": false, - "default_enabled": true - } - }, { "id": "inclusionai/ling-3.0-flash-vl", "canonical_slug": "inclusionai/ling-3.0-flash-vl-20260910", @@ -13709,7 +14039,7 @@ "name": "inclusionAI: Ling 3.0 Flash VL", "created": 1789056114, "description": "Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual...", - "context_length": 262144, + "context_length": 131072, "architecture": { "modality": "text+image+video->text", "input_modalities": ["text", "image", "video"], @@ -13718,12 +14048,12 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000000021", - "completion": "0.0000000616", - "input_cache_read": "0.0000000042" + "prompt": "0.00000006", + "completion": "0.00000018", + "input_cache_read": "0.000000012" }, "top_provider": { - "context_length": 262144, + "context_length": 131072, "max_completion_tokens": 32768, "is_moderated": false }, @@ -13732,7 +14062,6 @@ "frequency_penalty", "include_reasoning", "logit_bias", - "logprobs", "max_tokens", "min_p", "presence_penalty", @@ -13746,7 +14075,6 @@ "tool_choice", "tools", "top_k", - "top_logprobs", "top_p" ], "default_parameters": {}, @@ -13785,25 +14113,30 @@ "instruct_type": null }, "pricing": { - "prompt": "0", - "completion": "0" + "prompt": "0.000000075", + "completion": "0.000000225", + "input_cache_read": "0.000000015" }, "top_provider": { "context_length": 262144, - "max_completion_tokens": 32768, + "max_completion_tokens": 235929, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", "include_reasoning", + "logit_bias", "logprobs", "max_tokens", + "min_p", "presence_penalty", "reasoning", "repetition_penalty", + "response_format", "seed", "stop", + "structured_outputs", "temperature", "tool_choice", "tools", @@ -13972,8 +14305,7 @@ "tool_choice", "tools", "top_k", - "top_logprobs", - "top_p" + "top_logprobs" ], "default_parameters": { "temperature": 0.1, @@ -13998,6 +14330,67 @@ "mandatory": true } }, + { + "id": "liquid/lfm-2.5-24b-a2b", + "canonical_slug": "liquid/lfm-2.5-24b-a2b-20261012", + "hugging_face_id": "LiquidAI/LFM2.5-24B-A2B", + "name": "LiquidAI: LFM2.5-24B-A2B", + "created": 1791912025, + "description": "LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid...", + "context_length": 128000, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000005", + "completion": "0.0000007", + "input_cache_read": "0.000000025" + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 8192, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logprobs", + "max_completion_tokens", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs" + ], + "default_parameters": { + "temperature": 0.1, + "top_k": 50, + "repetition_penalty": 1.05 + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/liquid/lfm-2.5-24b-a2b-20261012/endpoints" + }, + "reasoning": { + "mandatory": true + } + }, { "id": "mancer/weaver", "canonical_slug": "mancer/weaver", @@ -14301,12 +14694,12 @@ "instruct_type": "llama3" }, "pricing": { - "prompt": "0.00000005", - "completion": "0.00000033" + "prompt": "0.0000000509", + "completion": "0.000000335" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": 117964, + "context_length": 80000, + "max_completion_tokens": 72000, "is_moderated": false }, "per_request_limits": null, @@ -14358,9 +14751,8 @@ "instruct_type": "llama3" }, "pricing": { - "prompt": "0.00000022", - "completion": "0.0000005", - "input_cache_read": "0.00000011" + "prompt": "0.0000001", + "completion": "0.00000032" }, "top_provider": { "context_length": 131072, @@ -14410,7 +14802,7 @@ "name": "Meta: Llama 4 Maverick", "created": 1743881822, "description": "Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...", - "context_length": 1048576, + "context_length": 524288, "architecture": { "modality": "text+image->text", "input_modalities": ["text", "image"], @@ -14459,48 +14851,48 @@ { "arena": "models", "category": "3d", - "elo": 908, + "elo": 901, "win_rate": 40.2, - "rank": 113 + "rank": 121 }, { "arena": "models", "category": "codecategories", - "elo": 885, + "elo": 880, "win_rate": 35.8, - "rank": 124 + "rank": 135 }, { "arena": "models", "category": "dataviz", - "elo": 887, + "elo": 882, "win_rate": 38.4, - "rank": 123 + "rank": 130 }, { "arena": "models", "category": "gamedev", - "elo": 848, + "elo": 838, "win_rate": 33.7, - "rank": 125 + "rank": 139 }, { "arena": "models", "category": "uicomponent", - "elo": 906, + "elo": 899, "win_rate": 40.8, - "rank": 120 + "rank": 128 }, { "arena": "models", "category": "website", - "elo": 877, + "elo": 871, "win_rate": 34.4, - "rank": 129 + "rank": 140 } ], "artificial_analysis": { - "intelligence_index": 10, + "intelligence_index": 9.3, "coding_index": 16.3, "agentic_index": 0.6 } @@ -14560,41 +14952,41 @@ { "arena": "models", "category": "codecategories", - "elo": 795, + "elo": 790, "win_rate": 26.6, - "rank": 127 + "rank": 138 }, { "arena": "models", "category": "dataviz", - "elo": 901, + "elo": 896, "win_rate": 39.3, - "rank": 121 + "rank": 128 }, { "arena": "models", "category": "gamedev", - "elo": 783, + "elo": 773, "win_rate": 27.4, - "rank": 127 + "rank": 140 }, { "arena": "models", "category": "uicomponent", - "elo": 774, + "elo": 768, "win_rate": 25.5, - "rank": 124 + "rank": 132 }, { "arena": "models", "category": "website", - "elo": 755, + "elo": 750, "win_rate": 22.7, - "rank": 135 + "rank": 146 } ], "artificial_analysis": { - "intelligence_index": 8.1, + "intelligence_index": 6.5, "coding_index": 8.2, "agentic_index": 0.5 } @@ -14704,7 +15096,15 @@ "details": "/api/v1/models/meta/muse-glimmer-30b-20260810/endpoints" }, "benchmarks": { - "design_arena": [], + "design_arena": [ + { + "arena": "models", + "category": "gamedev", + "elo": 1164, + "win_rate": 35.6, + "rank": 72 + } + ], "artificial_analysis": { "intelligence_index": 17.5, "coding_index": 49, @@ -14771,113 +15171,120 @@ "arena": "agents", "category": "agenticgamedev", "elo": 1183, - "win_rate": 48.3, + "win_rate": 48.2, "rank": 11 }, { "arena": "agents", "category": "androidnative", - "elo": 1188, - "win_rate": 47.2, - "rank": 18 + "elo": 1178, + "win_rate": 47.7, + "rank": 17 }, { "arena": "agents", "category": "fullstack", - "elo": 1198, + "elo": 1199, "win_rate": 45.4, "rank": 17 }, { "arena": "agents", "category": "godotgamedev", - "elo": 1104, + "elo": 1103, "win_rate": 39.8, "rank": 29 }, { "arena": "agents", "category": "htmlslides", - "elo": 1194, + "elo": 1195, "win_rate": 51.8, "rank": 8 }, { "arena": "agents", "category": "mobileapps", - "elo": 1172, - "win_rate": 46.3, - "rank": 22 + "elo": 1175, + "win_rate": 46.1, + "rank": 23 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1156, + "elo": 1155, "win_rate": 44.1, "rank": 21 }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1042, + "win_rate": 33.3, + "rank": 18 + }, { "arena": "agents", "category": "webapps", - "elo": 1199, - "win_rate": 49.3, - "rank": 19 + "elo": 1207, + "win_rate": 49.1, + "rank": 21 }, { "arena": "models", "category": "3d", - "elo": 1267, + "elo": 1260, "win_rate": 49, - "rank": 22 + "rank": 29 }, { "arena": "models", "category": "asciiart", - "elo": 1288, - "win_rate": 56.8, - "rank": 6 + "elo": 1271, + "win_rate": 55, + "rank": 10 }, { "arena": "models", "category": "codecategories", - "elo": 1281, - "win_rate": 51.4, - "rank": 19 + "elo": 1276, + "win_rate": 51.2, + "rank": 26 }, { "arena": "models", "category": "dataviz", - "elo": 1276, - "win_rate": 50.5, - "rank": 20 + "elo": 1268, + "win_rate": 50.2, + "rank": 27 }, { "arena": "models", "category": "gamedev", - "elo": 1282, + "elo": 1269, "win_rate": 48, - "rank": 19 + "rank": 26 }, { "arena": "models", "category": "svg", - "elo": 1238, - "win_rate": 49.3, + "elo": 1235, + "win_rate": 49, "rank": 15 }, { "arena": "models", "category": "uicomponent", - "elo": 1296, - "win_rate": 51.4, - "rank": 18 + "elo": 1289, + "win_rate": 51.1, + "rank": 24 }, { "arena": "models", "category": "website", - "elo": 1275, - "win_rate": 51.5, - "rank": 25 + "elo": 1270, + "win_rate": 51.3, + "rank": 29 } ], "artificial_analysis": { @@ -14946,106 +15353,106 @@ "arena": "agents", "category": "agenticgamedev", "elo": 1179, - "win_rate": 42.7, + "win_rate": 42.5, "rank": 15 }, { "arena": "agents", "category": "androidnative", - "elo": 1236, - "win_rate": 53.2, + "elo": 1221, + "win_rate": 53.1, "rank": 10 }, { "arena": "agents", "category": "fullstack", - "elo": 1208, + "elo": 1210, "win_rate": 48, "rank": 15 }, { "arena": "agents", "category": "htmlslides", - "elo": 1134, + "elo": 1135, "win_rate": 40, "rank": 20 }, { "arena": "agents", "category": "mobileapps", - "elo": 1174, - "win_rate": 47.5, - "rank": 20 + "elo": 1181, + "win_rate": 47.7, + "rank": 22 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1198, - "win_rate": 48.6, + "elo": 1195, + "win_rate": 48.5, "rank": 15 }, { "arena": "agents", "category": "webapps", - "elo": 1215, - "win_rate": 50.6, - "rank": 14 + "elo": 1221, + "win_rate": 50.2, + "rank": 18 }, { "arena": "models", "category": "3d", - "elo": 1312, - "win_rate": 52, - "rank": 13 + "elo": 1302, + "win_rate": 51.8, + "rank": 19 }, { "arena": "models", "category": "asciiart", - "elo": 1303, - "win_rate": 58, + "elo": 1284, + "win_rate": 56.1, "rank": 4 }, { "arena": "models", "category": "codecategories", - "elo": 1319, + "elo": 1313, "win_rate": 52, - "rank": 7 + "rank": 12 }, { "arena": "models", "category": "dataviz", - "elo": 1347, - "win_rate": 58.4, - "rank": 6 + "elo": 1334, + "win_rate": 57.6, + "rank": 9 }, { "arena": "models", "category": "gamedev", - "elo": 1312, - "win_rate": 50.3, - "rank": 12 + "elo": 1302, + "win_rate": 50.5, + "rank": 19 }, { "arena": "models", "category": "svg", - "elo": 1290, - "win_rate": 55.8, - "rank": 9 + "elo": 1285, + "win_rate": 55.3, + "rank": 10 }, { "arena": "models", "category": "uicomponent", - "elo": 1307, - "win_rate": 52.1, - "rank": 14 + "elo": 1300, + "win_rate": 52, + "rank": 17 }, { "arena": "models", "category": "website", - "elo": 1319, - "win_rate": 52, - "rank": 5 + "elo": 1313, + "win_rate": 52.1, + "rank": 10 } ], "artificial_analysis": { @@ -15160,161 +15567,354 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/meta/muse-spark-1.3-20260902/endpoints" + "details": "/api/v1/models/meta/muse-spark-1.3-20260902/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "fullstack", + "elo": 1312, + "win_rate": 60.8, + "rank": 3 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1219, + "win_rate": 48.3, + "rank": 13 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1240, + "win_rate": 51.4, + "rank": 10 + }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1050, + "win_rate": 29.4, + "rank": 16 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1297, + "win_rate": 56.6, + "rank": 6 + }, + { + "arena": "models", + "category": "3d", + "elo": 1396, + "win_rate": 63.5, + "rank": 5 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1280, + "win_rate": 53.6, + "rank": 6 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1353, + "win_rate": 57.4, + "rank": 5 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1343, + "win_rate": 58.1, + "rank": 6 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1344, + "win_rate": 56, + "rank": 9 + }, + { + "arena": "models", + "category": "svg", + "elo": 1325, + "win_rate": 54.4, + "rank": 2 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1351, + "win_rate": 57.9, + "rank": 4 + }, + { + "arena": "models", + "category": "website", + "elo": 1356, + "win_rate": 58.2, + "rank": 2 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1241, + "win_rate": 45.8, + "rank": 7 + } + ], + "artificial_analysis": { + "intelligence_index": 48.1, + "coding_index": 75.8, + "agentic_index": 55.5 + } + }, + "reasoning": { + "mandatory": true, + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "minimal"], + "default_effort": "medium" + } + }, + { + "id": "meta/muse-spark-1.3-contributor", + "canonical_slug": "meta/muse-spark-1.3-contributor-20260902", + "hugging_face_id": null, + "name": "Meta: Muse Spark 1.3 Contributor", + "created": 1788381519, + "description": "Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. It is designed to track information...", + "context_length": 1048576, + "architecture": { + "modality": "text+image+file+video->text", + "input_modalities": ["text", "image", "video", "file"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000001", + "completion": "0.0000002", + "web_search": "0.0025", + "input_cache_read": "0.000000002" + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 943718, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "reasoning_effort", + "repetition_penalty", + "response_format", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/meta/muse-spark-1.3-contributor-20260902/endpoints" + }, + "reasoning": { + "mandatory": true, + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "minimal"], + "default_effort": "medium" + } + }, + { + "id": "meta/muse-spark-open", + "canonical_slug": "meta/muse-spark-open-20261015", + "hugging_face_id": "meta-models/Muse-Spark-Open-816B-A42B", + "name": "Meta: Muse Spark Open", + "created": 1792087069, + "description": "Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers...", + "context_length": 1048576, + "architecture": { + "modality": "text+image+file+audio+video->text", + "input_modalities": ["text", "image", "video", "file", "audio"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000125", + "completion": "0.00000425", + "input_cache_read": "0.00000015" + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 943718, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "reasoning_effort", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/meta/muse-spark-open-20261015/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "gamedev", + "elo": 1289, + "win_rate": 53, + "rank": 22 + }, + { + "arena": "models", + "category": "website", + "elo": 1317, + "win_rate": 56.5, + "rank": 7 + } + ] + }, + "reasoning": { + "mandatory": true, + "supported_efforts": ["xhigh", "high", "medium", "low"], + "default_effort": "medium" + } + }, + { + "id": "meta/muse-wonder", + "canonical_slug": "meta/muse-wonder-20261012", + "hugging_face_id": null, + "name": "Meta: Muse Wonder", + "created": 1791807945, + "description": "Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...", + "context_length": 1048576, + "architecture": { + "modality": "text+image+file+audio+video->text", + "input_modalities": ["text", "image", "video", "file", "audio"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.000004", + "completion": "0.00002", + "web_search": "0.0025", + "input_cache_read": "0.0000002" + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 943718, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "reasoning_effort", + "repetition_penalty", + "response_format", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/meta/muse-wonder-20261012/endpoints" }, "benchmarks": { "design_arena": [ { "arena": "agents", - "category": "fullstack", - "elo": 1311, - "win_rate": 60.8, - "rank": 3 - }, - { - "arena": "agents", - "category": "mobileapps", - "elo": 1219, - "win_rate": 47.9, - "rank": 10 - }, - { - "arena": "agents", - "category": "python-pptxslides", - "elo": 1244, - "win_rate": 51.4, - "rank": 10 - }, - { - "arena": "agents", - "category": "webapps", - "elo": 1289, - "win_rate": 56.5, - "rank": 2 + "category": "spreadsheet", + "elo": 1221, + "win_rate": 49.7, + "rank": 9 }, { "arena": "models", "category": "3d", - "elo": 1408, - "win_rate": 63.9, - "rank": 2 - }, - { - "arena": "models", - "category": "asciiart", - "elo": 1260, - "win_rate": 51.9, - "rank": 17 + "elo": 1426, + "win_rate": 67.7, + "rank": 4 }, { "arena": "models", "category": "codecategories", - "elo": 1359, - "win_rate": 57.3, - "rank": 3 + "elo": 1371, + "win_rate": 63, + "rank": 2 }, { "arena": "models", "category": "dataviz", - "elo": 1346, - "win_rate": 57.5, - "rank": 7 + "elo": 1321, + "win_rate": 56.9, + "rank": 12 }, { "arena": "models", "category": "gamedev", - "elo": 1355, - "win_rate": 56.1, - "rank": 4 - }, - { - "arena": "models", - "category": "svg", - "elo": 1320, - "win_rate": 52.8, - "rank": 2 + "elo": 1379, + "win_rate": 63.1, + "rank": 5 }, { "arena": "models", "category": "uicomponent", - "elo": 1359, - "win_rate": 58, - "rank": 4 + "elo": 1376, + "win_rate": 62.5, + "rank": 2 }, { "arena": "models", "category": "website", - "elo": 1363, - "win_rate": 58.1, + "elo": 1362, + "win_rate": 62.5, "rank": 1 - }, - { - "arena": "agents", - "category": "godotgamedev", - "elo": 1241, - "win_rate": 45.8, - "rank": 7 } - ], - "artificial_analysis": { - "intelligence_index": 48.1, - "coding_index": 75.8, - "agentic_index": 55.5 - } - }, - "reasoning": { - "mandatory": true, - "supported_efforts": ["max", "xhigh", "high", "medium", "low", "minimal"], - "default_effort": "medium" - } - }, - { - "id": "meta/muse-spark-1.3-contributor", - "canonical_slug": "meta/muse-spark-1.3-contributor-20260902", - "hugging_face_id": null, - "name": "Meta: Muse Spark 1.3 Contributor", - "created": 1788381519, - "description": "Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. It is designed to track information...", - "context_length": 1048576, - "architecture": { - "modality": "text+image+file+video->text", - "input_modalities": ["text", "image", "video", "file"], - "output_modalities": ["text"], - "tokenizer": "Other", - "instruct_type": null - }, - "pricing": { - "prompt": "0.0000001", - "completion": "0.0000002", - "web_search": "0.0025", - "input_cache_read": "0.000000002" - }, - "top_provider": { - "context_length": 1048576, - "max_completion_tokens": 943718, - "is_moderated": true - }, - "per_request_limits": null, - "supported_parameters": [ - "include_reasoning", - "max_tokens", - "reasoning", - "reasoning_effort", - "repetition_penalty", - "response_format", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_k", - "top_p" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": null, - "links": { - "details": "/api/v1/models/meta/muse-spark-1.3-contributor-20260902/endpoints" + ] }, "reasoning": { "mandatory": true, @@ -15378,51 +15978,6 @@ } } }, - { - "id": "microsoft/wizardlm-2-8x22b", - "canonical_slug": "microsoft/wizardlm-2-8x22b", - "hugging_face_id": "microsoft/WizardLM-2-8x22B", - "name": "WizardLM-2 8x22B", - "created": 1713225600, - "description": "WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models. It is...", - "context_length": 65535, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Mistral", - "instruct_type": "vicuna" - }, - "pricing": { - "prompt": "0.00000062", - "completion": "0.00000062" - }, - "top_provider": { - "context_length": 65535, - "max_completion_tokens": 8000, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "max_tokens", - "presence_penalty", - "repetition_penalty", - "response_format", - "seed", - "stop", - "temperature", - "top_k", - "top_p" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": "2024-04-30", - "expiration_date": null, - "links": { - "details": "/api/v1/models/microsoft/wizardlm-2-8x22b/endpoints" - } - }, { "id": "minimax/minimax-01", "canonical_slug": "minimax/minimax-01", @@ -15540,12 +16095,12 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000003", - "completion": "0.0000012" + "prompt": "0.000000255", + "completion": "0.00000102" }, "top_provider": { - "context_length": 196608, - "max_completion_tokens": 176947, + "context_length": 204800, + "max_completion_tokens": 131072, "is_moderated": false }, "per_request_limits": null, @@ -15584,51 +16139,51 @@ { "arena": "models", "category": "3d", - "elo": 1105, + "elo": 1098, "win_rate": 48.3, - "rank": 82 + "rank": 90 }, { "arena": "models", "category": "codecategories", - "elo": 1139, + "elo": 1135, "win_rate": 48.1, - "rank": 84 + "rank": 95 }, { "arena": "models", "category": "dataviz", - "elo": 1147, + "elo": 1140, "win_rate": 50, - "rank": 77 + "rank": 86 }, { "arena": "models", "category": "gamedev", - "elo": 1128, + "elo": 1118, "win_rate": 48.1, - "rank": 80 + "rank": 91 }, { "arena": "models", "category": "svg", - "elo": 1099, + "elo": 1100, "win_rate": 55.3, - "rank": 59 + "rank": 60 }, { "arena": "models", "category": "uicomponent", - "elo": 1143, + "elo": 1137, "win_rate": 49.2, - "rank": 77 + "rank": 85 }, { "arena": "models", "category": "website", - "elo": 1149, + "elo": 1143, "win_rate": 48, - "rank": 84 + "rank": 97 } ], "artificial_analysis": { @@ -15707,19 +16262,13 @@ }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", "include_reasoning", "max_tokens", - "presence_penalty", "reasoning", - "repetition_penalty", "response_format", - "seed", - "stop", "temperature", "tool_choice", "tools", - "top_k", "top_p" ], "default_parameters": { @@ -15738,51 +16287,51 @@ { "arena": "models", "category": "3d", - "elo": 1173, + "elo": 1165, "win_rate": 57.5, - "rank": 54 + "rank": 62 }, { "arena": "models", "category": "codecategories", - "elo": 1196, + "elo": 1190, "win_rate": 55.3, - "rank": 52 + "rank": 61 }, { "arena": "models", "category": "dataviz", - "elo": 1213, + "elo": 1206, "win_rate": 57, - "rank": 49 + "rank": 56 }, { "arena": "models", "category": "gamedev", - "elo": 1145, + "elo": 1134, "win_rate": 50.4, - "rank": 73 + "rank": 85 }, { "arena": "models", "category": "svg", - "elo": 1131, + "elo": 1132, "win_rate": 55.4, - "rank": 52 + "rank": 53 }, { "arena": "models", "category": "uicomponent", - "elo": 1230, + "elo": 1223, "win_rate": 60.9, - "rank": 44 + "rank": 51 }, { "arena": "models", "category": "website", - "elo": 1206, + "elo": 1201, "win_rate": 55.4, - "rank": 54 + "rank": 63 } ], "artificial_analysis": { @@ -15812,12 +16361,12 @@ }, "pricing": { "prompt": "0.00000027", - "completion": "0.00000108", - "input_cache_read": "0.000000027" + "completion": "0.00000095", + "input_cache_read": "0.00000003" }, "top_provider": { - "context_length": 200000, - "max_completion_tokens": 128000, + "context_length": 198000, + "max_completion_tokens": 32768, "is_moderated": false }, "per_request_limits": null, @@ -15861,51 +16410,51 @@ { "arena": "models", "category": "3d", - "elo": 1178, + "elo": 1170, "win_rate": 57.6, - "rank": 52 + "rank": 60 }, { "arena": "models", "category": "codecategories", - "elo": 1211, + "elo": 1207, "win_rate": 56.8, - "rank": 48 + "rank": 57 }, { "arena": "models", "category": "dataviz", - "elo": 1178, + "elo": 1172, "win_rate": 51.2, - "rank": 62 + "rank": 70 }, { "arena": "models", "category": "gamedev", - "elo": 1187, + "elo": 1176, "win_rate": 55.5, - "rank": 54 + "rank": 64 }, { "arena": "models", "category": "svg", - "elo": 1148, + "elo": 1150, "win_rate": 54.5, "rank": 44 }, { "arena": "models", "category": "uicomponent", - "elo": 1179, + "elo": 1173, "win_rate": 53.4, - "rank": 61 + "rank": 69 }, { "arena": "models", "category": "website", - "elo": 1227, + "elo": 1222, "win_rate": 57.5, - "rank": 50 + "rank": 58 } ], "artificial_analysis": { @@ -15934,13 +16483,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000021", - "completion": "0.00000084", - "input_cache_read": "0.000000042" + "prompt": "0.0000003", + "completion": "0.0000012", + "input_cache_read": "0.00000006" }, "top_provider": { - "context_length": 196608, - "max_completion_tokens": 176947, + "context_length": 204800, + "max_completion_tokens": 131072, "is_moderated": false }, "per_request_limits": null, @@ -15981,58 +16530,58 @@ { "arena": "models", "category": "3d", - "elo": 1202, + "elo": 1195, "win_rate": 49.9, - "rank": 44 + "rank": 51 }, { "arena": "models", "category": "asciiart", - "elo": 1146, - "win_rate": 46.7, - "rank": 48 + "elo": 1136, + "win_rate": 46.5, + "rank": 51 }, { "arena": "models", "category": "codecategories", - "elo": 1238, - "win_rate": 51, - "rank": 40 + "elo": 1233, + "win_rate": 50.9, + "rank": 49 }, { "arena": "models", "category": "dataviz", - "elo": 1239, + "elo": 1233, "win_rate": 52.4, - "rank": 37 + "rank": 45 }, { "arena": "models", "category": "gamedev", - "elo": 1221, - "win_rate": 50, - "rank": 42 + "elo": 1209, + "win_rate": 49.5, + "rank": 52 }, { "arena": "models", "category": "svg", - "elo": 1136, - "win_rate": 47.4, - "rank": 51 + "elo": 1137, + "win_rate": 47.3, + "rank": 52 }, { "arena": "models", "category": "uicomponent", - "elo": 1216, + "elo": 1210, "win_rate": 48.5, - "rank": 48 + "rank": 55 }, { "arena": "models", "category": "website", - "elo": 1248, - "win_rate": 51.5, - "rank": 39 + "elo": 1243, + "win_rate": 51.4, + "rank": 48 } ], "artificial_analysis": { @@ -16112,106 +16661,113 @@ "arena": "agents", "category": "agenticgamedev", "elo": 1158, - "win_rate": 44.6, + "win_rate": 44.2, "rank": 19 }, { "arena": "agents", "category": "androidnative", - "elo": 1171, + "elo": 1158, "win_rate": 44.3, - "rank": 23 + "rank": 24 }, { "arena": "agents", "category": "fullstack", - "elo": 1196, - "win_rate": 47.3, - "rank": 18 + "elo": 1197, + "win_rate": 47.2, + "rank": 19 }, { "arena": "agents", "category": "htmlslides", "elo": 1180, - "win_rate": 46.6, + "win_rate": 46.7, "rank": 12 }, { "arena": "agents", "category": "mobileapps", - "elo": 1167, - "win_rate": 46, - "rank": 23 + "elo": 1169, + "win_rate": 45.8, + "rank": 25 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1204, - "win_rate": 46.8, + "elo": 1203, + "win_rate": 47, "rank": 14 }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1052, + "win_rate": 46.8, + "rank": 15 + }, { "arena": "agents", "category": "webapps", - "elo": 1192, - "win_rate": 47.1, - "rank": 21 + "elo": 1200, + "win_rate": 46.9, + "rank": 24 }, { "arena": "models", "category": "3d", - "elo": 1216, - "win_rate": 50.2, - "rank": 40 + "elo": 1209, + "win_rate": 50.1, + "rank": 47 }, { "arena": "models", "category": "asciiart", - "elo": 1169, - "win_rate": 46.8, - "rank": 34 + "elo": 1161, + "win_rate": 46.4, + "rank": 36 }, { "arena": "models", "category": "codecategories", - "elo": 1252, - "win_rate": 50.9, - "rank": 33 + "elo": 1247, + "win_rate": 50.8, + "rank": 41 }, { "arena": "models", "category": "dataviz", - "elo": 1241, - "win_rate": 51.3, - "rank": 36 + "elo": 1236, + "win_rate": 51.4, + "rank": 41 }, { "arena": "models", "category": "gamedev", - "elo": 1223, - "win_rate": 46, - "rank": 40 + "elo": 1211, + "win_rate": 45.7, + "rank": 50 }, { "arena": "models", "category": "svg", "elo": 1162, "win_rate": 45.2, - "rank": 38 + "rank": 39 }, { "arena": "models", "category": "uicomponent", - "elo": 1253, - "win_rate": 50.9, - "rank": 36 + "elo": 1245, + "win_rate": 50.6, + "rank": 43 }, { "arena": "models", "category": "website", - "elo": 1263, - "win_rate": 51.9, - "rank": 32 + "elo": 1257, + "win_rate": 51.7, + "rank": 40 } ], "artificial_analysis": { @@ -16224,6 +16780,63 @@ "mandatory": false } }, + { + "id": "minimax/minimax-m3.1-flash:free", + "canonical_slug": "minimax/minimax-m3.1-flash-20261019", + "hugging_face_id": null, + "name": "MiniMax: MiniMax M3.1 Flash (free)", + "created": 1792379569, + "description": "MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex,...", + "context_length": 1000000, + "architecture": { + "modality": "text+image+video->text", + "input_modalities": ["text", "image", "video"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0", + "completion": "0" + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 524288, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "reasoning_effort", + "response_format", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/minimax/minimax-m3.1-flash-20261019/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 42.7, + "coding_index": null, + "agentic_index": null + } + }, + "reasoning": { + "mandatory": true, + "supported_efforts": ["max", "xhigh", "high", "medium", "low"], + "default_effort": "max" + } + }, { "id": "mistralai/codestral-2508", "canonical_slug": "mistralai/codestral-2508", @@ -16278,44 +16891,44 @@ { "arena": "models", "category": "codecategories", - "elo": 1011, + "elo": 1007, "win_rate": 38.5, - "rank": 113 + "rank": 124 }, { "arena": "models", "category": "dataviz", - "elo": 1024, + "elo": 1017, "win_rate": 41.1, - "rank": 106 + "rank": 114 }, { "arena": "models", "category": "gamedev", - "elo": 978, + "elo": 968, "win_rate": 36.3, - "rank": 115 + "rank": 128 }, { "arena": "models", "category": "uicomponent", - "elo": 1024, + "elo": 1017, "win_rate": 46.7, - "rank": 105 + "rank": 113 }, { "arena": "models", "category": "website", - "elo": 1019, + "elo": 1013, "win_rate": 37.8, - "rank": 118 + "rank": 129 }, { "arena": "models", "category": "3d", - "elo": 1028, + "elo": 1020, "win_rate": 45.4, - "rank": 101 + "rank": 109 } ] } @@ -16374,44 +16987,44 @@ { "arena": "models", "category": "codecategories", - "elo": 1011, + "elo": 1007, "win_rate": 38.5, - "rank": 113 + "rank": 124 }, { "arena": "models", "category": "dataviz", - "elo": 1024, + "elo": 1017, "win_rate": 41.1, - "rank": 106 + "rank": 114 }, { "arena": "models", "category": "gamedev", - "elo": 978, + "elo": 968, "win_rate": 36.3, - "rank": 115 + "rank": 128 }, { "arena": "models", "category": "uicomponent", - "elo": 1024, + "elo": 1017, "win_rate": 46.7, - "rank": 105 + "rank": 113 }, { "arena": "models", "category": "website", - "elo": 1019, + "elo": 1013, "win_rate": 37.8, - "rank": 118 + "rank": 129 }, { "arena": "models", "category": "3d", - "elo": 1028, + "elo": 1020, "win_rate": 45.4, - "rank": 101 + "rank": 109 } ] } @@ -16530,30 +17143,30 @@ { "arena": "models", "category": "3d", - "elo": 998, + "elo": 990, "win_rate": 39.6, - "rank": 105 + "rank": 113 }, { "arena": "models", "category": "codecategories", - "elo": 1069, + "elo": 1065, "win_rate": 44, - "rank": 100 + "rank": 112 }, { "arena": "models", "category": "gamedev", - "elo": 1048, + "elo": 1038, "win_rate": 43.6, - "rank": 103 + "rank": 116 }, { "arena": "models", "category": "website", - "elo": 1086, + "elo": 1081, "win_rate": 44.8, - "rank": 103 + "rank": 114 } ], "artificial_analysis": { @@ -16618,30 +17231,30 @@ { "arena": "models", "category": "3d", - "elo": 970, + "elo": 963, "win_rate": 35.9, - "rank": 110 + "rank": 118 }, { "arena": "models", "category": "codecategories", - "elo": 1014, + "elo": 1010, "win_rate": 37.3, - "rank": 112 + "rank": 123 }, { "arena": "models", "category": "gamedev", - "elo": 959, + "elo": 949, "win_rate": 33, - "rank": 118 + "rank": 132 }, { "arena": "models", "category": "website", - "elo": 1034, + "elo": 1028, "win_rate": 38.2, - "rank": 116 + "rank": 127 } ], "artificial_analysis": { @@ -16706,30 +17319,30 @@ { "arena": "models", "category": "3d", - "elo": 1040, + "elo": 1032, "win_rate": 46.2, - "rank": 99 + "rank": 108 }, { "arena": "models", "category": "codecategories", - "elo": 1057, + "elo": 1053, "win_rate": 42.9, - "rank": 103 + "rank": 114 }, { "arena": "models", "category": "gamedev", - "elo": 1001, + "elo": 990, "win_rate": 38.7, - "rank": 111 + "rank": 124 }, { "arena": "models", "category": "website", - "elo": 1070, + "elo": 1065, "win_rate": 42.9, - "rank": 105 + "rank": 116 } ], "artificial_analysis": { @@ -16794,30 +17407,30 @@ { "arena": "models", "category": "3d", - "elo": 1040, + "elo": 1032, "win_rate": 46.2, - "rank": 99 + "rank": 108 }, { "arena": "models", "category": "codecategories", - "elo": 1057, + "elo": 1053, "win_rate": 42.9, - "rank": 103 + "rank": 114 }, { "arena": "models", "category": "gamedev", - "elo": 1001, + "elo": 990, "win_rate": 38.7, - "rank": 111 + "rank": 124 }, { "arena": "models", "category": "website", - "elo": 1070, + "elo": 1065, "win_rate": 42.9, - "rank": 105 + "rank": 116 } ], "artificial_analysis": { @@ -16996,58 +17609,58 @@ { "arena": "models", "category": "3d", - "elo": 1107, + "elo": 1099, "win_rate": 46.9, - "rank": 81 + "rank": 89 }, { "arena": "models", "category": "asciiart", - "elo": 1078, + "elo": 1069, "win_rate": 40.3, - "rank": 64 + "rank": 66 }, { "arena": "models", "category": "codecategories", - "elo": 1147, + "elo": 1142, "win_rate": 47.6, - "rank": 79 + "rank": 92 }, { "arena": "models", "category": "dataviz", - "elo": 1143, + "elo": 1136, "win_rate": 45.7, - "rank": 79 + "rank": 87 }, { "arena": "models", "category": "gamedev", - "elo": 1090, + "elo": 1080, "win_rate": 41.5, - "rank": 92 + "rank": 105 }, { "arena": "models", "category": "svg", - "elo": 992, + "elo": 993, "win_rate": 38, - "rank": 84 + "rank": 85 }, { "arena": "models", "category": "uicomponent", - "elo": 1107, + "elo": 1102, "win_rate": 43, - "rank": 87 + "rank": 94 }, { "arena": "models", "category": "website", - "elo": 1167, + "elo": 1162, "win_rate": 49.5, - "rank": 77 + "rank": 87 } ], "artificial_analysis": { @@ -17112,58 +17725,58 @@ { "arena": "models", "category": "3d", - "elo": 1107, + "elo": 1099, "win_rate": 46.9, - "rank": 81 + "rank": 89 }, { "arena": "models", "category": "asciiart", - "elo": 1078, + "elo": 1069, "win_rate": 40.3, - "rank": 64 + "rank": 66 }, { "arena": "models", "category": "codecategories", - "elo": 1147, + "elo": 1142, "win_rate": 47.6, - "rank": 79 + "rank": 92 }, { "arena": "models", "category": "dataviz", - "elo": 1143, + "elo": 1136, "win_rate": 45.7, - "rank": 79 + "rank": 87 }, { "arena": "models", "category": "gamedev", - "elo": 1090, + "elo": 1080, "win_rate": 41.5, - "rank": 92 + "rank": 105 }, { "arena": "models", "category": "svg", - "elo": 992, + "elo": 993, "win_rate": 38, - "rank": 84 + "rank": 85 }, { "arena": "models", "category": "uicomponent", - "elo": 1107, + "elo": 1102, "win_rate": 43, - "rank": 87 + "rank": 94 }, { "arena": "models", "category": "website", - "elo": 1167, + "elo": 1162, "win_rate": 49.5, - "rank": 77 + "rank": 87 } ], "artificial_analysis": { @@ -17179,8 +17792,8 @@ "hugging_face_id": null, "name": "Mistral: Mistral Large 4", "created": 1791294122, - "description": "Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 512K-token context window with up...", - "context_length": 524288, + "description": "Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up...", + "context_length": 1048576, "architecture": { "modality": "text+image->text", "input_modalities": ["text", "image"], @@ -17189,12 +17802,12 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000068", - "completion": "0.00000209", - "input_cache_read": "0.00000007" + "prompt": "0.00000136", + "completion": "0.00000418", + "input_cache_read": "0.00000014" }, "top_provider": { - "context_length": 524288, + "context_length": 1048576, "max_completion_tokens": 262144, "is_moderated": false }, @@ -17224,6 +17837,71 @@ "links": { "details": "/api/v1/models/mistralai/mistral-large-4-0-20261006/endpoints" }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1253, + "win_rate": 45, + "rank": 32 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1202, + "win_rate": 43.5, + "rank": 24 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1259, + "win_rate": 46.6, + "rank": 38 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1275, + "win_rate": 51, + "rank": 24 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1226, + "win_rate": 42.2, + "rank": 45 + }, + { + "arena": "models", + "category": "svg", + "elo": 1233, + "win_rate": 45.3, + "rank": 17 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1275, + "win_rate": 47.8, + "rank": 30 + }, + { + "arena": "models", + "category": "website", + "elo": 1258, + "win_rate": 47.2, + "rank": 39 + } + ], + "artificial_analysis": { + "intelligence_index": 38.4, + "coding_index": null, + "agentic_index": null + } + }, "reasoning": { "mandatory": false, "default_enabled": true, @@ -17284,44 +17962,44 @@ { "arena": "models", "category": "3d", - "elo": 1091, + "elo": 1084, "win_rate": 54.7, - "rank": 84 + "rank": 92 }, { "arena": "models", "category": "codecategories", - "elo": 1073, + "elo": 1069, "win_rate": 48.1, - "rank": 99 + "rank": 110 }, { "arena": "models", "category": "dataviz", - "elo": 1040, + "elo": 1034, "win_rate": 46, - "rank": 104 + "rank": 112 }, { "arena": "models", "category": "gamedev", - "elo": 1028, + "elo": 1018, "win_rate": 45.2, - "rank": 107 + "rank": 120 }, { "arena": "models", "category": "uicomponent", - "elo": 1031, + "elo": 1025, "win_rate": 49.6, - "rank": 103 + "rank": 112 }, { "arena": "models", "category": "website", - "elo": 1085, + "elo": 1079, "win_rate": 47.6, - "rank": 104 + "rank": 115 } ], "artificial_analysis": { @@ -17522,58 +18200,58 @@ { "arena": "models", "category": "3d", - "elo": 1089, + "elo": 1081, "win_rate": 44.6, - "rank": 85 + "rank": 95 }, { "arena": "models", "category": "asciiart", - "elo": 1006, + "elo": 997, "win_rate": 30.8, - "rank": 68 + "rank": 70 }, { "arena": "models", "category": "codecategories", - "elo": 1125, + "elo": 1120, "win_rate": 45.1, - "rank": 85 + "rank": 96 }, { "arena": "models", "category": "dataviz", - "elo": 1151, + "elo": 1144, "win_rate": 47.2, - "rank": 76 + "rank": 83 }, { "arena": "models", "category": "gamedev", - "elo": 1084, + "elo": 1074, "win_rate": 40.8, - "rank": 94 + "rank": 107 }, { "arena": "models", "category": "svg", - "elo": 992, + "elo": 993, "win_rate": 38.2, - "rank": 85 + "rank": 86 }, { "arena": "models", "category": "uicomponent", - "elo": 1106, + "elo": 1100, "win_rate": 43.6, - "rank": 88 + "rank": 96 }, { "arena": "models", "category": "website", - "elo": 1139, + "elo": 1133, "win_rate": 46, - "rank": 88 + "rank": 99 } ], "artificial_analysis": { @@ -17636,58 +18314,58 @@ { "arena": "models", "category": "3d", - "elo": 1089, + "elo": 1081, "win_rate": 44.6, - "rank": 85 + "rank": 95 }, { "arena": "models", "category": "asciiart", - "elo": 1006, + "elo": 997, "win_rate": 30.8, - "rank": 68 + "rank": 70 }, { "arena": "models", "category": "codecategories", - "elo": 1125, + "elo": 1120, "win_rate": 45.1, - "rank": 85 + "rank": 96 }, { "arena": "models", "category": "dataviz", - "elo": 1151, + "elo": 1144, "win_rate": 47.2, - "rank": 76 + "rank": 83 }, { "arena": "models", "category": "gamedev", - "elo": 1084, + "elo": 1074, "win_rate": 40.8, - "rank": 94 + "rank": 107 }, { "arena": "models", "category": "svg", - "elo": 992, + "elo": 993, "win_rate": 38.2, - "rank": 85 + "rank": 86 }, { "arena": "models", "category": "uicomponent", - "elo": 1106, + "elo": 1100, "win_rate": 43.6, - "rank": 88 + "rank": 96 }, { "arena": "models", "category": "website", - "elo": 1139, + "elo": 1133, "win_rate": 46, - "rank": 88 + "rank": 99 } ], "artificial_analysis": { @@ -17713,7 +18391,7 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000000019", + "prompt": "0.000000029", "completion": "0.00000003" }, "top_provider": { @@ -18121,37 +18799,37 @@ { "arena": "models", "category": "codecategories", - "elo": 911, + "elo": 907, "win_rate": 39.8, - "rank": 123 + "rank": 134 }, { "arena": "models", "category": "dataviz", - "elo": 934, + "elo": 929, "win_rate": 43.3, - "rank": 118 + "rank": 125 }, { "arena": "models", "category": "gamedev", - "elo": 899, + "elo": 889, "win_rate": 39.4, - "rank": 124 + "rank": 137 }, { "arena": "models", "category": "uicomponent", - "elo": 912, + "elo": 907, "win_rate": 40.5, - "rank": 118 + "rank": 127 }, { "arena": "models", "category": "website", - "elo": 902, + "elo": 896, "win_rate": 38.3, - "rank": 127 + "rank": 139 } ] } @@ -18265,6 +18943,102 @@ "details": "/api/v1/models/mistralai/voxtral-small-24b-2507/endpoints" } }, + { + "id": "moondream/moondream3-preview", + "canonical_slug": "moondream/moondream3-preview-20261013", + "hugging_face_id": "moondream/moondream3-preview", + "name": "Moondream: Moondream 3 Preview", + "created": 1792102385, + "description": "Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with...", + "context_length": 32000, + "architecture": { + "modality": "text+image->text", + "input_modalities": ["text", "image"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000003", + "completion": "0.0000025" + }, + "top_provider": { + "context_length": 32000, + "max_completion_tokens": 4096, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_completion_tokens", + "max_tokens", + "reasoning", + "temperature", + "top_p" + ], + "default_parameters": { + "temperature": 0.2, + "top_p": 0.9 + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/moondream/moondream3-preview-20261013/endpoints" + }, + "reasoning": { + "mandatory": false, + "default_enabled": false + } + }, + { + "id": "moondream/moondream3.1-9b-a2b", + "canonical_slug": "moondream/moondream3.1-9b-a2b-20261013", + "hugging_face_id": "moondream/moondream3.1-9B-A2B", + "name": "Moondream: Moondream 3.1", + "created": 1792102373, + "description": "Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and...", + "context_length": 32000, + "architecture": { + "modality": "text+image->text", + "input_modalities": ["text", "image"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000003", + "completion": "0.0000025" + }, + "top_provider": { + "context_length": 32000, + "max_completion_tokens": 4096, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_completion_tokens", + "max_tokens", + "reasoning", + "temperature", + "top_p" + ], + "default_parameters": { + "temperature": 0.2, + "top_p": 0.9 + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/moondream/moondream3.1-9b-a2b-20261013/endpoints" + }, + "reasoning": { + "mandatory": false, + "default_enabled": false + } + }, { "id": "moonshotai/kimi-k2", "canonical_slug": "moonshotai/kimi-k2", @@ -18315,37 +19089,37 @@ { "arena": "models", "category": "codecategories", - "elo": 1039, + "elo": 1034, "win_rate": 51.7, - "rank": 106 + "rank": 117 }, { "arena": "models", "category": "dataviz", - "elo": 1023, + "elo": 1018, "win_rate": 49.4, - "rank": 107 + "rank": 113 }, { "arena": "models", "category": "gamedev", - "elo": 984, + "elo": 974, "win_rate": 46.4, - "rank": 113 + "rank": 126 }, { "arena": "models", "category": "uicomponent", - "elo": 1037, + "elo": 1030, "win_rate": 55.1, - "rank": 101 + "rank": 110 }, { "arena": "models", "category": "website", - "elo": 1055, + "elo": 1050, "win_rate": 53.1, - "rank": 110 + "rank": 121 } ], "artificial_analysis": { @@ -18407,16 +19181,16 @@ { "arena": "models", "category": "codecategories", - "elo": 1102, + "elo": 1098, "win_rate": 48.5, - "rank": 94 + "rank": 105 }, { "arena": "models", "category": "website", - "elo": 1112, + "elo": 1107, "win_rate": 48.3, - "rank": 97 + "rank": 108 } ], "artificial_analysis": { @@ -18443,11 +19217,12 @@ }, "pricing": { "prompt": "0.0000006", - "completion": "0.0000025" + "completion": "0.0000025", + "input_cache_read": "0.00000015" }, "top_provider": { "context_length": 262144, - "max_completion_tokens": 235929, + "max_completion_tokens": 98304, "is_moderated": false }, "per_request_limits": null, @@ -18489,9 +19264,9 @@ { "arena": "models", "category": "website", - "elo": 1118, + "elo": 1113, "win_rate": 48.8, - "rank": 95 + "rank": 106 } ], "artificial_analysis": { @@ -18521,9 +19296,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000045", - "completion": "0.00000225", - "input_cache_read": "0.00000007" + "prompt": "0.0000005", + "completion": "0.0000025", + "input_cache_read": "0.00000015" }, "top_provider": { "context_length": 262144, @@ -18571,14 +19346,14 @@ { "arena": "agents", "category": "androidnative", - "elo": 1133, + "elo": 1118, "win_rate": 57.8, - "rank": 26 + "rank": 27 }, { "arena": "agents", "category": "fullstack", - "elo": 1112, + "elo": 1114, "win_rate": 54.5, "rank": 28 }, @@ -18592,72 +19367,72 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1144, + "elo": 1147, "win_rate": 54.7, - "rank": 28 + "rank": 30 }, { "arena": "agents", "category": "webapps", - "elo": 1129, + "elo": 1136, "win_rate": 51.6, - "rank": 28 + "rank": 32 }, { "arena": "models", "category": "3d", - "elo": 1213, + "elo": 1205, "win_rate": 53.1, - "rank": 41 + "rank": 48 }, { "arena": "models", "category": "asciiart", - "elo": 1174, + "elo": 1166, "win_rate": 46.4, - "rank": 32 + "rank": 33 }, { "arena": "models", "category": "codecategories", - "elo": 1240, + "elo": 1236, "win_rate": 54.1, - "rank": 38 + "rank": 47 }, { "arena": "models", "category": "dataviz", - "elo": 1226, + "elo": 1219, "win_rate": 51.3, - "rank": 46 + "rank": 52 }, { "arena": "models", "category": "gamedev", - "elo": 1217, + "elo": 1207, "win_rate": 53.4, - "rank": 44 + "rank": 54 }, { "arena": "models", "category": "svg", - "elo": 1149, + "elo": 1150, "win_rate": 48.4, - "rank": 43 + "rank": 45 }, { "arena": "models", "category": "uicomponent", - "elo": 1243, + "elo": 1237, "win_rate": 53.6, - "rank": 40 + "rank": 47 }, { "arena": "models", "category": "website", - "elo": 1255, + "elo": 1248, "win_rate": 55.2, - "rank": 36 + "rank": 45 } ], "artificial_analysis": { @@ -18687,9 +19462,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000000465", - "completion": "0.00000245", - "input_cache_read": "0.0000000975" + "prompt": "0.00000065", + "completion": "0.00000341", + "input_cache_read": "0.00000015" }, "top_provider": { "context_length": 262144, @@ -18773,14 +19548,14 @@ { "arena": "agents", "category": "androidnative", - "elo": 1174, - "win_rate": 49.1, - "rank": 21 + "elo": 1161, + "win_rate": 49.2, + "rank": 22 }, { "arena": "agents", "category": "fullstack", - "elo": 1154, + "elo": 1155, "win_rate": 49.4, "rank": 25 }, @@ -18794,16 +19569,16 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1184, + "elo": 1185, "win_rate": 52.3, "rank": 10 }, { "arena": "agents", "category": "mobileapps", - "elo": 1153, - "win_rate": 47.8, - "rank": 26 + "elo": 1156, + "win_rate": 47.6, + "rank": 28 }, { "arena": "agents", @@ -18819,68 +19594,75 @@ "win_rate": 42.1, "rank": 18 }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1276, + "win_rate": 54.8, + "rank": 5 + }, { "arena": "agents", "category": "webapps", "elo": 1268, "win_rate": 59.3, - "rank": 6 + "rank": 9 }, { "arena": "models", "category": "3d", - "elo": 1276, + "elo": 1268, "win_rate": 57.6, - "rank": 19 + "rank": 26 }, { "arena": "models", "category": "asciiart", - "elo": 1173, + "elo": 1165, "win_rate": 47.5, - "rank": 33 + "rank": 35 }, { "arena": "models", "category": "codecategories", - "elo": 1276, + "elo": 1272, "win_rate": 54.8, - "rank": 23 + "rank": 29 }, { "arena": "models", "category": "dataviz", - "elo": 1255, + "elo": 1249, "win_rate": 52, - "rank": 29 + "rank": 35 }, { "arena": "models", "category": "gamedev", - "elo": 1261, + "elo": 1251, "win_rate": 54.9, - "rank": 30 + "rank": 37 }, { "arena": "models", "category": "svg", - "elo": 1181, + "elo": 1182, "win_rate": 51.2, - "rank": 31 + "rank": 32 }, { "arena": "models", "category": "uicomponent", - "elo": 1273, + "elo": 1266, "win_rate": 55.6, - "rank": 28 + "rank": 34 }, { "arena": "models", "category": "website", - "elo": 1274, + "elo": 1269, "win_rate": 54.2, - "rank": 26 + "rank": 30 } ], "artificial_analysis": { @@ -18968,14 +19750,14 @@ { "arena": "agents", "category": "androidnative", - "elo": 1152, + "elo": 1137, "win_rate": 46, - "rank": 25 + "rank": 26 }, { "arena": "agents", "category": "fullstack", - "elo": 1174, + "elo": 1175, "win_rate": 50.9, "rank": 22 }, @@ -18989,86 +19771,86 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1201, + "elo": 1202, "win_rate": 53.6, "rank": 7 }, { "arena": "agents", "category": "mobileapps", - "elo": 1140, - "win_rate": 46.3, - "rank": 29 + "elo": 1143, + "win_rate": 46.2, + "rank": 31 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1154, - "win_rate": 44.7, - "rank": 22 + "elo": 1152, + "win_rate": 44.6, + "rank": 23 }, { "arena": "agents", "category": "webapps", - "elo": 1169, + "elo": 1176, "win_rate": 46.9, - "rank": 24 + "rank": 28 }, { "arena": "models", "category": "3d", - "elo": 1249, - "win_rate": 50.5, - "rank": 30 + "elo": 1241, + "win_rate": 50.3, + "rank": 37 }, { "arena": "models", "category": "asciiart", - "elo": 1206, + "elo": 1196, "win_rate": 48.3, - "rank": 24 + "rank": 27 }, { "arena": "models", "category": "codecategories", - "elo": 1258, - "win_rate": 50.3, - "rank": 32 + "elo": 1253, + "win_rate": 49.9, + "rank": 40 }, { "arena": "models", "category": "dataviz", - "elo": 1231, - "win_rate": 48.8, - "rank": 41 + "elo": 1227, + "win_rate": 48.7, + "rank": 48 }, { "arena": "models", "category": "gamedev", - "elo": 1230, - "win_rate": 47.4, - "rank": 38 + "elo": 1220, + "win_rate": 47, + "rank": 48 }, { "arena": "models", "category": "svg", - "elo": 1176, - "win_rate": 44.5, - "rank": 35 + "elo": 1177, + "win_rate": 44.4, + "rank": 36 }, { "arena": "models", "category": "uicomponent", - "elo": 1268, - "win_rate": 51.3, - "rank": 30 + "elo": 1259, + "win_rate": 50.6, + "rank": 39 }, { "arena": "models", "category": "website", - "elo": 1270, - "win_rate": 51.7, - "rank": 30 + "elo": 1264, + "win_rate": 51.3, + "rank": 35 } ], "artificial_analysis": { @@ -19098,9 +19880,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000062", - "completion": "0.000015", - "input_cache_read": "0.00000043" + "prompt": "0.000000239", + "completion": "0.000011936", + "input_cache_read": "0.00000021" }, "top_provider": { "context_length": 1048576, @@ -19150,20 +19932,208 @@ "arena": "agents", "category": "agenticgamedev", "elo": 1252, - "win_rate": 55, + "win_rate": 54.9, + "rank": 3 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 1251, + "win_rate": 55.9, + "rank": 5 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1315, + "win_rate": 61.8, + "rank": 2 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1223, + "win_rate": 48.2, + "rank": 14 + }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1255, + "win_rate": 59.2, + "rank": 2 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1269, + "win_rate": 57.5, + "rank": 3 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1270, + "win_rate": 58.9, + "rank": 4 + }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1057, + "win_rate": 33.1, + "rank": 13 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1295, + "win_rate": 59.3, + "rank": 7 + }, + { + "arena": "models", + "category": "3d", + "elo": 1388, + "win_rate": 67.2, + "rank": 8 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1360, + "win_rate": 62.3, + "rank": 4 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1351, + "win_rate": 63.3, + "rank": 4 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1359, + "win_rate": 60.4, + "rank": 8 + }, + { + "arena": "models", + "category": "svg", + "elo": 1302, + "win_rate": 59.3, + "rank": 5 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1344, + "win_rate": 60.1, + "rank": 6 + }, + { + "arena": "models", + "category": "website", + "elo": 1335, + "win_rate": 59.2, + "rank": 4 + } + ], + "artificial_analysis": { + "intelligence_index": 43.6, + "coding_index": 76.2, + "agentic_index": 50 + } + }, + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["max", "high", "low", "none"], + "default_effort": "max" + } + }, + { + "id": "moonshotai/kimi-k3:batch", + "canonical_slug": "moonshotai/kimi-k3-20260715", + "hugging_face_id": "moonshotai/Kimi-K3", + "name": "MoonshotAI: Kimi K3 (batch)", + "created": 1784215858, + "description": "Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...", + "context_length": 1048576, + "architecture": { + "modality": "text+image+video->text", + "input_modalities": ["text", "image", "video"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000228", + "completion": "0.0000114", + "input_cache_read": "0.000000228" + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "reasoning_effort", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], + "default_parameters": { + "temperature": null, + "top_p": 0.95, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/moonshotai/kimi-k3-20260715/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "agenticgamedev", + "elo": 1252, + "win_rate": 54.9, "rank": 3 }, { "arena": "agents", "category": "androidnative", - "elo": 1262, - "win_rate": 55.4, + "elo": 1251, + "win_rate": 55.9, "rank": 5 }, { "arena": "agents", "category": "fullstack", - "elo": 1313, + "elo": 1315, "win_rate": 61.8, "rank": 2 }, @@ -19177,260 +20147,86 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1256, - "win_rate": 59.6, - "rank": 2 - }, - { - "arena": "agents", - "category": "mobileapps", - "elo": 1263, - "win_rate": 56.9, - "rank": 4 - }, - { - "arena": "agents", - "category": "python-pptxslides", - "elo": 1273, + "elo": 1255, "win_rate": 59.2, - "rank": 4 - }, - { - "arena": "agents", - "category": "webapps", - "elo": 1285, - "win_rate": 59.1, - "rank": 4 - }, - { - "arena": "models", - "category": "3d", - "elo": 1399, - "win_rate": 67.8, - "rank": 4 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1370, - "win_rate": 63.2, "rank": 2 }, - { - "arena": "models", - "category": "dataviz", - "elo": 1354, - "win_rate": 63, - "rank": 3 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1375, - "win_rate": 61.8, - "rank": 3 - }, - { - "arena": "models", - "category": "svg", - "elo": 1305, - "win_rate": 59.7, - "rank": 4 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1362, - "win_rate": 62.3, - "rank": 3 - }, - { - "arena": "models", - "category": "website", - "elo": 1343, - "win_rate": 59.9, - "rank": 2 - } - ], - "artificial_analysis": { - "intelligence_index": 43.6, - "coding_index": 76.2, - "agentic_index": 50 - } - }, - "reasoning": { - "mandatory": false, - "default_enabled": true, - "supported_efforts": ["max", "high", "low"], - "default_effort": "max" - } - }, - { - "id": "moonshotai/kimi-k3:batch", - "canonical_slug": "moonshotai/kimi-k3-20260715", - "hugging_face_id": "moonshotai/Kimi-K3", - "name": "MoonshotAI: Kimi K3 (batch)", - "created": 1784215858, - "description": "Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...", - "context_length": 1048576, - "architecture": { - "modality": "text+image+video->text", - "input_modalities": ["text", "image", "video"], - "output_modalities": ["text"], - "tokenizer": "Other", - "instruct_type": null - }, - "pricing": { - "prompt": "0.00000228", - "completion": "0.0000114", - "input_cache_read": "0.000000228" - }, - "top_provider": { - "context_length": 1048576, - "max_completion_tokens": 16384, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "include_reasoning", - "logit_bias", - "max_tokens", - "min_p", - "presence_penalty", - "reasoning", - "reasoning_effort", - "repetition_penalty", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_k", - "top_p" - ], - "default_parameters": { - "temperature": null, - "top_p": 0.95, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": null, - "links": { - "details": "/api/v1/models/moonshotai/kimi-k3-20260715/endpoints" - }, - "benchmarks": { - "design_arena": [ { "arena": "agents", - "category": "agenticgamedev", - "elo": 1252, - "win_rate": 55, + "category": "mobileapps", + "elo": 1269, + "win_rate": 57.5, "rank": 3 }, { "arena": "agents", - "category": "androidnative", - "elo": 1262, - "win_rate": 55.4, - "rank": 5 - }, - { - "arena": "agents", - "category": "fullstack", - "elo": 1313, - "win_rate": 61.8, - "rank": 2 - }, - { - "arena": "agents", - "category": "godotgamedev", - "elo": 1223, - "win_rate": 48.2, - "rank": 14 - }, - { - "arena": "agents", - "category": "htmlslides", - "elo": 1256, - "win_rate": 59.6, - "rank": 2 - }, - { - "arena": "agents", - "category": "mobileapps", - "elo": 1263, - "win_rate": 56.9, + "category": "python-pptxslides", + "elo": 1270, + "win_rate": 58.9, "rank": 4 }, { "arena": "agents", - "category": "python-pptxslides", - "elo": 1273, - "win_rate": 59.2, - "rank": 4 + "category": "spreadsheet", + "elo": 1057, + "win_rate": 33.1, + "rank": 13 }, { "arena": "agents", "category": "webapps", - "elo": 1285, - "win_rate": 59.1, - "rank": 4 + "elo": 1295, + "win_rate": 59.3, + "rank": 7 }, { "arena": "models", "category": "3d", - "elo": 1399, - "win_rate": 67.8, - "rank": 4 + "elo": 1388, + "win_rate": 67.2, + "rank": 8 }, { "arena": "models", "category": "codecategories", - "elo": 1370, - "win_rate": 63.2, - "rank": 2 + "elo": 1360, + "win_rate": 62.3, + "rank": 4 }, { "arena": "models", "category": "dataviz", - "elo": 1354, - "win_rate": 63, - "rank": 3 + "elo": 1351, + "win_rate": 63.3, + "rank": 4 }, { "arena": "models", "category": "gamedev", - "elo": 1375, - "win_rate": 61.8, - "rank": 3 + "elo": 1359, + "win_rate": 60.4, + "rank": 8 }, { "arena": "models", "category": "svg", - "elo": 1305, - "win_rate": 59.7, - "rank": 4 + "elo": 1302, + "win_rate": 59.3, + "rank": 5 }, { "arena": "models", "category": "uicomponent", - "elo": 1362, - "win_rate": 62.3, - "rank": 3 + "elo": 1344, + "win_rate": 60.1, + "rank": 6 }, { "arena": "models", "category": "website", - "elo": 1343, - "win_rate": 59.9, - "rank": 2 + "elo": 1335, + "win_rate": 59.2, + "rank": 4 } ], "artificial_analysis": { @@ -19442,7 +20238,7 @@ "reasoning": { "mandatory": false, "default_enabled": true, - "supported_efforts": ["max", "high", "low"], + "supported_efforts": ["max", "high", "low", "none"], "default_effort": "max" } }, @@ -19453,7 +20249,7 @@ "name": "Morph: Morph V3 Fast", "created": 1751910002, "description": "Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: {instruction} {initial_code} {edit_snippet}...", - "context_length": 81920, + "context_length": 262144, "architecture": { "modality": "text->text", "input_modalities": ["text"], @@ -19466,12 +20262,20 @@ "completion": "0.0000012" }, "top_provider": { - "context_length": 81920, - "max_completion_tokens": 38000, + "context_length": 262144, + "max_completion_tokens": 131072, "is_moderated": false }, "per_request_limits": null, - "supported_parameters": ["max_tokens", "stop", "temperature"], + "supported_parameters": [ + "logprobs", + "max_tokens", + "response_format", + "stop", + "structured_outputs", + "temperature", + "top_logprobs" + ], "default_parameters": { "temperature": null, "top_p": null, @@ -19685,17 +20489,9 @@ "default_parameters": {}, "supported_voices": null, "knowledge_cutoff": "2023-12-31", - "expiration_date": null, + "expiration_date": "2026-11-02", "links": { "details": "/api/v1/models/nousresearch/hermes-3-llama-3.1-405b/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 7.4, - "coding_index": null, - "agentic_index": null - } } }, { @@ -19740,7 +20536,7 @@ "default_parameters": {}, "supported_voices": null, "knowledge_cutoff": "2023-12-31", - "expiration_date": null, + "expiration_date": "2026-11-02", "links": { "details": "/api/v1/models/nousresearch/hermes-3-llama-3.1-70b/endpoints" }, @@ -19781,13 +20577,16 @@ "supported_parameters": [ "frequency_penalty", "include_reasoning", + "logprobs", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", + "structured_outputs", "temperature", "top_k", + "top_logprobs", "top_p" ], "default_parameters": {}, @@ -19825,9 +20624,8 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000005", - "completion": "0.0000002", - "input_cache_read": "0.00000003" + "prompt": "0.00000006", + "completion": "0.00000024" }, "top_provider": { "context_length": 262144, @@ -19841,7 +20639,6 @@ "logit_bias", "logprobs", "max_tokens", - "min_p", "presence_penalty", "reasoning", "repetition_penalty", @@ -19958,8 +20755,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000008", - "completion": "0.00000045" + "prompt": "0.0000003", + "completion": "0.0000024", + "input_cache_read": "0.00000015" }, "top_provider": { "context_length": 262144, @@ -20015,7 +20813,7 @@ "mandatory": false, "default_enabled": true, "supports_max_tokens": true, - "supported_efforts": ["medium", "low"], + "supported_efforts": ["medium", "low", "none"], "default_effort": "medium" } }, @@ -20083,7 +20881,7 @@ "mandatory": false, "default_enabled": true, "supports_max_tokens": true, - "supported_efforts": ["medium", "low"], + "supported_efforts": ["medium", "low", "none"], "default_effort": "medium" } }, @@ -20103,13 +20901,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000005", - "completion": "0.0000022", - "input_cache_read": "0.0000001" + "prompt": "0.0000006", + "completion": "0.0000024", + "input_cache_read": "0.00000012" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 16384, + "context_length": 202800, + "max_completion_tokens": 182520, "is_moderated": false }, "per_request_limits": null, @@ -20152,58 +20950,58 @@ { "arena": "models", "category": "3d", - "elo": 1139, - "win_rate": 39.2, - "rank": 68 + "elo": 1132, + "win_rate": 38.9, + "rank": 76 }, { "arena": "models", "category": "asciiart", - "elo": 1104, - "win_rate": 37.8, - "rank": 59 + "elo": 1100, + "win_rate": 37.6, + "rank": 60 }, { "arena": "models", "category": "codecategories", - "elo": 1149, + "elo": 1147, "win_rate": 36.1, - "rank": 77 + "rank": 87 }, { "arena": "models", "category": "dataviz", - "elo": 1145, - "win_rate": 37.3, - "rank": 78 + "elo": 1141, + "win_rate": 37.5, + "rank": 85 }, { "arena": "models", "category": "gamedev", - "elo": 1149, - "win_rate": 36.8, - "rank": 69 + "elo": 1138, + "win_rate": 36.2, + "rank": 82 }, { "arena": "models", "category": "svg", - "elo": 1069, - "win_rate": 32.5, - "rank": 68 + "elo": 1070, + "win_rate": 32.4, + "rank": 69 }, { "arena": "models", "category": "uicomponent", - "elo": 1146, - "win_rate": 36.3, - "rank": 75 + "elo": 1139, + "win_rate": 35.8, + "rank": 83 }, { "arena": "models", "category": "website", "elo": 1145, - "win_rate": 34.9, - "rank": 86 + "win_rate": 35.2, + "rank": 96 } ], "artificial_analysis": { @@ -20216,7 +21014,7 @@ "mandatory": false, "default_enabled": true, "supports_max_tokens": true, - "supported_efforts": ["high", "medium"], + "supported_efforts": ["high", "medium", "none"], "default_effort": "high" } }, @@ -20275,58 +21073,58 @@ { "arena": "models", "category": "3d", - "elo": 1139, - "win_rate": 39.2, - "rank": 68 + "elo": 1132, + "win_rate": 38.9, + "rank": 76 }, { "arena": "models", "category": "asciiart", - "elo": 1104, - "win_rate": 37.8, - "rank": 59 + "elo": 1100, + "win_rate": 37.6, + "rank": 60 }, { "arena": "models", "category": "codecategories", - "elo": 1149, + "elo": 1147, "win_rate": 36.1, - "rank": 77 + "rank": 87 }, { "arena": "models", "category": "dataviz", - "elo": 1145, - "win_rate": 37.3, - "rank": 78 + "elo": 1141, + "win_rate": 37.5, + "rank": 85 }, { "arena": "models", "category": "gamedev", - "elo": 1149, - "win_rate": 36.8, - "rank": 69 + "elo": 1138, + "win_rate": 36.2, + "rank": 82 }, { "arena": "models", "category": "svg", - "elo": 1069, - "win_rate": 32.5, - "rank": 68 + "elo": 1070, + "win_rate": 32.4, + "rank": 69 }, { "arena": "models", "category": "uicomponent", - "elo": 1146, - "win_rate": 36.3, - "rank": 75 + "elo": 1139, + "win_rate": 35.8, + "rank": 83 }, { "arena": "models", "category": "website", "elo": 1145, - "win_rate": 34.9, - "rank": 86 + "win_rate": 35.2, + "rank": 96 } ], "artificial_analysis": { @@ -20339,7 +21137,7 @@ "mandatory": false, "default_enabled": true, "supports_max_tokens": true, - "supported_efforts": ["high", "medium"], + "supported_efforts": ["high", "medium", "none"], "default_effort": "high" } }, @@ -20470,13 +21268,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000006", - "completion": "0.00000016", - "input_cache_read": "0.00000003" + "prompt": "0.00000007", + "completion": "0.0000002", + "input_cache_read": "0.00000004" }, "top_provider": { "context_length": 262144, - "max_completion_tokens": 32768, + "max_completion_tokens": 235929, "is_moderated": false }, "per_request_limits": null, @@ -20574,6 +21372,200 @@ "mandatory": false } }, + { + "id": "nvidia/nemotron-3.5-super-vl", + "canonical_slug": "nvidia/nemotron-3.5-super-vl-20261015", + "hugging_face_id": "nvidia/NVIDIA-Nemotron-3.5-Super-VL", + "name": "NVIDIA: Nemotron 3.5 Super VL", + "created": 1792076662, + "description": "NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...", + "context_length": 1048576, + "architecture": { + "modality": "text+image+video->text", + "input_modalities": ["text", "image", "video"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000015", + "completion": "0.0000005", + "input_cache_read": "0.00000002" + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 235929, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/nvidia/nemotron-3.5-super-vl-20261015/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1129, + "win_rate": 28.5, + "rank": 78 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1156, + "win_rate": 32.8, + "rank": 82 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1111, + "win_rate": 29.2, + "rank": 93 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1143, + "win_rate": 32, + "rank": 81 + }, + { + "arena": "models", + "category": "website", + "elo": 1173, + "win_rate": 34.9, + "rank": 81 + } + ], + "artificial_analysis": { + "intelligence_index": 26.5, + "coding_index": null, + "agentic_index": null + } + }, + "reasoning": { + "mandatory": false + } + }, + { + "id": "nvidia/nemotron-3.5-super-vl:free", + "canonical_slug": "nvidia/nemotron-3.5-super-vl-20261015", + "hugging_face_id": "nvidia/NVIDIA-Nemotron-3.5-Super-VL", + "name": "NVIDIA: Nemotron 3.5 Super VL (free)", + "created": 1792076662, + "description": "NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...", + "context_length": 1000000, + "architecture": { + "modality": "text+image+video->text", + "input_modalities": ["text", "image", "video"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0", + "completion": "0" + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 131072, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/nvidia/nemotron-3.5-super-vl-20261015/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1129, + "win_rate": 28.5, + "rank": 78 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1156, + "win_rate": 32.8, + "rank": 82 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1111, + "win_rate": 29.2, + "rank": 93 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1143, + "win_rate": 32, + "rank": 81 + }, + { + "arena": "models", + "category": "website", + "elo": 1173, + "win_rate": 34.9, + "rank": 81 + } + ], + "artificial_analysis": { + "intelligence_index": 26.5, + "coding_index": null, + "agentic_index": null + } + }, + "reasoning": { + "mandatory": false + } + }, { "id": "openai/gpt-3.5-turbo", "canonical_slug": "openai/gpt-3.5-turbo", @@ -20702,7 +21694,7 @@ "top_provider": { "context_length": 16385, "max_completion_tokens": 4096, - "is_moderated": true + "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ @@ -21058,44 +22050,44 @@ { "arena": "models", "category": "3d", - "elo": 858, + "elo": 850, "win_rate": 30.9, - "rank": 117 + "rank": 125 }, { "arena": "models", "category": "codecategories", - "elo": 1031, + "elo": 1026, "win_rate": 50.9, - "rank": 108 + "rank": 119 }, { "arena": "models", "category": "dataviz", - "elo": 1109, + "elo": 1104, "win_rate": 59.5, - "rank": 90 + "rank": 97 }, { "arena": "models", "category": "gamedev", - "elo": 1090, + "elo": 1080, "win_rate": 59.1, - "rank": 91 + "rank": 104 }, { "arena": "models", "category": "uicomponent", - "elo": 1007, + "elo": 1000, "win_rate": 49.7, - "rank": 107 + "rank": 115 }, { "arena": "models", "category": "website", - "elo": 1045, + "elo": 1039, "win_rate": 52.3, - "rank": 111 + "rank": 122 } ], "artificial_analysis": { @@ -21155,44 +22147,44 @@ { "arena": "models", "category": "3d", - "elo": 844, + "elo": 837, "win_rate": 30.5, - "rank": 118 + "rank": 126 }, { "arena": "models", "category": "codecategories", - "elo": 999, + "elo": 994, "win_rate": 47.5, - "rank": 115 + "rank": 126 }, { "arena": "models", "category": "dataviz", - "elo": 1039, + "elo": 1034, "win_rate": 49.2, - "rank": 105 + "rank": 111 }, { "arena": "models", "category": "gamedev", - "elo": 1081, + "elo": 1071, "win_rate": 58.5, - "rank": 95 + "rank": 108 }, { "arena": "models", "category": "uicomponent", - "elo": 968, + "elo": 961, "win_rate": 45.4, - "rank": 111 + "rank": 119 }, { "arena": "models", "category": "website", - "elo": 1002, + "elo": 997, "win_rate": 47.8, - "rank": 119 + "rank": 130 } ], "artificial_analysis": { @@ -21251,44 +22243,44 @@ { "arena": "models", "category": "3d", - "elo": 844, + "elo": 837, "win_rate": 30.5, - "rank": 118 + "rank": 126 }, { "arena": "models", "category": "codecategories", - "elo": 999, + "elo": 994, "win_rate": 47.5, - "rank": 115 + "rank": 126 }, { "arena": "models", "category": "dataviz", - "elo": 1039, + "elo": 1034, "win_rate": 49.2, - "rank": 105 + "rank": 111 }, { "arena": "models", "category": "gamedev", - "elo": 1081, + "elo": 1071, "win_rate": 58.5, - "rank": 95 + "rank": 108 }, { "arena": "models", "category": "uicomponent", - "elo": 968, + "elo": 961, "win_rate": 45.4, - "rank": 111 + "rank": 119 }, { "arena": "models", "category": "website", - "elo": 1002, + "elo": 997, "win_rate": 47.8, - "rank": 119 + "rank": 130 } ], "artificial_analysis": { @@ -21348,44 +22340,44 @@ { "arena": "models", "category": "3d", - "elo": 933, + "elo": 925, "win_rate": 46, - "rank": 111 + "rank": 119 }, { "arena": "models", "category": "codecategories", - "elo": 967, + "elo": 963, "win_rate": 47.3, - "rank": 119 + "rank": 130 }, { "arena": "models", "category": "dataviz", - "elo": 897, + "elo": 891, "win_rate": 41.1, - "rank": 122 + "rank": 129 }, { "arena": "models", "category": "gamedev", - "elo": 981, + "elo": 971, "win_rate": 49.6, - "rank": 114 + "rank": 127 }, { "arena": "models", "category": "uicomponent", - "elo": 921, + "elo": 916, "win_rate": 43.9, - "rank": 117 + "rank": 125 }, { "arena": "models", "category": "website", - "elo": 979, + "elo": 973, "win_rate": 48.1, - "rank": 121 + "rank": 133 } ], "artificial_analysis": { @@ -21444,44 +22436,44 @@ { "arena": "models", "category": "3d", - "elo": 933, + "elo": 925, "win_rate": 46, - "rank": 111 + "rank": 119 }, { "arena": "models", "category": "codecategories", - "elo": 967, + "elo": 963, "win_rate": 47.3, - "rank": 119 + "rank": 130 }, { "arena": "models", "category": "dataviz", - "elo": 897, + "elo": 891, "win_rate": 41.1, - "rank": 122 + "rank": 129 }, { "arena": "models", "category": "gamedev", - "elo": 981, + "elo": 971, "win_rate": 49.6, - "rank": 114 + "rank": 127 }, { "arena": "models", "category": "uicomponent", - "elo": 921, + "elo": 916, "win_rate": 43.9, - "rank": 117 + "rank": 125 }, { "arena": "models", "category": "website", - "elo": 979, + "elo": 973, "win_rate": 48.1, - "rank": 121 + "rank": 133 } ], "artificial_analysis": { @@ -21540,44 +22532,44 @@ { "arena": "models", "category": "3d", - "elo": 858, + "elo": 850, "win_rate": 30.9, - "rank": 117 + "rank": 125 }, { "arena": "models", "category": "codecategories", - "elo": 1031, + "elo": 1026, "win_rate": 50.9, - "rank": 108 + "rank": 119 }, { "arena": "models", "category": "dataviz", - "elo": 1109, + "elo": 1104, "win_rate": 59.5, - "rank": 90 + "rank": 97 }, { "arena": "models", "category": "gamedev", - "elo": 1090, + "elo": 1080, "win_rate": 59.1, - "rank": 91 + "rank": 104 }, { "arena": "models", "category": "uicomponent", - "elo": 1007, + "elo": 1000, "win_rate": 49.7, - "rank": 107 + "rank": 115 }, { "arena": "models", "category": "website", - "elo": 1045, + "elo": 1039, "win_rate": 52.3, - "rank": 111 + "rank": 122 } ], "artificial_analysis": { @@ -21644,44 +22636,44 @@ { "arena": "models", "category": "3d", - "elo": 877, + "elo": 869, "win_rate": 39.2, - "rank": 114 + "rank": 122 }, { "arena": "models", "category": "codecategories", - "elo": 866, + "elo": 861, "win_rate": 34.8, - "rank": 125 + "rank": 136 }, { "arena": "models", "category": "dataviz", - "elo": 862, + "elo": 858, "win_rate": 36, - "rank": 124 + "rank": 131 }, { "arena": "models", "category": "gamedev", - "elo": 917, + "elo": 906, "win_rate": 42.3, - "rank": 122 + "rank": 135 }, { "arena": "models", "category": "uicomponent", - "elo": 892, + "elo": 885, "win_rate": 38.1, - "rank": 122 + "rank": 130 }, { "arena": "models", "category": "website", - "elo": 836, + "elo": 831, "win_rate": 31.5, - "rank": 133 + "rank": 144 } ] } @@ -22098,44 +23090,44 @@ { "arena": "models", "category": "3d", - "elo": 877, + "elo": 869, "win_rate": 39.2, - "rank": 114 + "rank": 122 }, { "arena": "models", "category": "codecategories", - "elo": 866, + "elo": 861, "win_rate": 34.8, - "rank": 125 + "rank": 136 }, { "arena": "models", "category": "dataviz", - "elo": 862, + "elo": 858, "win_rate": 36, - "rank": 124 + "rank": 131 }, { "arena": "models", "category": "gamedev", - "elo": 917, + "elo": 906, "win_rate": 42.3, - "rank": 122 + "rank": 135 }, { "arena": "models", "category": "uicomponent", - "elo": 892, + "elo": 885, "win_rate": 38.1, - "rank": 122 + "rank": 130 }, { "arena": "models", "category": "website", - "elo": 836, + "elo": 831, "win_rate": 31.5, - "rank": 133 + "rank": 144 } ] } @@ -22199,58 +23191,58 @@ { "arena": "models", "category": "3d", - "elo": 1063, + "elo": 1056, "win_rate": 41.3, - "rank": 95 + "rank": 104 }, { "arena": "models", "category": "asciiart", - "elo": 1149, + "elo": 1141, "win_rate": 49, - "rank": 46 + "rank": 48 }, { "arena": "models", "category": "codecategories", - "elo": 1172, + "elo": 1168, "win_rate": 54.5, - "rank": 66 + "rank": 75 }, { "arena": "models", "category": "dataviz", - "elo": 1228, + "elo": 1221, "win_rate": 60.5, - "rank": 44 + "rank": 51 }, { "arena": "models", "category": "gamedev", - "elo": 1195, + "elo": 1185, "win_rate": 59.3, - "rank": 52 + "rank": 62 }, { "arena": "models", "category": "svg", - "elo": 1188, + "elo": 1189, "win_rate": 64.1, - "rank": 29 + "rank": 30 }, { "arena": "models", "category": "uicomponent", - "elo": 1186, + "elo": 1180, "win_rate": 57.4, - "rank": 58 + "rank": 65 }, { "arena": "models", "category": "website", - "elo": 1191, + "elo": 1184, "win_rate": 53.7, - "rank": 65 + "rank": 74 } ], "artificial_analysis": { @@ -22322,21 +23314,21 @@ { "arena": "models", "category": "graphicdesign", - "elo": 1171, + "elo": 1172, "win_rate": 48.9, "rank": 9 }, { "arena": "models", "category": "image", - "elo": 1192, + "elo": 1191, "win_rate": 53.9, "rank": 9 }, { "arena": "models", "category": "logo", - "elo": 1204, + "elo": 1202, "win_rate": 52.7, "rank": 9 } @@ -22403,7 +23395,7 @@ { "arena": "models", "category": "graphicdesign", - "elo": 1164, + "elo": 1165, "win_rate": 47.7, "rank": 11 }, @@ -22417,9 +23409,9 @@ { "arena": "models", "category": "logo", - "elo": 1210, + "elo": 1209, "win_rate": 51.4, - "rank": 7 + "rank": 8 } ] }, @@ -22486,58 +23478,58 @@ { "arena": "models", "category": "3d", - "elo": 1045, + "elo": 1037, "win_rate": 36.9, - "rank": 98 + "rank": 106 }, { "arena": "models", "category": "asciiart", - "elo": 1132, - "win_rate": 44.7, - "rank": 52 + "elo": 1125, + "win_rate": 44.8, + "rank": 53 }, { "arena": "models", "category": "codecategories", - "elo": 1119, + "elo": 1115, "win_rate": 43.5, - "rank": 88 + "rank": 99 }, { "arena": "models", "category": "dataviz", - "elo": 1137, + "elo": 1131, "win_rate": 43.7, - "rank": 83 + "rank": 90 }, { "arena": "models", "category": "gamedev", - "elo": 1140, + "elo": 1130, "win_rate": 46.5, - "rank": 77 + "rank": 90 }, { "arena": "models", "category": "svg", - "elo": 1090, + "elo": 1091, "win_rate": 45.8, - "rank": 61 + "rank": 62 }, { "arena": "models", "category": "uicomponent", - "elo": 1113, + "elo": 1106, "win_rate": 41.9, - "rank": 83 + "rank": 92 }, { "arena": "models", "category": "website", - "elo": 1131, + "elo": 1125, "win_rate": 44.3, - "rank": 89 + "rank": 100 } ], "artificial_analysis": { @@ -22610,58 +23602,58 @@ { "arena": "models", "category": "3d", - "elo": 1045, + "elo": 1037, "win_rate": 36.9, - "rank": 98 + "rank": 106 }, { "arena": "models", "category": "asciiart", - "elo": 1132, - "win_rate": 44.7, - "rank": 52 + "elo": 1125, + "win_rate": 44.8, + "rank": 53 }, { "arena": "models", "category": "codecategories", - "elo": 1119, + "elo": 1115, "win_rate": 43.5, - "rank": 88 + "rank": 99 }, { "arena": "models", "category": "dataviz", - "elo": 1137, + "elo": 1131, "win_rate": 43.7, - "rank": 83 + "rank": 90 }, { "arena": "models", "category": "gamedev", - "elo": 1140, + "elo": 1130, "win_rate": 46.5, - "rank": 77 + "rank": 90 }, { "arena": "models", "category": "svg", - "elo": 1090, + "elo": 1091, "win_rate": 45.8, - "rank": 61 + "rank": 62 }, { "arena": "models", "category": "uicomponent", - "elo": 1113, + "elo": 1106, "win_rate": 41.9, - "rank": 83 + "rank": 92 }, { "arena": "models", "category": "website", - "elo": 1131, + "elo": 1125, "win_rate": 44.3, - "rank": 89 + "rank": 100 } ], "artificial_analysis": { @@ -22735,44 +23727,44 @@ { "arena": "models", "category": "3d", - "elo": 973, + "elo": 966, "win_rate": 36.3, - "rank": 109 + "rank": 117 }, { "arena": "models", "category": "codecategories", - "elo": 1088, + "elo": 1084, "win_rate": 48, - "rank": 96 + "rank": 107 }, { "arena": "models", "category": "dataviz", - "elo": 1062, + "elo": 1056, "win_rate": 46.2, - "rank": 102 + "rank": 109 }, { "arena": "models", "category": "gamedev", - "elo": 1055, + "elo": 1045, "win_rate": 46.5, - "rank": 100 + "rank": 115 }, { "arena": "models", "category": "uicomponent", - "elo": 1073, + "elo": 1067, "win_rate": 51.9, - "rank": 96 + "rank": 104 }, { "arena": "models", "category": "website", - "elo": 1106, + "elo": 1101, "win_rate": 48.9, - "rank": 98 + "rank": 109 } ], "artificial_analysis": { @@ -22845,44 +23837,44 @@ { "arena": "models", "category": "3d", - "elo": 973, + "elo": 966, "win_rate": 36.3, - "rank": 109 + "rank": 117 }, { "arena": "models", "category": "codecategories", - "elo": 1088, + "elo": 1084, "win_rate": 48, - "rank": 96 + "rank": 107 }, { "arena": "models", "category": "dataviz", - "elo": 1062, + "elo": 1056, "win_rate": 46.2, - "rank": 102 + "rank": 109 }, { "arena": "models", "category": "gamedev", - "elo": 1055, + "elo": 1045, "win_rate": 46.5, - "rank": 100 + "rank": 115 }, { "arena": "models", "category": "uicomponent", - "elo": 1073, + "elo": 1067, "win_rate": 51.9, - "rank": 96 + "rank": 104 }, { "arena": "models", "category": "website", - "elo": 1106, + "elo": 1101, "win_rate": 48.9, - "rank": 98 + "rank": 109 } ], "artificial_analysis": { @@ -23065,58 +24057,58 @@ { "arena": "models", "category": "3d", - "elo": 1063, + "elo": 1056, "win_rate": 41.3, - "rank": 95 + "rank": 104 }, { "arena": "models", "category": "asciiart", - "elo": 1149, + "elo": 1141, "win_rate": 49, - "rank": 46 + "rank": 48 }, { "arena": "models", "category": "codecategories", - "elo": 1172, + "elo": 1168, "win_rate": 54.5, - "rank": 66 + "rank": 75 }, { "arena": "models", "category": "dataviz", - "elo": 1228, + "elo": 1221, "win_rate": 60.5, - "rank": 44 + "rank": 51 }, { "arena": "models", "category": "gamedev", - "elo": 1195, + "elo": 1185, "win_rate": 59.3, - "rank": 52 + "rank": 62 }, { "arena": "models", "category": "svg", - "elo": 1188, + "elo": 1189, "win_rate": 64.1, - "rank": 29 + "rank": 30 }, { "arena": "models", "category": "uicomponent", - "elo": 1186, + "elo": 1180, "win_rate": 57.4, - "rank": 58 + "rank": 65 }, { "arena": "models", "category": "website", - "elo": 1191, + "elo": 1184, "win_rate": 53.7, - "rank": 65 + "rank": 74 } ], "artificial_analysis": { @@ -23190,58 +24182,58 @@ { "arena": "models", "category": "3d", - "elo": 1069, + "elo": 1061, "win_rate": 43.7, - "rank": 94 + "rank": 102 }, { "arena": "models", "category": "asciiart", - "elo": 1127, + "elo": 1119, "win_rate": 48.6, - "rank": 54 + "rank": 55 }, { "arena": "models", "category": "codecategories", - "elo": 1175, + "elo": 1171, "win_rate": 53, - "rank": 64 + "rank": 73 }, { "arena": "models", "category": "dataviz", - "elo": 1210, + "elo": 1204, "win_rate": 58, - "rank": 51 + "rank": 57 }, { "arena": "models", "category": "gamedev", - "elo": 1189, + "elo": 1179, "win_rate": 55.9, - "rank": 53 + "rank": 63 }, { "arena": "models", "category": "svg", - "elo": 1148, + "elo": 1149, "win_rate": 57.4, - "rank": 45 + "rank": 46 }, { "arena": "models", "category": "uicomponent", - "elo": 1173, + "elo": 1166, "win_rate": 52.9, - "rank": 64 + "rank": 71 }, { "arena": "models", "category": "website", - "elo": 1193, + "elo": 1187, "win_rate": 54, - "rank": 64 + "rank": 72 } ], "artificial_analysis": { @@ -23252,9 +24244,9 @@ }, "reasoning": { "mandatory": false, - "default_enabled": true, + "default_enabled": false, "supported_efforts": ["high", "medium", "low", "none"], - "default_effort": "none" + "default_effort": "medium" } }, { @@ -23324,49 +24316,49 @@ "category": "mobileapps", "elo": 1191, "win_rate": 53.4, - "rank": 18 + "rank": 20 }, { "arena": "agents", "category": "webapps", - "elo": 1011, + "elo": 1018, "win_rate": 44, - "rank": 40 + "rank": 44 }, { "arena": "models", "category": "codecategories", - "elo": 1158, + "elo": 1153, "win_rate": 54.6, - "rank": 72 + "rank": 83 }, { "arena": "models", "category": "dataviz", - "elo": 1220, + "elo": 1213, "win_rate": 55.9, - "rank": 48 + "rank": 54 }, { "arena": "models", "category": "gamedev", - "elo": 1148, + "elo": 1138, "win_rate": 50.5, - "rank": 70 + "rank": 81 }, { "arena": "models", "category": "uicomponent", - "elo": 1244, + "elo": 1237, "win_rate": 60, - "rank": 39 + "rank": 46 }, { "arena": "models", "category": "website", - "elo": 1168, + "elo": 1162, "win_rate": 56.1, - "rank": 76 + "rank": 86 } ], "artificial_analysis": { @@ -23498,58 +24490,58 @@ { "arena": "models", "category": "3d", - "elo": 996, + "elo": 988, "win_rate": 32.8, - "rank": 106 + "rank": 114 }, { "arena": "models", "category": "asciiart", - "elo": 1113, + "elo": 1105, "win_rate": 43, - "rank": 57 + "rank": 59 }, { "arena": "models", "category": "codecategories", - "elo": 1099, + "elo": 1094, "win_rate": 41.5, - "rank": 95 + "rank": 106 }, { "arena": "models", "category": "dataviz", - "elo": 1103, + "elo": 1097, "win_rate": 40.6, - "rank": 94 + "rank": 101 }, { "arena": "models", "category": "gamedev", - "elo": 1103, + "elo": 1092, "win_rate": 43.4, - "rank": 88 + "rank": 101 }, { "arena": "models", "category": "svg", - "elo": 977, + "elo": 978, "win_rate": 35.3, - "rank": 86 + "rank": 87 }, { "arena": "models", "category": "uicomponent", - "elo": 1088, + "elo": 1081, "win_rate": 41, - "rank": 93 + "rank": 101 }, { "arena": "models", "category": "website", - "elo": 1117, - "win_rate": 42.8, - "rank": 96 + "elo": 1111, + "win_rate": 42.9, + "rank": 107 } ], "artificial_analysis": { @@ -23559,7 +24551,7 @@ } }, "reasoning": { - "mandatory": false, + "mandatory": true, "supported_efforts": ["high", "medium", "low"], "default_effort": "medium" } @@ -23622,58 +24614,58 @@ { "arena": "models", "category": "3d", - "elo": 1069, + "elo": 1061, "win_rate": 43.7, - "rank": 94 + "rank": 102 }, { "arena": "models", "category": "asciiart", - "elo": 1127, + "elo": 1119, "win_rate": 48.6, - "rank": 54 + "rank": 55 }, { "arena": "models", "category": "codecategories", - "elo": 1175, + "elo": 1171, "win_rate": 53, - "rank": 64 + "rank": 73 }, { "arena": "models", "category": "dataviz", - "elo": 1210, + "elo": 1204, "win_rate": 58, - "rank": 51 + "rank": 57 }, { "arena": "models", "category": "gamedev", - "elo": 1189, + "elo": 1179, "win_rate": 55.9, - "rank": 53 + "rank": 63 }, { "arena": "models", "category": "svg", - "elo": 1148, + "elo": 1149, "win_rate": 57.4, - "rank": 45 + "rank": 46 }, { "arena": "models", "category": "uicomponent", - "elo": 1173, + "elo": 1166, "win_rate": 52.9, - "rank": 64 + "rank": 71 }, { "arena": "models", "category": "website", - "elo": 1193, + "elo": 1187, "win_rate": 54, - "rank": 64 + "rank": 72 } ], "artificial_analysis": { @@ -23684,9 +24676,9 @@ }, "reasoning": { "mandatory": false, - "default_enabled": true, + "default_enabled": false, "supported_efforts": ["high", "medium", "low", "none"], - "default_effort": "none" + "default_effort": "medium" } }, { @@ -23748,21 +24740,21 @@ { "arena": "models", "category": "website", - "elo": 1201, + "elo": 1195, "win_rate": 54.4, - "rank": 55 + "rank": 67 }, { "arena": "agents", "category": "androidnative", - "elo": 1074, + "elo": 1058, "win_rate": 49.1, - "rank": 32 + "rank": 33 }, { "arena": "agents", "category": "fullstack", - "elo": 1041, + "elo": 1043, "win_rate": 44.3, "rank": 37 }, @@ -23776,65 +24768,65 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1091, + "elo": 1093, "win_rate": 46.8, - "rank": 37 + "rank": 40 }, { "arena": "agents", "category": "webapps", - "elo": 1079, + "elo": 1086, "win_rate": 45.5, - "rank": 35 + "rank": 39 }, { "arena": "models", "category": "3d", - "elo": 1087, + "elo": 1079, "win_rate": 41.5, - "rank": 88 + "rank": 96 }, { "arena": "models", "category": "codecategories", - "elo": 1175, + "elo": 1170, "win_rate": 49.6, - "rank": 65 + "rank": 74 }, { "arena": "models", "category": "dataviz", - "elo": 1207, + "elo": 1202, "win_rate": 56.1, - "rank": 52 + "rank": 60 }, { "arena": "models", "category": "gamedev", - "elo": 1205, + "elo": 1195, "win_rate": 56, - "rank": 47 + "rank": 59 }, { "arena": "models", "category": "uicomponent", - "elo": 1197, + "elo": 1190, "win_rate": 51.3, - "rank": 55 + "rank": 63 }, { "arena": "models", "category": "asciiart", - "elo": 1161, + "elo": 1152, "win_rate": 50.7, - "rank": 36 + "rank": 43 }, { "arena": "models", "category": "svg", - "elo": 1138, + "elo": 1139, "win_rate": 53.7, - "rank": 50 + "rank": 51 } ], "artificial_analysis": { @@ -23954,12 +24946,12 @@ "category": "androidnative", "elo": 1176, "win_rate": 47.5, - "rank": 20 + "rank": 19 }, { "arena": "agents", "category": "fullstack", - "elo": 991, + "elo": 993, "win_rate": 37.2, "rank": 41 }, @@ -23973,16 +24965,16 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1087, + "elo": 1090, "win_rate": 46.6, - "rank": 40 + "rank": 42 }, { "arena": "agents", "category": "webapps", - "elo": 1043, + "elo": 1051, "win_rate": 39.6, - "rank": 38 + "rank": 42 } ], "artificial_analysis": { @@ -24165,21 +25157,21 @@ { "arena": "models", "category": "website", - "elo": 1201, + "elo": 1195, "win_rate": 54.4, - "rank": 55 + "rank": 67 }, { "arena": "agents", "category": "androidnative", - "elo": 1074, + "elo": 1058, "win_rate": 49.1, - "rank": 32 + "rank": 33 }, { "arena": "agents", "category": "fullstack", - "elo": 1041, + "elo": 1043, "win_rate": 44.3, "rank": 37 }, @@ -24193,65 +25185,65 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1091, + "elo": 1093, "win_rate": 46.8, - "rank": 37 + "rank": 40 }, { "arena": "agents", "category": "webapps", - "elo": 1079, + "elo": 1086, "win_rate": 45.5, - "rank": 35 + "rank": 39 }, { "arena": "models", "category": "3d", - "elo": 1087, + "elo": 1079, "win_rate": 41.5, - "rank": 88 + "rank": 96 }, { "arena": "models", "category": "codecategories", - "elo": 1175, + "elo": 1170, "win_rate": 49.6, - "rank": 65 + "rank": 74 }, { "arena": "models", "category": "dataviz", - "elo": 1207, + "elo": 1202, "win_rate": 56.1, - "rank": 52 + "rank": 60 }, { "arena": "models", "category": "gamedev", - "elo": 1205, + "elo": 1195, "win_rate": 56, - "rank": 47 + "rank": 59 }, { "arena": "models", "category": "uicomponent", - "elo": 1197, + "elo": 1190, "win_rate": 51.3, - "rank": 55 + "rank": 63 }, { "arena": "models", "category": "asciiart", - "elo": 1161, + "elo": 1152, "win_rate": 50.7, - "rank": 36 + "rank": 43 }, { "arena": "models", "category": "svg", - "elo": 1138, + "elo": 1139, "win_rate": 53.7, - "rank": 50 + "rank": 51 } ], "artificial_analysis": { @@ -24327,12 +25319,12 @@ "category": "androidnative", "elo": 1084, "win_rate": 35.2, - "rank": 30 + "rank": 31 }, { "arena": "agents", "category": "fullstack", - "elo": 981, + "elo": 983, "win_rate": 36.5, "rank": 42 }, @@ -24346,72 +25338,72 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1051, + "elo": 1053, "win_rate": 41.4, - "rank": 44 + "rank": 46 }, { "arena": "agents", "category": "webapps", - "elo": 1025, + "elo": 1032, "win_rate": 36.9, - "rank": 39 + "rank": 43 }, { "arena": "models", "category": "3d", - "elo": 1016, + "elo": 1008, "win_rate": 35.3, - "rank": 102 + "rank": 110 }, { "arena": "models", "category": "asciiart", - "elo": 1160, + "elo": 1152, "win_rate": 51.2, - "rank": 37 + "rank": 42 }, { "arena": "models", "category": "codecategories", - "elo": 1149, + "elo": 1145, "win_rate": 47.2, - "rank": 76 + "rank": 88 }, { "arena": "models", "category": "dataviz", - "elo": 1170, + "elo": 1164, "win_rate": 50.6, - "rank": 69 + "rank": 75 }, { "arena": "models", "category": "gamedev", - "elo": 1172, + "elo": 1161, "win_rate": 51.3, - "rank": 62 + "rank": 73 }, { "arena": "models", "category": "svg", - "elo": 1128, + "elo": 1129, "win_rate": 54, - "rank": 53 + "rank": 54 }, { "arena": "models", "category": "uicomponent", - "elo": 1144, + "elo": 1137, "win_rate": 47.3, - "rank": 76 + "rank": 84 }, { "arena": "models", "category": "website", - "elo": 1169, + "elo": 1163, "win_rate": 48.6, - "rank": 75 + "rank": 85 } ], "artificial_analysis": { @@ -24493,70 +25485,70 @@ { "arena": "models", "category": "3d", - "elo": 1109, + "elo": 1102, "win_rate": 42.3, - "rank": 80 + "rank": 88 }, { "arena": "models", "category": "asciiart", - "elo": 1208, + "elo": 1199, "win_rate": 55.4, - "rank": 23 + "rank": 26 }, { "arena": "models", "category": "codecategories", - "elo": 1217, + "elo": 1212, "win_rate": 52.5, - "rank": 47 + "rank": 56 }, { "arena": "models", "category": "dataviz", - "elo": 1241, + "elo": 1235, "win_rate": 56.6, - "rank": 34 + "rank": 42 }, { "arena": "models", "category": "gamedev", - "elo": 1249, + "elo": 1239, "win_rate": 57.6, - "rank": 33 + "rank": 40 }, { "arena": "models", "category": "svg", - "elo": 1194, + "elo": 1195, "win_rate": 57.8, - "rank": 27 + "rank": 28 }, { "arena": "models", "category": "uicomponent", - "elo": 1245, + "elo": 1240, "win_rate": 57.4, - "rank": 38 + "rank": 44 }, { "arena": "models", "category": "website", - "elo": 1226, + "elo": 1220, "win_rate": 52.5, - "rank": 51 + "rank": 60 }, { "arena": "agents", "category": "androidnative", - "elo": 1046, + "elo": 1031, "win_rate": 47.4, - "rank": 36 + "rank": 37 }, { "arena": "agents", "category": "fullstack", - "elo": 1016, + "elo": 1017, "win_rate": 40.9, "rank": 39 }, @@ -24570,16 +25562,16 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1084, + "elo": 1087, "win_rate": 46.1, - "rank": 42 + "rank": 44 }, { "arena": "agents", "category": "webapps", - "elo": 1052, + "elo": 1059, "win_rate": 40.3, - "rank": 37 + "rank": 41 } ], "artificial_analysis": { @@ -25127,70 +26119,70 @@ { "arena": "models", "category": "3d", - "elo": 1109, + "elo": 1102, "win_rate": 42.3, - "rank": 80 + "rank": 88 }, { "arena": "models", "category": "asciiart", - "elo": 1208, + "elo": 1199, "win_rate": 55.4, - "rank": 23 + "rank": 26 }, { "arena": "models", "category": "codecategories", - "elo": 1217, + "elo": 1212, "win_rate": 52.5, - "rank": 47 + "rank": 56 }, { "arena": "models", "category": "dataviz", - "elo": 1241, + "elo": 1235, "win_rate": 56.6, - "rank": 34 + "rank": 42 }, { "arena": "models", "category": "gamedev", - "elo": 1249, + "elo": 1239, "win_rate": 57.6, - "rank": 33 + "rank": 40 }, { "arena": "models", "category": "svg", - "elo": 1194, + "elo": 1195, "win_rate": 57.8, - "rank": 27 + "rank": 28 }, { "arena": "models", "category": "uicomponent", - "elo": 1245, + "elo": 1240, "win_rate": 57.4, - "rank": 38 + "rank": 44 }, { "arena": "models", "category": "website", - "elo": 1226, + "elo": 1220, "win_rate": 52.5, - "rank": 51 + "rank": 60 }, { "arena": "agents", "category": "androidnative", - "elo": 1046, + "elo": 1031, "win_rate": 47.4, - "rank": 36 + "rank": 37 }, { "arena": "agents", "category": "fullstack", - "elo": 1016, + "elo": 1017, "win_rate": 40.9, "rank": 39 }, @@ -25204,16 +26196,16 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1084, + "elo": 1087, "win_rate": 46.1, - "rank": 42 + "rank": 44 }, { "arena": "agents", "category": "webapps", - "elo": 1052, + "elo": 1059, "win_rate": 40.3, - "rank": 37 + "rank": 41 } ], "artificial_analysis": { @@ -25331,14 +26323,14 @@ { "arena": "agents", "category": "androidnative", - "elo": 1177, + "elo": 1163, "win_rate": 50.9, - "rank": 19 + "rank": 21 }, { "arena": "agents", "category": "fullstack", - "elo": 1088, + "elo": 1089, "win_rate": 43, "rank": 29 }, @@ -25352,16 +26344,16 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1067, + "elo": 1068, "win_rate": 35.6, "rank": 22 }, { "arena": "agents", "category": "mobileapps", - "elo": 1139, + "elo": 1142, "win_rate": 50.4, - "rank": 30 + "rank": 32 }, { "arena": "agents", @@ -25375,70 +26367,70 @@ "category": "python-pptxslides", "elo": 1152, "win_rate": 43.3, - "rank": 23 + "rank": 22 }, { "arena": "agents", "category": "webapps", - "elo": 1110, + "elo": 1117, "win_rate": 42.6, - "rank": 32 + "rank": 36 }, { "arena": "models", "category": "3d", - "elo": 1205, - "win_rate": 49.8, - "rank": 43 + "elo": 1197, + "win_rate": 49.3, + "rank": 50 }, { "arena": "models", "category": "asciiart", - "elo": 1262, - "win_rate": 58.5, - "rank": 15 + "elo": 1255, + "win_rate": 58.2, + "rank": 16 }, { "arena": "models", "category": "codecategories", - "elo": 1265, - "win_rate": 53.6, - "rank": 29 + "elo": 1260, + "win_rate": 53, + "rank": 36 }, { "arena": "models", "category": "dataviz", - "elo": 1271, - "win_rate": 56, - "rank": 24 + "elo": 1265, + "win_rate": 55.7, + "rank": 29 }, { "arena": "models", "category": "gamedev", - "elo": 1305, - "win_rate": 58, - "rank": 13 + "elo": 1294, + "win_rate": 56.9, + "rank": 21 }, { "arena": "models", "category": "svg", "elo": 1235, - "win_rate": 55.4, + "win_rate": 55.1, "rank": 16 }, { "arena": "models", "category": "uicomponent", - "elo": 1265, - "win_rate": 53.7, - "rank": 32 + "elo": 1260, + "win_rate": 53.3, + "rank": 38 }, { "arena": "models", "category": "website", - "elo": 1262, - "win_rate": 52.8, - "rank": 34 + "elo": 1256, + "win_rate": 52.2, + "rank": 41 } ], "artificial_analysis": { @@ -25685,14 +26677,14 @@ { "arena": "agents", "category": "androidnative", - "elo": 1177, + "elo": 1163, "win_rate": 50.9, - "rank": 19 + "rank": 21 }, { "arena": "agents", "category": "fullstack", - "elo": 1088, + "elo": 1089, "win_rate": 43, "rank": 29 }, @@ -25706,16 +26698,16 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1067, + "elo": 1068, "win_rate": 35.6, "rank": 22 }, { "arena": "agents", "category": "mobileapps", - "elo": 1139, + "elo": 1142, "win_rate": 50.4, - "rank": 30 + "rank": 32 }, { "arena": "agents", @@ -25729,70 +26721,70 @@ "category": "python-pptxslides", "elo": 1152, "win_rate": 43.3, - "rank": 23 + "rank": 22 }, { "arena": "agents", "category": "webapps", - "elo": 1110, + "elo": 1117, "win_rate": 42.6, - "rank": 32 + "rank": 36 }, { "arena": "models", "category": "3d", - "elo": 1205, - "win_rate": 49.8, - "rank": 43 + "elo": 1197, + "win_rate": 49.3, + "rank": 50 }, { "arena": "models", "category": "asciiart", - "elo": 1262, - "win_rate": 58.5, - "rank": 15 + "elo": 1255, + "win_rate": 58.2, + "rank": 16 }, { "arena": "models", "category": "codecategories", - "elo": 1265, - "win_rate": 53.6, - "rank": 29 + "elo": 1260, + "win_rate": 53, + "rank": 36 }, { "arena": "models", "category": "dataviz", - "elo": 1271, - "win_rate": 56, - "rank": 24 + "elo": 1265, + "win_rate": 55.7, + "rank": 29 }, { "arena": "models", "category": "gamedev", - "elo": 1305, - "win_rate": 58, - "rank": 13 + "elo": 1294, + "win_rate": 56.9, + "rank": 21 }, { "arena": "models", "category": "svg", "elo": 1235, - "win_rate": 55.4, + "win_rate": 55.1, "rank": 16 }, { "arena": "models", "category": "uicomponent", - "elo": 1265, - "win_rate": 53.7, - "rank": 32 + "elo": 1260, + "win_rate": 53.3, + "rank": 38 }, { "arena": "models", "category": "website", - "elo": 1262, - "win_rate": 52.8, - "rank": 34 + "elo": 1256, + "win_rate": 52.2, + "rank": 41 } ], "artificial_analysis": { @@ -26118,18 +27110,18 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000002", - "completion": "0.00001", + "prompt": "0.000004", + "completion": "0.00002", "web_search": "0.01", - "input_cache_read": "0.0000002", - "input_cache_write": "0.0000025", + "input_cache_read": "0.0000004", + "input_cache_write": "0.000005", "overrides": [ { "min_prompt_tokens": 272000, - "prompt": "0.000004", - "completion": "0.000015", - "input_cache_read": "0.0000004", - "input_cache_write": "0.000005" + "prompt": "0.000008", + "completion": "0.00003", + "input_cache_read": "0.0000008", + "input_cache_write": "0.00001" } ] }, @@ -26197,18 +27189,18 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000002", - "completion": "0.00001", + "prompt": "0.000004", + "completion": "0.00002", "web_search": "0.01", - "input_cache_read": "0.0000002", - "input_cache_write": "0.0000025", + "input_cache_read": "0.0000004", + "input_cache_write": "0.000005", "overrides": [ { "min_prompt_tokens": 272000, - "prompt": "0.000004", - "completion": "0.000015", - "input_cache_read": "0.0000004", - "input_cache_write": "0.000005" + "prompt": "0.000008", + "completion": "0.00003", + "input_cache_read": "0.0000008", + "input_cache_write": "0.00001" } ] }, @@ -26268,18 +27260,18 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000001", - "completion": "0.000005", + "prompt": "0.000002", + "completion": "0.00001", "web_search": "0.01", - "input_cache_read": "0.0000001", - "input_cache_write": "0.00000125", + "input_cache_read": "0.0000002", + "input_cache_write": "0.0000025", "overrides": [ { "min_prompt_tokens": 272000, - "prompt": "0.000002", - "completion": "0.0000075", - "input_cache_read": "0.0000002", - "input_cache_write": "0.0000025" + "prompt": "0.000004", + "completion": "0.000015", + "input_cache_read": "0.0000004", + "input_cache_write": "0.000005" } ] }, @@ -26338,18 +27330,18 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000001", - "completion": "0.000005", + "prompt": "0.000002", + "completion": "0.00001", "web_search": "0.01", - "input_cache_read": "0.0000001", - "input_cache_write": "0.00000125", + "input_cache_read": "0.0000002", + "input_cache_write": "0.0000025", "overrides": [ { "min_prompt_tokens": 272000, - "prompt": "0.000002", - "completion": "0.0000075", - "input_cache_read": "0.0000002", - "input_cache_write": "0.0000025" + "prompt": "0.000004", + "completion": "0.000015", + "input_cache_read": "0.0000004", + "input_cache_write": "0.000005" } ] }, @@ -26800,7 +27792,7 @@ "top_provider": { "context_length": 1050000, "max_completion_tokens": 128000, - "is_moderated": true + "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ @@ -26942,35 +27934,333 @@ "tools", "verbosity" ], - "default_parameters": {}, + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/openai/gpt-6-astra-20260903/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 52.7, + "coding_index": 76.9, + "agentic_index": 51 + } + }, + "reasoning": { + "mandatory": true, + "default_enabled": true, + "supported_efforts": ["max", "xhigh", "high", "medium", "low"], + "default_effort": "medium" + } + }, + { + "id": "openai/gpt-6-luna", + "canonical_slug": "openai/gpt-6-luna-20260922", + "hugging_face_id": null, + "name": "OpenAI: GPT-6 Luna", + "created": 1790100786, + "description": "GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...", + "context_length": 1050000, + "architecture": { + "modality": "text+image+file->text", + "input_modalities": ["file", "image", "text"], + "output_modalities": ["text"], + "tokenizer": "GPT", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000001", + "completion": "0.0000005", + "web_search": "0.01", + "input_cache_read": "0.00000001", + "input_cache_write": "0.000000125", + "overrides": [ + { + "min_prompt_tokens": 272000, + "prompt": "0.0000002", + "completion": "0.00000075", + "input_cache_read": "0.00000002", + "input_cache_write": "0.00000025" + } + ] + }, + "top_provider": { + "context_length": 1050000, + "max_completion_tokens": 128000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_completion_tokens", + "max_tokens", + "reasoning", + "reasoning_effort", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools", + "verbosity" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/openai/gpt-6-luna-20260922/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 38.1, + "coding_index": null, + "agentic_index": null + } + }, + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], + "default_effort": "medium" + } + }, + { + "id": "openai/gpt-6-luna-pro", + "canonical_slug": "openai/gpt-6-luna-pro-20260922", + "hugging_face_id": null, + "name": "OpenAI: GPT-6 Luna Pro", + "created": 1790100791, + "description": "GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...", + "context_length": 1050000, + "architecture": { + "modality": "text+image+file->text", + "input_modalities": ["file", "image", "text"], + "output_modalities": ["text"], + "tokenizer": "GPT", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000001", + "completion": "0.0000005", + "web_search": "0.01", + "input_cache_read": "0.00000001", + "input_cache_write": "0.000000125", + "overrides": [ + { + "min_prompt_tokens": 272000, + "prompt": "0.0000002", + "completion": "0.00000075", + "input_cache_read": "0.00000002", + "input_cache_write": "0.00000025" + } + ] + }, + "top_provider": { + "context_length": 1050000, + "max_completion_tokens": 128000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_completion_tokens", + "max_tokens", + "reasoning", + "reasoning_effort", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools", + "verbosity" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/openai/gpt-6-luna-pro-20260922/endpoints" + }, + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], + "default_effort": "medium" + } + }, + { + "id": "openai/gpt-6-luna-pro:batch", + "canonical_slug": "openai/gpt-6-luna-pro-20260922", + "hugging_face_id": null, + "name": "OpenAI: GPT-6 Luna Pro (batch)", + "created": 1790100791, + "description": "GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...", + "context_length": 1050000, + "architecture": { + "modality": "text+image+file->text", + "input_modalities": ["file", "image", "text"], + "output_modalities": ["text"], + "tokenizer": "GPT", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000005", + "completion": "0.00000025", + "web_search": "0.01", + "input_cache_read": "0.000000005", + "input_cache_write": "0.0000000625", + "overrides": [ + { + "min_prompt_tokens": 272000, + "prompt": "0.0000001", + "completion": "0.000000375", + "input_cache_read": "0.00000001", + "input_cache_write": "0.000000125" + } + ] + }, + "top_provider": { + "context_length": 1050000, + "max_completion_tokens": 128000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "reasoning_effort", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools", + "verbosity" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/openai/gpt-6-luna-pro-20260922/endpoints" + }, + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], + "default_effort": "medium" + } + }, + { + "id": "openai/gpt-6-luna:batch", + "canonical_slug": "openai/gpt-6-luna-20260922", + "hugging_face_id": null, + "name": "OpenAI: GPT-6 Luna (batch)", + "created": 1790100786, + "description": "GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...", + "context_length": 1050000, + "architecture": { + "modality": "text+image+file->text", + "input_modalities": ["file", "image", "text"], + "output_modalities": ["text"], + "tokenizer": "GPT", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000005", + "completion": "0.00000025", + "web_search": "0.01", + "input_cache_read": "0.000000005", + "input_cache_write": "0.0000000625", + "overrides": [ + { + "min_prompt_tokens": 272000, + "prompt": "0.0000001", + "completion": "0.000000375", + "input_cache_read": "0.00000001", + "input_cache_write": "0.000000125" + } + ] + }, + "top_provider": { + "context_length": 1050000, + "max_completion_tokens": 128000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "reasoning_effort", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools", + "verbosity" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-6-astra-20260903/endpoints" + "details": "/api/v1/models/openai/gpt-6-luna-20260922/endpoints" }, "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 52.7, - "coding_index": 76.9, - "agentic_index": 51 + "intelligence_index": 38.1, + "coding_index": null, + "agentic_index": null } }, "reasoning": { - "mandatory": true, + "mandatory": false, "default_enabled": true, - "supported_efforts": ["max", "xhigh", "high", "medium", "low"], + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], "default_effort": "medium" } }, { - "id": "openai/gpt-6-luna", - "canonical_slug": "openai/gpt-6-luna-20260922", + "id": "openai/gpt-6-sol", + "canonical_slug": "openai/gpt-6-sol-20260922", "hugging_face_id": null, - "name": "OpenAI: GPT-6 Luna", - "created": 1790100786, - "description": "GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...", + "name": "OpenAI: GPT-6 Sol", + "created": 1790100775, + "description": "GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional...", "context_length": 1050000, "architecture": { "modality": "text+image+file->text", @@ -26980,18 +28270,18 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000001", - "completion": "0.0000005", + "prompt": "0.000002", + "completion": "0.00001", "web_search": "0.01", - "input_cache_read": "0.00000001", - "input_cache_write": "0.000000125", + "input_cache_read": "0.0000002", + "input_cache_write": "0.0000025", "overrides": [ { "min_prompt_tokens": 272000, - "prompt": "0.0000002", - "completion": "0.00000075", - "input_cache_read": "0.00000002", - "input_cache_write": "0.00000025" + "prompt": "0.000004", + "completion": "0.000015", + "input_cache_read": "0.0000004", + "input_cache_write": "0.000005" } ] }, @@ -27026,12 +28316,12 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-6-luna-20260922/endpoints" + "details": "/api/v1/models/openai/gpt-6-sol-20260922/endpoints" }, "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 38.1, + "intelligence_index": 47.6, "coding_index": null, "agentic_index": null } @@ -27044,12 +28334,12 @@ } }, { - "id": "openai/gpt-6-luna-pro", - "canonical_slug": "openai/gpt-6-luna-pro-20260922", + "id": "openai/gpt-6-sol-pro", + "canonical_slug": "openai/gpt-6-sol-pro-20260922", "hugging_face_id": null, - "name": "OpenAI: GPT-6 Luna Pro", - "created": 1790100791, - "description": "GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...", + "name": "OpenAI: GPT-6 Sol Pro", + "created": 1790100781, + "description": "GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...", "context_length": 1050000, "architecture": { "modality": "text+image+file->text", @@ -27059,18 +28349,18 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000001", - "completion": "0.0000005", + "prompt": "0.000002", + "completion": "0.00001", "web_search": "0.01", - "input_cache_read": "0.00000001", - "input_cache_write": "0.000000125", + "input_cache_read": "0.0000002", + "input_cache_write": "0.0000025", "overrides": [ { "min_prompt_tokens": 272000, - "prompt": "0.0000002", - "completion": "0.00000075", - "input_cache_read": "0.00000002", - "input_cache_write": "0.00000025" + "prompt": "0.000004", + "completion": "0.000015", + "input_cache_read": "0.0000004", + "input_cache_write": "0.000005" } ] }, @@ -27105,7 +28395,7 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-6-luna-pro-20260922/endpoints" + "details": "/api/v1/models/openai/gpt-6-sol-pro-20260922/endpoints" }, "reasoning": { "mandatory": false, @@ -27115,12 +28405,12 @@ } }, { - "id": "openai/gpt-6-luna-pro:batch", - "canonical_slug": "openai/gpt-6-luna-pro-20260922", + "id": "openai/gpt-6-sol-pro:batch", + "canonical_slug": "openai/gpt-6-sol-pro-20260922", "hugging_face_id": null, - "name": "OpenAI: GPT-6 Luna Pro (batch)", - "created": 1790100791, - "description": "GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...", + "name": "OpenAI: GPT-6 Sol Pro (batch)", + "created": 1790100781, + "description": "GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...", "context_length": 1050000, "architecture": { "modality": "text+image+file->text", @@ -27130,18 +28420,18 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000005", - "completion": "0.00000025", + "prompt": "0.000001", + "completion": "0.000005", "web_search": "0.01", - "input_cache_read": "0.000000005", - "input_cache_write": "0.0000000625", + "input_cache_read": "0.0000001", + "input_cache_write": "0.00000125", "overrides": [ { "min_prompt_tokens": 272000, - "prompt": "0.0000001", - "completion": "0.000000375", - "input_cache_read": "0.00000001", - "input_cache_write": "0.000000125" + "prompt": "0.000002", + "completion": "0.0000075", + "input_cache_read": "0.0000002", + "input_cache_write": "0.0000025" } ] }, @@ -27175,7 +28465,7 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-6-luna-pro-20260922/endpoints" + "details": "/api/v1/models/openai/gpt-6-sol-pro-20260922/endpoints" }, "reasoning": { "mandatory": false, @@ -27185,12 +28475,12 @@ } }, { - "id": "openai/gpt-6-luna:batch", - "canonical_slug": "openai/gpt-6-luna-20260922", + "id": "openai/gpt-6-sol:batch", + "canonical_slug": "openai/gpt-6-sol-20260922", "hugging_face_id": null, - "name": "OpenAI: GPT-6 Luna (batch)", - "created": 1790100786, - "description": "GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...", + "name": "OpenAI: GPT-6 Sol (batch)", + "created": 1790100775, + "description": "GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional...", "context_length": 1050000, "architecture": { "modality": "text+image+file->text", @@ -27200,18 +28490,18 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000005", - "completion": "0.00000025", + "prompt": "0.000001", + "completion": "0.000005", "web_search": "0.01", - "input_cache_read": "0.000000005", - "input_cache_write": "0.0000000625", + "input_cache_read": "0.0000001", + "input_cache_write": "0.00000125", "overrides": [ { "min_prompt_tokens": 272000, - "prompt": "0.0000001", - "completion": "0.000000375", - "input_cache_read": "0.00000001", - "input_cache_write": "0.000000125" + "prompt": "0.000002", + "completion": "0.0000075", + "input_cache_read": "0.0000002", + "input_cache_write": "0.0000025" } ] }, @@ -27245,12 +28535,12 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-6-luna-20260922/endpoints" + "details": "/api/v1/models/openai/gpt-6-sol-20260922/endpoints" }, "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 38.1, + "intelligence_index": 47.6, "coding_index": null, "agentic_index": null } @@ -27263,12 +28553,12 @@ } }, { - "id": "openai/gpt-6-sol", - "canonical_slug": "openai/gpt-6-sol-20260922", + "id": "openai/gpt-6.1-sol", + "canonical_slug": "openai/gpt-6.1-sol-20260929", "hugging_face_id": null, - "name": "OpenAI: GPT-6 Sol", - "created": 1790100775, - "description": "GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional...", + "name": "OpenAI: GPT-6.1 Sol", + "created": 1790702882, + "description": "GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...", "context_length": 1050000, "architecture": { "modality": "text+image+file->text", @@ -27281,14 +28571,14 @@ "prompt": "0.000002", "completion": "0.00001", "web_search": "0.01", - "input_cache_read": "0.0000002", + "input_cache_read": "0.0000001", "input_cache_write": "0.0000025", "overrides": [ { "min_prompt_tokens": 272000, "prompt": "0.000004", "completion": "0.000015", - "input_cache_read": "0.0000004", + "input_cache_read": "0.0000002", "input_cache_write": "0.000005" } ] @@ -27312,42 +28602,99 @@ "tools", "verbosity" ], - "default_parameters": { - "temperature": null, - "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, + "default_parameters": {}, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-6-sol-20260922/endpoints" + "details": "/api/v1/models/openai/gpt-6.1-sol-20260929/endpoints" }, "benchmarks": { - "design_arena": [], + "design_arena": [ + { + "arena": "agents", + "category": "mobileapps", + "elo": 1212, + "win_rate": 49.2, + "rank": 16 + }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1235, + "win_rate": 52.3, + "rank": 7 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1306, + "win_rate": 60.3, + "rank": 4 + }, + { + "arena": "models", + "category": "3d", + "elo": 1463, + "win_rate": 70.6, + "rank": 2 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1345, + "win_rate": 58.4, + "rank": 6 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1284, + "win_rate": 51.4, + "rank": 18 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1390, + "win_rate": 63.9, + "rank": 3 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1322, + "win_rate": 54.9, + "rank": 11 + }, + { + "arena": "models", + "category": "website", + "elo": 1321, + "win_rate": 55.8, + "rank": 6 + } + ], "artificial_analysis": { - "intelligence_index": 47.6, + "intelligence_index": 51.8, "coding_index": null, "agentic_index": null } }, "reasoning": { - "mandatory": false, + "mandatory": true, "default_enabled": true, - "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], + "supported_efforts": ["max", "xhigh", "high", "medium", "low"], "default_effort": "medium" } }, { - "id": "openai/gpt-6-sol-pro", - "canonical_slug": "openai/gpt-6-sol-pro-20260922", + "id": "openai/gpt-6.1-sol-pro", + "canonical_slug": "openai/gpt-6.1-sol-pro-20260929", "hugging_face_id": null, - "name": "OpenAI: GPT-6 Sol Pro", - "created": 1790100781, - "description": "GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...", + "name": "OpenAI: GPT-6.1 Sol Pro", + "created": 1790702886, + "description": "GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...", "context_length": 1050000, "architecture": { "modality": "text+image+file->text", @@ -27360,14 +28707,14 @@ "prompt": "0.000002", "completion": "0.00001", "web_search": "0.01", - "input_cache_read": "0.0000002", + "input_cache_read": "0.0000001", "input_cache_write": "0.0000025", "overrides": [ { "min_prompt_tokens": 272000, "prompt": "0.000004", "completion": "0.000015", - "input_cache_read": "0.0000004", + "input_cache_read": "0.0000002", "input_cache_write": "0.000005" } ] @@ -27403,22 +28750,22 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-6-sol-pro-20260922/endpoints" + "details": "/api/v1/models/openai/gpt-6.1-sol-pro-20260929/endpoints" }, "reasoning": { - "mandatory": false, + "mandatory": true, "default_enabled": true, - "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], + "supported_efforts": ["max", "xhigh", "high", "medium", "low"], "default_effort": "medium" } }, { - "id": "openai/gpt-6-sol-pro:batch", - "canonical_slug": "openai/gpt-6-sol-pro-20260922", + "id": "openai/gpt-6.1-sol-pro:batch", + "canonical_slug": "openai/gpt-6.1-sol-pro-20260929", "hugging_face_id": null, - "name": "OpenAI: GPT-6 Sol Pro (batch)", - "created": 1790100781, - "description": "GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...", + "name": "OpenAI: GPT-6.1 Sol Pro (batch)", + "created": 1790702886, + "description": "GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...", "context_length": 1050000, "architecture": { "modality": "text+image+file->text", @@ -27431,14 +28778,14 @@ "prompt": "0.000001", "completion": "0.000005", "web_search": "0.01", - "input_cache_read": "0.0000001", + "input_cache_read": "0.00000005", "input_cache_write": "0.00000125", "overrides": [ { "min_prompt_tokens": 272000, "prompt": "0.000002", "completion": "0.0000075", - "input_cache_read": "0.0000002", + "input_cache_read": "0.0000001", "input_cache_write": "0.0000025" } ] @@ -27473,22 +28820,22 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-6-sol-pro-20260922/endpoints" + "details": "/api/v1/models/openai/gpt-6.1-sol-pro-20260929/endpoints" }, "reasoning": { - "mandatory": false, + "mandatory": true, "default_enabled": true, - "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], + "supported_efforts": ["max", "xhigh", "high", "medium", "low"], "default_effort": "medium" } }, { - "id": "openai/gpt-6-sol:batch", - "canonical_slug": "openai/gpt-6-sol-20260922", + "id": "openai/gpt-6.1-sol:batch", + "canonical_slug": "openai/gpt-6.1-sol-20260929", "hugging_face_id": null, - "name": "OpenAI: GPT-6 Sol (batch)", - "created": 1790100775, - "description": "GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional...", + "name": "OpenAI: GPT-6.1 Sol (batch)", + "created": 1790702882, + "description": "GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...", "context_length": 1050000, "architecture": { "modality": "text+image+file->text", @@ -27501,14 +28848,14 @@ "prompt": "0.000001", "completion": "0.000005", "web_search": "0.01", - "input_cache_read": "0.0000001", + "input_cache_read": "0.00000005", "input_cache_write": "0.00000125", "overrides": [ { "min_prompt_tokens": 272000, "prompt": "0.000002", "completion": "0.0000075", - "input_cache_read": "0.0000002", + "input_cache_read": "0.0000001", "input_cache_write": "0.0000025" } ] @@ -27531,85 +28878,6 @@ "tools", "verbosity" ], - "default_parameters": { - "temperature": null, - "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": null, - "links": { - "details": "/api/v1/models/openai/gpt-6-sol-20260922/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 47.6, - "coding_index": null, - "agentic_index": null - } - }, - "reasoning": { - "mandatory": false, - "default_enabled": true, - "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], - "default_effort": "medium" - } - }, - { - "id": "openai/gpt-6.1-sol", - "canonical_slug": "openai/gpt-6.1-sol-20260929", - "hugging_face_id": null, - "name": "OpenAI: GPT-6.1 Sol", - "created": 1790702882, - "description": "GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...", - "context_length": 1050000, - "architecture": { - "modality": "text+image+file->text", - "input_modalities": ["file", "image", "text"], - "output_modalities": ["text"], - "tokenizer": "GPT", - "instruct_type": null - }, - "pricing": { - "prompt": "0.000002", - "completion": "0.00001", - "web_search": "0.01", - "input_cache_read": "0.0000001", - "input_cache_write": "0.0000025", - "overrides": [ - { - "min_prompt_tokens": 272000, - "prompt": "0.000004", - "completion": "0.000015", - "input_cache_read": "0.0000002", - "input_cache_write": "0.000005" - } - ] - }, - "top_provider": { - "context_length": 1050000, - "max_completion_tokens": 128000, - "is_moderated": true - }, - "per_request_limits": null, - "supported_parameters": [ - "include_reasoning", - "max_completion_tokens", - "max_tokens", - "reasoning", - "reasoning_effort", - "response_format", - "seed", - "structured_outputs", - "tool_choice", - "tools", - "verbosity" - ], "default_parameters": {}, "supported_voices": null, "knowledge_cutoff": null, @@ -27618,7 +28886,71 @@ "details": "/api/v1/models/openai/gpt-6.1-sol-20260929/endpoints" }, "benchmarks": { - "design_arena": [], + "design_arena": [ + { + "arena": "agents", + "category": "mobileapps", + "elo": 1212, + "win_rate": 49.2, + "rank": 16 + }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1235, + "win_rate": 52.3, + "rank": 7 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1306, + "win_rate": 60.3, + "rank": 4 + }, + { + "arena": "models", + "category": "3d", + "elo": 1463, + "win_rate": 70.6, + "rank": 2 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1345, + "win_rate": 58.4, + "rank": 6 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1284, + "win_rate": 51.4, + "rank": 18 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1390, + "win_rate": 63.9, + "rank": 3 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1322, + "win_rate": 54.9, + "rank": 11 + }, + { + "arena": "models", + "category": "website", + "elo": 1321, + "win_rate": 55.8, + "rank": 6 + } + ], "artificial_analysis": { "intelligence_index": 51.8, "coding_index": null, @@ -27632,77 +28964,6 @@ "default_effort": "medium" } }, - { - "id": "openai/gpt-6.1-sol-pro", - "canonical_slug": "openai/gpt-6.1-sol-pro-20260929", - "hugging_face_id": null, - "name": "OpenAI: GPT-6.1 Sol Pro", - "created": 1790702886, - "description": "GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...", - "context_length": 1050000, - "architecture": { - "modality": "text+image+file->text", - "input_modalities": ["file", "image", "text"], - "output_modalities": ["text"], - "tokenizer": "GPT", - "instruct_type": null - }, - "pricing": { - "prompt": "0.000002", - "completion": "0.00001", - "web_search": "0.01", - "input_cache_read": "0.0000001", - "input_cache_write": "0.0000025", - "overrides": [ - { - "min_prompt_tokens": 272000, - "prompt": "0.000004", - "completion": "0.000015", - "input_cache_read": "0.0000002", - "input_cache_write": "0.000005" - } - ] - }, - "top_provider": { - "context_length": 1050000, - "max_completion_tokens": 128000, - "is_moderated": true - }, - "per_request_limits": null, - "supported_parameters": [ - "include_reasoning", - "max_completion_tokens", - "max_tokens", - "reasoning", - "reasoning_effort", - "response_format", - "seed", - "structured_outputs", - "tool_choice", - "tools", - "verbosity" - ], - "default_parameters": { - "temperature": null, - "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": null, - "links": { - "details": "/api/v1/models/openai/gpt-6.1-sol-pro-20260929/endpoints" - }, - "reasoning": { - "mandatory": true, - "default_enabled": true, - "supported_efforts": ["max", "xhigh", "high", "medium", "low"], - "default_effort": "medium" - } - }, { "id": "openai/gpt-audio", "canonical_slug": "openai/gpt-audio", @@ -27882,12 +29143,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000000037", - "completion": "0.00000017" + "prompt": "0.00000015", + "completion": "0.0000006", + "input_cache_read": "0.000000075" }, "top_provider": { "context_length": 131072, - "max_completion_tokens": 117964, + "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, @@ -27930,44 +29192,44 @@ { "arena": "models", "category": "3d", - "elo": 909, + "elo": 901, "win_rate": 29.4, - "rank": 112 + "rank": 120 }, { "arena": "models", "category": "codecategories", - "elo": 967, + "elo": 963, "win_rate": 33.4, - "rank": 120 + "rank": 131 }, { "arena": "models", "category": "dataviz", - "elo": 993, + "elo": 987, "win_rate": 43.6, - "rank": 111 + "rank": 118 }, { "arena": "models", "category": "gamedev", - "elo": 1002, + "elo": 992, "win_rate": 40.5, - "rank": 110 + "rank": 123 }, { "arena": "models", "category": "uicomponent", - "elo": 932, + "elo": 927, "win_rate": 35.7, - "rank": 116 + "rank": 124 }, { "arena": "models", "category": "website", - "elo": 974, + "elo": 968, "win_rate": 32.5, - "rank": 123 + "rank": 135 } ], "artificial_analysis": { @@ -28043,44 +29305,44 @@ { "arena": "models", "category": "3d", - "elo": 909, + "elo": 901, "win_rate": 29.4, - "rank": 112 + "rank": 120 }, { "arena": "models", "category": "codecategories", - "elo": 967, + "elo": 963, "win_rate": 33.4, - "rank": 120 + "rank": 131 }, { "arena": "models", "category": "dataviz", - "elo": 993, + "elo": 987, "win_rate": 43.6, - "rank": 111 + "rank": 118 }, { "arena": "models", "category": "gamedev", - "elo": 1002, + "elo": 992, "win_rate": 40.5, - "rank": 110 + "rank": 123 }, { "arena": "models", "category": "uicomponent", - "elo": 932, + "elo": 927, "win_rate": 35.7, - "rank": 116 + "rank": 124 }, { "arena": "models", "category": "website", - "elo": 974, + "elo": 968, "win_rate": 32.5, - "rank": 123 + "rank": 135 } ], "artificial_analysis": { @@ -28159,16 +29421,16 @@ { "arena": "models", "category": "dataviz", - "elo": 938, + "elo": 933, "win_rate": 39.7, - "rank": 116 + "rank": 124 }, { "arena": "models", "category": "website", - "elo": 859, + "elo": 852, "win_rate": 27.9, - "rank": 130 + "rank": 141 } ], "artificial_analysis": { @@ -28244,16 +29506,16 @@ { "arena": "models", "category": "dataviz", - "elo": 938, + "elo": 933, "win_rate": 39.7, - "rank": 116 + "rank": 124 }, { "arena": "models", "category": "website", - "elo": 859, + "elo": 852, "win_rate": 27.9, - "rank": 130 + "rank": 141 } ], "artificial_analysis": { @@ -28378,7 +29640,7 @@ } }, "reasoning": { - "mandatory": false + "mandatory": true } }, { @@ -28431,7 +29693,7 @@ } }, "reasoning": { - "mandatory": false + "mandatory": true } }, { @@ -28483,37 +29745,37 @@ { "arena": "models", "category": "codecategories", - "elo": 1024, + "elo": 1020, "win_rate": 51.9, - "rank": 109 + "rank": 122 }, { "arena": "models", "category": "dataviz", "elo": 1200, "win_rate": 48.1, - "rank": 55 + "rank": 61 }, { "arena": "models", "category": "gamedev", - "elo": 1045, + "elo": 1034, "win_rate": 56.9, - "rank": 104 + "rank": 117 }, { "arena": "models", "category": "uicomponent", - "elo": 1023, + "elo": 1017, "win_rate": 53.3, - "rank": 106 + "rank": 114 }, { "arena": "models", "category": "website", - "elo": 1041, + "elo": 1036, "win_rate": 53.8, - "rank": 112 + "rank": 124 } ], "artificial_analysis": { @@ -28523,7 +29785,7 @@ } }, "reasoning": { - "mandatory": false + "mandatory": true } }, { @@ -28586,7 +29848,7 @@ } }, "reasoning": { - "mandatory": false + "mandatory": true } }, { @@ -28712,7 +29974,7 @@ } }, "reasoning": { - "mandatory": false + "mandatory": true } }, { @@ -28771,7 +30033,7 @@ } }, "reasoning": { - "mandatory": false + "mandatory": true } }, { @@ -28823,37 +30085,37 @@ { "arena": "models", "category": "codecategories", - "elo": 1024, + "elo": 1020, "win_rate": 51.9, - "rank": 109 + "rank": 122 }, { "arena": "models", "category": "dataviz", "elo": 1200, "win_rate": 48.1, - "rank": 55 + "rank": 61 }, { "arena": "models", "category": "gamedev", - "elo": 1045, + "elo": 1034, "win_rate": 56.9, - "rank": 104 + "rank": 117 }, { "arena": "models", "category": "uicomponent", - "elo": 1023, + "elo": 1017, "win_rate": 53.3, - "rank": 106 + "rank": 114 }, { "arena": "models", "category": "website", - "elo": 1041, + "elo": 1036, "win_rate": 53.8, - "rank": 112 + "rank": 124 } ], "artificial_analysis": { @@ -28863,7 +30125,7 @@ } }, "reasoning": { - "mandatory": false + "mandatory": true } }, { @@ -28915,44 +30177,44 @@ { "arena": "models", "category": "3d", - "elo": 862, + "elo": 854, "win_rate": 34, - "rank": 116 + "rank": 124 }, { "arena": "models", "category": "codecategories", - "elo": 980, + "elo": 976, "win_rate": 46.4, - "rank": 116 + "rank": 129 }, { "arena": "models", "category": "dataviz", - "elo": 997, + "elo": 991, "win_rate": 50, - "rank": 110 + "rank": 117 }, { "arena": "models", "category": "gamedev", - "elo": 1013, + "elo": 1003, "win_rate": 50, - "rank": 109 + "rank": 122 }, { "arena": "models", "category": "uicomponent", - "elo": 990, + "elo": 983, "win_rate": 46.9, - "rank": 109 + "rank": 117 }, { "arena": "models", "category": "website", - "elo": 990, + "elo": 985, "win_rate": 47.1, - "rank": 120 + "rank": 131 } ], "artificial_analysis": { @@ -28962,7 +30224,7 @@ } }, "reasoning": { - "mandatory": false + "mandatory": true } }, { @@ -29069,44 +30331,44 @@ { "arena": "models", "category": "3d", - "elo": 862, + "elo": 854, "win_rate": 34, - "rank": 116 + "rank": 124 }, { "arena": "models", "category": "codecategories", - "elo": 980, + "elo": 976, "win_rate": 46.4, - "rank": 116 + "rank": 129 }, { "arena": "models", "category": "dataviz", - "elo": 997, + "elo": 991, "win_rate": 50, - "rank": 110 + "rank": 117 }, { "arena": "models", "category": "gamedev", - "elo": 1013, + "elo": 1003, "win_rate": 50, - "rank": 109 + "rank": 122 }, { "arena": "models", "category": "uicomponent", - "elo": 990, + "elo": 983, "win_rate": 46.9, - "rank": 109 + "rank": 117 }, { "arena": "models", "category": "website", - "elo": 990, + "elo": 985, "win_rate": 47.1, - "rank": 120 + "rank": 131 } ], "artificial_analysis": { @@ -29116,7 +30378,7 @@ } }, "reasoning": { - "mandatory": false + "mandatory": true } }, { @@ -29322,7 +30584,7 @@ "details": "/api/v1/models/perplexity/sonar-deep-research/endpoints" }, "reasoning": { - "mandatory": false + "mandatory": true } }, { @@ -29482,7 +30744,7 @@ } }, "reasoning": { - "mandatory": false + "mandatory": true } }, { @@ -29727,7 +30989,7 @@ "reasoning": { "mandatory": false, "default_enabled": true, - "supported_efforts": ["xhigh", "medium"], + "supported_efforts": ["xhigh", "medium", "none"], "default_effort": "xhigh" } }, @@ -29957,69 +31219,6 @@ "details": "/api/v1/models/qwen/qwen-plus-2025-01-25/endpoints" } }, - { - "id": "qwen/qwen-plus-2025-07-28", - "canonical_slug": "qwen/qwen-plus-2025-07-28", - "hugging_face_id": "", - "name": "Qwen: Qwen Plus 0728", - "created": 1757347599, - "description": "Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.", - "context_length": 1000000, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Qwen3", - "instruct_type": null - }, - "pricing": { - "prompt": "0.00000026", - "completion": "0.00000078", - "overrides": [ - { - "min_prompt_tokens": 256000, - "prompt": "0.00000078", - "completion": "0.00000234" - } - ] - }, - "top_provider": { - "context_length": 1000000, - "max_completion_tokens": 32768, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "logprobs", - "max_tokens", - "presence_penalty", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_k", - "top_logprobs", - "top_p" - ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": "2025-03-31", - "expiration_date": "2026-10-09", - "links": { - "details": "/api/v1/models/qwen/qwen-plus-2025-07-28/endpoints" - }, - "reasoning": { - "mandatory": false - } - }, { "id": "qwen/qwen2.5-vl-72b-instruct", "canonical_slug": "qwen/qwen2.5-vl-72b-instruct", @@ -30077,7 +31276,7 @@ "name": "Qwen: Qwen3 14B", "created": 1745876478, "description": "Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...", - "context_length": 131072, + "context_length": 40960, "architecture": { "modality": "text->text", "input_modalities": ["text"], @@ -30126,109 +31325,7 @@ "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 8.2, - "coding_index": 13.8, - "agentic_index": 0.9 - } - }, - "reasoning": { - "mandatory": false - } - }, - { - "id": "qwen/qwen3-235b-a22b", - "canonical_slug": "qwen/qwen3-235b-a22b-04-28", - "hugging_face_id": "Qwen/Qwen3-235B-A22B", - "name": "Qwen: Qwen3 235B A22B", - "created": 1745875757, - "description": "Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a \"thinking\" mode for complex reasoning, math, and...", - "context_length": 131072, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Qwen3", - "instruct_type": "qwen3" - }, - "pricing": { - "prompt": "0.000000455", - "completion": "0.00000182" - }, - "top_provider": { - "context_length": 131072, - "max_completion_tokens": 8192, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "include_reasoning", - "max_tokens", - "presence_penalty", - "reasoning", - "response_format", - "seed", - "stop", - "temperature", - "tool_choice", - "tools", - "top_k", - "top_p" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": "2025-03-31", - "expiration_date": "2026-10-09", - "links": { - "details": "/api/v1/models/qwen/qwen3-235b-a22b-04-28/endpoints" - }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 866, - "win_rate": 24.5, - "rank": 115 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1006, - "win_rate": 38.2, - "rank": 114 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1002, - "win_rate": 40, - "rank": 109 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 938, - "win_rate": 32.9, - "rank": 120 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 964, - "win_rate": 38.6, - "rank": 112 - }, - { - "arena": "models", - "category": "website", - "elo": 1035, - "win_rate": 40.4, - "rank": 115 - } - ], - "artificial_analysis": { - "intelligence_index": 9.5, + "intelligence_index": 6.7, "coding_index": null, "agentic_index": null } @@ -30293,44 +31390,44 @@ { "arena": "models", "category": "3d", - "elo": 1002, + "elo": 994, "win_rate": 41.1, - "rank": 104 + "rank": 112 }, { "arena": "models", "category": "codecategories", - "elo": 1044, + "elo": 1039, "win_rate": 42.6, - "rank": 105 + "rank": 116 }, { "arena": "models", "category": "dataviz", - "elo": 1075, + "elo": 1070, "win_rate": 49, - "rank": 100 + "rank": 108 }, { "arena": "models", "category": "gamedev", - "elo": 962, + "elo": 952, "win_rate": 35, - "rank": 117 + "rank": 131 }, { "arena": "models", "category": "uicomponent", - "elo": 972, + "elo": 965, "win_rate": 38.4, - "rank": 110 + "rank": 118 }, { "arena": "models", "category": "website", - "elo": 1064, + "elo": 1058, "win_rate": 43.6, - "rank": 106 + "rank": 118 } ], "artificial_analysis": { @@ -30347,7 +31444,7 @@ "name": "Qwen: Qwen3 235B A22B Thinking 2507", "created": 1753449557, "description": "Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...", - "context_length": 131072, + "context_length": 128000, "architecture": { "modality": "text->text", "input_modalities": ["text"], @@ -30356,31 +31453,26 @@ "instruct_type": "qwen3" }, "pricing": { - "prompt": "0.00000023", - "completion": "0.0000023" + "prompt": "0.00000045", + "completion": "0.0000035" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": 117964, + "context_length": 128000, + "max_completion_tokens": 16384, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", "include_reasoning", - "logprobs", "max_tokens", "presence_penalty", - "reasoning", - "repetition_penalty", - "response_format", - "seed", + "reasoning", "stop", "temperature", "tool_choice", "tools", "top_k", - "top_logprobs", "top_p" ], "default_parameters": { @@ -30390,7 +31482,7 @@ }, "supported_voices": null, "knowledge_cutoff": "2025-06-30", - "expiration_date": "2026-10-09", + "expiration_date": null, "links": { "details": "/api/v1/models/qwen/qwen3-235b-a22b-thinking-2507/endpoints" }, @@ -30399,44 +31491,44 @@ { "arena": "models", "category": "3d", - "elo": 1005, + "elo": 998, "win_rate": 40.4, - "rank": 103 + "rank": 111 }, { "arena": "models", "category": "codecategories", - "elo": 1037, + "elo": 1033, "win_rate": 40.8, - "rank": 107 + "rank": 118 }, { "arena": "models", "category": "dataviz", - "elo": 955, + "elo": 950, "win_rate": 32.6, - "rank": 114 + "rank": 121 }, { "arena": "models", "category": "gamedev", - "elo": 967, + "elo": 957, "win_rate": 34.2, - "rank": 116 + "rank": 129 }, { "arena": "models", "category": "uicomponent", - "elo": 952, + "elo": 945, "win_rate": 34, - "rank": 113 + "rank": 122 }, { "arena": "models", "category": "website", - "elo": 1059, + "elo": 1053, "win_rate": 42, - "rank": 108 + "rank": 120 } ], "artificial_analysis": { @@ -30456,7 +31548,7 @@ "name": "Qwen: Qwen3 30B A3B", "created": 1745878604, "description": "Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...", - "context_length": 131072, + "context_length": 40960, "architecture": { "modality": "text->text", "input_modalities": ["text"], @@ -30509,37 +31601,37 @@ { "arena": "models", "category": "codecategories", - "elo": 946, + "elo": 942, "win_rate": 37.5, - "rank": 121 + "rank": 132 }, { "arena": "models", "category": "dataviz", - "elo": 971, + "elo": 967, "win_rate": 39, - "rank": 113 + "rank": 120 }, { "arena": "models", "category": "gamedev", - "elo": 909, + "elo": 899, "win_rate": 33.9, - "rank": 123 + "rank": 136 }, { "arena": "models", "category": "uicomponent", - "elo": 952, + "elo": 946, "win_rate": 42.4, - "rank": 114 + "rank": 121 }, { "arena": "models", "category": "website", - "elo": 961, + "elo": 955, "win_rate": 37.7, - "rank": 125 + "rank": 136 } ], "artificial_analysis": { @@ -30569,12 +31661,12 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000004815", - "completion": "0.00000019305" + "prompt": "0.00000009", + "completion": "0.0000003" }, "top_provider": { - "context_length": 128000, - "max_completion_tokens": 32000, + "context_length": 262144, + "max_completion_tokens": 235929, "is_moderated": false }, "per_request_limits": null, @@ -30612,80 +31704,6 @@ } } }, - { - "id": "qwen/qwen3-30b-a3b-thinking-2507", - "canonical_slug": "qwen/qwen3-30b-a3b-thinking-2507", - "hugging_face_id": "Qwen/Qwen3-30B-A3B-Thinking-2507", - "name": "Qwen: Qwen3 30B A3B Thinking 2507", - "created": 1756399192, - "description": "Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...", - "context_length": 81920, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Qwen3", - "instruct_type": null - }, - "pricing": { - "prompt": "0.0000002", - "completion": "0.0000024" - }, - "top_provider": { - "context_length": 81920, - "max_completion_tokens": 32768, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "include_reasoning", - "max_tokens", - "presence_penalty", - "reasoning", - "response_format", - "seed", - "stop", - "temperature", - "tool_choice", - "tools", - "top_k", - "top_p" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": "2025-06-30", - "expiration_date": "2026-10-09", - "links": { - "details": "/api/v1/models/qwen/qwen3-30b-a3b-thinking-2507/endpoints" - }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "dataviz", - "elo": 931, - "win_rate": 33.3, - "rank": 119 - }, - { - "arena": "models", - "category": "website", - "elo": 935, - "win_rate": 35.5, - "rank": 126 - } - ], - "artificial_analysis": { - "intelligence_index": 9.8, - "coding_index": 12.1, - "agentic_index": 0.9 - } - }, - "reasoning": { - "mandatory": true - } - }, { "id": "qwen/qwen3-32b", "canonical_slug": "qwen/qwen3-32b-04-28", @@ -30740,83 +31758,16 @@ "links": { "details": "/api/v1/models/qwen/qwen3-32b-04-28/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 8.6, - "coding_index": 15.3, - "agentic_index": 0.9 - } - }, - "reasoning": { - "mandatory": false - } - }, - { - "id": "qwen/qwen3-8b", - "canonical_slug": "qwen/qwen3-8b-04-28", - "hugging_face_id": "Qwen/Qwen3-8B", - "name": "Qwen: Qwen3 8B", - "created": 1745876632, - "description": "Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between \"thinking\" mode for math,...", - "context_length": 131072, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Qwen3", - "instruct_type": "qwen3" - }, - "pricing": { - "prompt": "0.000000117", - "completion": "0.000000455" - }, - "top_provider": { - "context_length": 131072, - "max_completion_tokens": 8192, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "include_reasoning", - "max_tokens", - "presence_penalty", - "reasoning", - "response_format", - "seed", - "stop", - "temperature", - "tool_choice", - "tools", - "top_k", - "top_p" - ], - "default_parameters": { - "temperature": 0.6, - "top_p": 0.95, - "top_k": 20, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": "2025-03-31", - "expiration_date": "2026-10-09", - "links": { - "details": "/api/v1/models/qwen/qwen3-8b-04-28/endpoints" - }, "benchmarks": { "design_arena": [], "artificial_analysis": { "intelligence_index": 7.3, - "coding_index": 9, - "agentic_index": 0.8 + "coding_index": null, + "agentic_index": null } }, "reasoning": { - "mandatory": false, - "default_enabled": true + "mandatory": false } }, { @@ -30876,37 +31827,37 @@ { "arena": "models", "category": "codecategories", - "elo": 1147, + "elo": 1143, "win_rate": 61.2, - "rank": 80 + "rank": 89 }, { "arena": "models", "category": "dataviz", - "elo": 1089, + "elo": 1084, "win_rate": 54.9, - "rank": 98 + "rank": 105 }, { "arena": "models", "category": "gamedev", - "elo": 1109, + "elo": 1099, "win_rate": 58.7, - "rank": 83 + "rank": 96 }, { "arena": "models", "category": "uicomponent", - "elo": 1119, + "elo": 1113, "win_rate": 61.4, - "rank": 82 + "rank": 90 }, { "arena": "models", "category": "website", - "elo": 1165, + "elo": 1159, "win_rate": 61.7, - "rank": 78 + "rank": 89 } ], "artificial_analysis": { @@ -30943,19 +31894,14 @@ "per_request_limits": null, "supported_parameters": [ "frequency_penalty", - "logprobs", "max_tokens", - "presence_penalty", - "repetition_penalty", "response_format", - "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", - "top_logprobs", "top_p" ], "default_parameters": {}, @@ -30970,23 +31916,23 @@ { "arena": "models", "category": "dataviz", - "elo": 1089, + "elo": 1085, "win_rate": 54.7, - "rank": 97 + "rank": 104 }, { "arena": "models", "category": "uicomponent", - "elo": 1053, + "elo": 1046, "win_rate": 54.1, - "rank": 97 + "rank": 105 }, { "arena": "models", "category": "website", - "elo": 1092, + "elo": 1087, "win_rate": 57.1, - "rank": 101 + "rank": 112 } ], "artificial_analysis": { @@ -31130,294 +32076,6 @@ } } }, - { - "id": "qwen/qwen3-coder-plus", - "canonical_slug": "qwen/qwen3-coder-plus", - "hugging_face_id": "", - "name": "Qwen: Qwen3 Coder Plus", - "created": 1758662707, - "description": "Qwen3 Coder Plus is Alibaba's proprietary version of the Open Source Qwen3 Coder 480B A35B. It is a powerful coding agent model specializing in autonomous programming via tool calling and...", - "context_length": 1000000, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Qwen3", - "instruct_type": null - }, - "pricing": { - "prompt": "0.00000065", - "completion": "0.00000325", - "input_cache_read": "0.00000013", - "input_cache_write": "0.0000008125", - "overrides": [ - { - "min_prompt_tokens": 32000, - "prompt": "0.00000117", - "completion": "0.00000585", - "input_cache_read": "0.000000234", - "input_cache_write": "0.0000014625" - }, - { - "min_prompt_tokens": 128000, - "prompt": "0.00000195", - "completion": "0.00000975", - "input_cache_read": "0.00000039", - "input_cache_write": "0.0000024375" - } - ] - }, - "top_provider": { - "context_length": 1000000, - "max_completion_tokens": 65536, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "logprobs", - "max_tokens", - "presence_penalty", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_k", - "top_logprobs", - "top_p" - ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": "2025-06-30", - "expiration_date": "2026-10-09", - "links": { - "details": "/api/v1/models/qwen/qwen3-coder-plus/endpoints" - } - }, - { - "id": "qwen/qwen3-max", - "canonical_slug": "qwen/qwen3-max", - "hugging_face_id": "", - "name": "Qwen: Qwen3 Max", - "created": 1758662808, - "description": "Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It...", - "context_length": 262144, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Qwen3", - "instruct_type": null - }, - "pricing": { - "prompt": "0.00000078", - "completion": "0.0000039", - "input_cache_read": "0.000000156", - "input_cache_write": "0.000000975", - "overrides": [ - { - "min_prompt_tokens": 32000, - "prompt": "0.00000156", - "completion": "0.0000078", - "input_cache_read": "0.000000312", - "input_cache_write": "0.00000195" - }, - { - "min_prompt_tokens": 128000, - "prompt": "0.00000195", - "completion": "0.00000975", - "input_cache_read": "0.00000039", - "input_cache_write": "0.0000024375" - } - ] - }, - "top_provider": { - "context_length": 262144, - "max_completion_tokens": 65536, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "logprobs", - "max_tokens", - "presence_penalty", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_k", - "top_logprobs", - "top_p" - ], - "default_parameters": { - "temperature": 1, - "top_p": 1, - "frequency_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": "2025-06-30", - "expiration_date": "2026-10-09", - "links": { - "details": "/api/v1/models/qwen/qwen3-max/endpoints" - }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1082, - "win_rate": 43.5, - "rank": 90 - }, - { - "arena": "models", - "category": "asciiart", - "elo": 1136, - "win_rate": 47.2, - "rank": 51 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1115, - "win_rate": 44, - "rank": 90 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1107, - "win_rate": 41.2, - "rank": 91 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1105, - "win_rate": 43.8, - "rank": 86 - }, - { - "arena": "models", - "category": "svg", - "elo": 1010, - "win_rate": 37.2, - "rank": 82 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1085, - "win_rate": 40.2, - "rank": 94 - }, - { - "arena": "models", - "category": "website", - "elo": 1125, - "win_rate": 44.5, - "rank": 93 - } - ], - "artificial_analysis": { - "intelligence_index": 15.6, - "coding_index": null, - "agentic_index": null - } - }, - "reasoning": { - "mandatory": false - } - }, - { - "id": "qwen/qwen3-max-thinking", - "canonical_slug": "qwen/qwen3-max-thinking-20260123", - "hugging_face_id": null, - "name": "Qwen: Qwen3 Max Thinking", - "created": 1770671901, - "description": "Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it...", - "context_length": 262144, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Qwen", - "instruct_type": null - }, - "pricing": { - "prompt": "0.00000078", - "completion": "0.0000039", - "overrides": [ - { - "min_prompt_tokens": 32000, - "prompt": "0.00000156", - "completion": "0.0000078" - }, - { - "min_prompt_tokens": 128000, - "prompt": "0.00000195", - "completion": "0.00000975" - } - ] - }, - "top_provider": { - "context_length": 262144, - "max_completion_tokens": 65536, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "include_reasoning", - "logprobs", - "max_tokens", - "presence_penalty", - "reasoning", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_k", - "top_logprobs", - "top_p" - ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": "2026-10-09", - "links": { - "details": "/api/v1/models/qwen/qwen3-max-thinking-20260123/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 21.3, - "coding_index": null, - "agentic_index": null - } - }, - "reasoning": { - "mandatory": false - } - }, { "id": "qwen/qwen3-next-80b-a3b-instruct", "canonical_slug": "qwen/qwen3-next-80b-a3b-instruct-2509", @@ -31434,13 +32092,12 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000001", - "completion": "0.0000011", - "input_cache_read": "0.00000007" + "prompt": "0.00000009", + "completion": "0.0000011" }, "top_provider": { "context_length": 262144, - "max_completion_tokens": 235929, + "max_completion_tokens": 16384, "is_moderated": false }, "per_request_limits": null, @@ -31499,8 +32156,8 @@ "completion": "0.0000012" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": 32768, + "context_length": 262144, + "max_completion_tokens": 235929, "is_moderated": false }, "per_request_limits": null, @@ -31530,7 +32187,7 @@ }, "supported_voices": null, "knowledge_cutoff": "2025-09-30", - "expiration_date": "2026-10-09", + "expiration_date": null, "links": { "details": "/api/v1/models/qwen/qwen3-next-80b-a3b-thinking-2509/endpoints" }, @@ -31611,76 +32268,6 @@ } } }, - { - "id": "qwen/qwen3-vl-235b-a22b-thinking", - "canonical_slug": "qwen/qwen3-vl-235b-a22b-thinking", - "hugging_face_id": "Qwen/Qwen3-VL-235B-A22B-Thinking", - "name": "Qwen: Qwen3 VL 235B A22B Thinking", - "created": 1758668690, - "description": "Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math....", - "context_length": 131072, - "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], - "output_modalities": ["text"], - "tokenizer": "Qwen3", - "instruct_type": null - }, - "pricing": { - "prompt": "0.0000004", - "completion": "0.000004" - }, - "top_provider": { - "context_length": 131072, - "max_completion_tokens": 32768, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "include_reasoning", - "logprobs", - "max_tokens", - "presence_penalty", - "reasoning", - "repetition_penalty", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_k", - "top_logprobs", - "top_p" - ], - "default_parameters": { - "temperature": 0.8, - "top_p": 0.95, - "top_k": 20, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": 1 - }, - "supported_voices": null, - "knowledge_cutoff": "2025-03-31", - "expiration_date": "2026-10-09", - "links": { - "details": "/api/v1/models/qwen/qwen3-vl-235b-a22b-thinking/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 13.4, - "coding_index": null, - "agentic_index": null - } - }, - "reasoning": { - "mandatory": true - } - }, { "id": "qwen/qwen3-vl-30b-a3b-instruct", "canonical_slug": "qwen/qwen3-vl-30b-a3b-instruct", @@ -31764,31 +32351,26 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000002", - "completion": "0.0000024" + "prompt": "0.00000029", + "completion": "0.000001" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": 32768, + "context_length": 262144, + "max_completion_tokens": 235929, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", "include_reasoning", - "logprobs", "max_tokens", - "presence_penalty", "reasoning", "response_format", - "seed", - "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", - "top_logprobs", "top_p" ], "default_parameters": { @@ -31801,7 +32383,7 @@ }, "supported_voices": null, "knowledge_cutoff": "2025-03-31", - "expiration_date": "2026-10-09", + "expiration_date": null, "links": { "details": "/api/v1/models/qwen/qwen3-vl-30b-a3b-thinking/endpoints" }, @@ -31817,70 +32399,6 @@ "mandatory": true } }, - { - "id": "qwen/qwen3-vl-32b-instruct", - "canonical_slug": "qwen/qwen3-vl-32b-instruct", - "hugging_face_id": "Qwen/Qwen3-VL-32B-Instruct", - "name": "Qwen: Qwen3 VL 32B Instruct", - "created": 1761231332, - "description": "Qwen3-VL-32B-Instruct is a large-scale multimodal vision-language model designed for high-precision understanding and reasoning across text, images, and video. With 32 billion parameters, it combines deep visual perception with advanced text...", - "context_length": 131072, - "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], - "output_modalities": ["text"], - "tokenizer": "Qwen", - "instruct_type": null - }, - "pricing": { - "prompt": "0.000000104", - "completion": "0.000000416" - }, - "top_provider": { - "context_length": 131072, - "max_completion_tokens": 32768, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "logprobs", - "max_tokens", - "presence_penalty", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_k", - "top_logprobs", - "top_p" - ], - "default_parameters": { - "temperature": 0.7, - "top_p": 0.8, - "top_k": 20, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": 1 - }, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": "2026-10-09", - "links": { - "details": "/api/v1/models/qwen/qwen3-vl-32b-instruct/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 11.9, - "coding_index": null, - "agentic_index": null - } - } - }, { "id": "qwen/qwen3-vl-8b-instruct", "canonical_slug": "qwen/qwen3-vl-8b-instruct", @@ -31897,12 +32415,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000000117", - "completion": "0.000000455" + "prompt": "0.00000025", + "completion": "0.00000075", + "input_cache_read": "0.00000012" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": 32768, + "context_length": 262144, + "max_completion_tokens": 235929, "is_moderated": false }, "per_request_limits": null, @@ -31931,7 +32450,7 @@ }, "supported_voices": null, "knowledge_cutoff": null, - "expiration_date": "2026-10-09", + "expiration_date": null, "links": { "details": "/api/v1/models/qwen/qwen3-vl-8b-instruct/endpoints" }, @@ -31944,71 +32463,6 @@ } } }, - { - "id": "qwen/qwen3-vl-8b-thinking", - "canonical_slug": "qwen/qwen3-vl-8b-thinking", - "hugging_face_id": "Qwen/Qwen3-VL-8B-Thinking", - "name": "Qwen: Qwen3 VL 8B Thinking", - "created": 1760463746, - "description": "Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, and temporal sequences. It integrates enhanced multimodal alignment and...", - "context_length": 131072, - "architecture": { - "modality": "text+image->text", - "input_modalities": ["image", "text"], - "output_modalities": ["text"], - "tokenizer": "Qwen3", - "instruct_type": null - }, - "pricing": { - "prompt": "0.00000018", - "completion": "0.0000021" - }, - "top_provider": { - "context_length": 131072, - "max_completion_tokens": 32768, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "include_reasoning", - "logprobs", - "max_tokens", - "presence_penalty", - "reasoning", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_k", - "top_logprobs", - "top_p" - ], - "default_parameters": { - "temperature": 1, - "top_p": 0.95 - }, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": "2026-10-09", - "links": { - "details": "/api/v1/models/qwen/qwen3-vl-8b-thinking/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 8.2, - "coding_index": null, - "agentic_index": null - } - }, - "reasoning": { - "mandatory": true - } - }, { "id": "qwen/qwen3.5-122b-a10b", "canonical_slug": "qwen/qwen3.5-122b-a10b-20260224", @@ -32025,8 +32479,8 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000026", - "completion": "0.00000208" + "prompt": "0.0000004", + "completion": "0.0000032" }, "top_provider": { "context_length": 262144, @@ -32097,8 +32551,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000000195", - "completion": "0.00000156" + "prompt": "0.00000027", + "completion": "0.00000216", + "input_cache_read": "0.00000027" }, "top_provider": { "context_length": 262144, @@ -32169,13 +32624,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000015", + "prompt": "0.00000014", "completion": "0.000001", "input_cache_read": "0.00000005" }, "top_provider": { "context_length": 262144, - "max_completion_tokens": 235929, + "max_completion_tokens": 81920, "is_moderated": false }, "per_request_limits": null, @@ -32242,13 +32697,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000045", - "completion": "0.000003", - "input_cache_read": "0.00000022" + "prompt": "0.0000005", + "completion": "0.0000036", + "input_cache_read": "0.0000003" }, "top_provider": { "context_length": 262144, - "max_completion_tokens": 81920, + "max_completion_tokens": 235929, "is_moderated": false }, "per_request_limits": null, @@ -32292,51 +32747,51 @@ { "arena": "models", "category": "3d", - "elo": 1169, + "elo": 1161, "win_rate": 56.7, - "rank": 56 + "rank": 65 }, { "arena": "models", "category": "codecategories", - "elo": 1184, + "elo": 1180, "win_rate": 52.6, - "rank": 58 + "rank": 67 }, { "arena": "models", "category": "dataviz", - "elo": 1182, + "elo": 1175, "win_rate": 53.2, - "rank": 61 + "rank": 69 }, { "arena": "models", "category": "gamedev", - "elo": 1151, + "elo": 1140, "win_rate": 50.2, - "rank": 67 + "rank": 79 }, { "arena": "models", "category": "svg", - "elo": 1139, + "elo": 1140, "win_rate": 56.1, - "rank": 49 + "rank": 50 }, { "arena": "models", "category": "uicomponent", - "elo": 1170, + "elo": 1163, "win_rate": 51.4, - "rank": 68 + "rank": 75 }, { "arena": "models", "category": "website", - "elo": 1197, + "elo": 1191, "win_rate": 52.5, - "rank": 60 + "rank": 69 } ], "artificial_analysis": { @@ -32365,12 +32820,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000001", - "completion": "0.00000015" + "prompt": "0.00000008", + "completion": "0.00000013", + "input_cache_read": "0.00000004" }, "top_provider": { - "context_length": 256000, - "max_completion_tokens": 32768, + "context_length": 262144, + "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, @@ -32543,58 +32999,58 @@ { "arena": "models", "category": "3d", - "elo": 1127, + "elo": 1119, "win_rate": 47.7, - "rank": 77 + "rank": 85 }, { "arena": "models", "category": "asciiart", - "elo": 1102, + "elo": 1094, "win_rate": 43.2, - "rank": 60 + "rank": 62 }, { "arena": "models", "category": "codecategories", - "elo": 1171, + "elo": 1167, "win_rate": 48.4, - "rank": 68 + "rank": 76 }, { "arena": "models", "category": "dataviz", - "elo": 1142, - "win_rate": 44.9, - "rank": 81 + "elo": 1135, + "win_rate": 44.8, + "rank": 88 }, { "arena": "models", "category": "gamedev", - "elo": 1116, + "elo": 1105, "win_rate": 42.6, - "rank": 82 + "rank": 95 }, { "arena": "models", "category": "svg", - "elo": 1107, + "elo": 1108, "win_rate": 48.9, - "rank": 58 + "rank": 59 }, { "arena": "models", "category": "uicomponent", - "elo": 1184, + "elo": 1178, "win_rate": 52.2, - "rank": 60 + "rank": 67 }, { "arena": "models", "category": "website", - "elo": 1194, + "elo": 1187, "win_rate": 50, - "rank": 62 + "rank": 73 } ] }, @@ -32681,9 +33137,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000003", + "prompt": "0.00000025", "completion": "0.000002", - "input_cache_read": "0.00000003" + "input_cache_read": "0.000000025" }, "top_provider": { "context_length": 262144, @@ -32755,8 +33211,8 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000015", - "completion": "0.000001", + "prompt": "0.0000001", + "completion": "0.00000095", "input_cache_read": "0.00000005" }, "top_provider": { @@ -32873,78 +33329,6 @@ "mandatory": false } }, - { - "id": "qwen/qwen3.6-max-preview", - "canonical_slug": "qwen/qwen3.6-max-preview-20260420", - "hugging_face_id": null, - "name": "Qwen: Qwen3.6 Max Preview", - "created": 1777260242, - "description": "Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic coding, tool use, and...", - "context_length": 262144, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Qwen", - "instruct_type": null - }, - "pricing": { - "prompt": "0.000001027", - "completion": "0.000006162", - "input_cache_write": "0.00000128375", - "overrides": [ - { - "min_prompt_tokens": 128000, - "prompt": "0.00000158", - "completion": "0.00000948", - "input_cache_write": "0.000001975" - } - ] - }, - "top_provider": { - "context_length": 262144, - "max_completion_tokens": 65536, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "include_reasoning", - "logprobs", - "max_tokens", - "presence_penalty", - "reasoning", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_k", - "top_logprobs", - "top_p" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": "2026-10-09", - "links": { - "details": "/api/v1/models/qwen/qwen3.6-max-preview-20260420/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 28.4, - "coding_index": null, - "agentic_index": null - } - }, - "reasoning": { - "mandatory": false, - "default_enabled": true - } - }, { "id": "qwen/qwen3.6-plus", "canonical_slug": "qwen/qwen3.6-plus-04-02", @@ -33016,58 +33400,58 @@ { "arena": "models", "category": "3d", - "elo": 1210, - "win_rate": 50.7, - "rank": 42 + "elo": 1202, + "win_rate": 50.5, + "rank": 49 }, { "arena": "models", "category": "asciiart", - "elo": 1124, - "win_rate": 41.7, - "rank": 55 + "elo": 1113, + "win_rate": 40.9, + "rank": 57 }, { "arena": "models", "category": "codecategories", - "elo": 1240, - "win_rate": 50.5, - "rank": 39 + "elo": 1236, + "win_rate": 50.2, + "rank": 48 }, { "arena": "models", "category": "dataviz", - "elo": 1235, - "win_rate": 50.9, - "rank": 39 + "elo": 1228, + "win_rate": 50.8, + "rank": 47 }, { "arena": "models", "category": "gamedev", - "elo": 1222, - "win_rate": 49.1, - "rank": 41 + "elo": 1211, + "win_rate": 48.5, + "rank": 51 }, { "arena": "models", "category": "svg", - "elo": 1161, - "win_rate": 50.6, - "rank": 39 + "elo": 1162, + "win_rate": 50.3, + "rank": 40 }, { "arena": "models", "category": "uicomponent", - "elo": 1238, - "win_rate": 50.8, - "rank": 42 + "elo": 1233, + "win_rate": 50.5, + "rank": 49 }, { "arena": "models", "category": "website", - "elo": 1247, - "win_rate": 50.4, - "rank": 40 + "elo": 1243, + "win_rate": 50.1, + "rank": 49 } ], "artificial_analysis": { @@ -33222,21 +33606,21 @@ "arena": "agents", "category": "agenticgamedev", "elo": 1161, - "win_rate": 46.6, + "win_rate": 46.2, "rank": 18 }, { "arena": "agents", "category": "androidnative", - "elo": 1174, - "win_rate": 48.9, - "rank": 22 + "elo": 1159, + "win_rate": 48.5, + "rank": 23 }, { "arena": "agents", "category": "fullstack", - "elo": 1188, - "win_rate": 47.6, + "elo": 1191, + "win_rate": 47.7, "rank": 20 }, { @@ -33256,79 +33640,79 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1147, - "win_rate": 44.8, - "rank": 27 + "elo": 1155, + "win_rate": 45.2, + "rank": 29 }, { "arena": "agents", "category": "python-pptxslides", "elo": 1194, - "win_rate": 47.2, - "rank": 17 + "win_rate": 47.7, + "rank": 16 }, { "arena": "agents", "category": "webapps", - "elo": 1202, - "win_rate": 49.4, - "rank": 17 + "elo": 1208, + "win_rate": 48.8, + "rank": 20 }, { "arena": "models", "category": "3d", - "elo": 1275, - "win_rate": 54.8, - "rank": 20 + "elo": 1266, + "win_rate": 54.5, + "rank": 27 }, { "arena": "models", "category": "asciiart", - "elo": 1222, - "win_rate": 53.4, - "rank": 19 + "elo": 1211, + "win_rate": 53.2, + "rank": 20 }, { "arena": "models", "category": "codecategories", - "elo": 1281, - "win_rate": 54.4, - "rank": 20 + "elo": 1275, + "win_rate": 54, + "rank": 27 }, { "arena": "models", "category": "dataviz", - "elo": 1283, - "win_rate": 53.1, - "rank": 18 + "elo": 1275, + "win_rate": 52.9, + "rank": 25 }, { "arena": "models", "category": "gamedev", - "elo": 1277, - "win_rate": 53.6, - "rank": 21 + "elo": 1265, + "win_rate": 53, + "rank": 29 }, { "arena": "models", "category": "svg", - "elo": 1216, - "win_rate": 55.5, - "rank": 21 + "elo": 1217, + "win_rate": 55.4, + "rank": 20 }, { "arena": "models", "category": "uicomponent", - "elo": 1276, - "win_rate": 53.6, - "rank": 27 + "elo": 1270, + "win_rate": 53.3, + "rank": 33 }, { "arena": "models", "category": "website", - "elo": 1279, - "win_rate": 54.8, - "rank": 22 + "elo": 1274, + "win_rate": 54.4, + "rank": 27 } ], "artificial_analysis": { @@ -33408,58 +33792,178 @@ { "arena": "models", "category": "3d", - "elo": 1245, + "elo": 1239, "win_rate": 48.5, - "rank": 31 + "rank": 38 }, { "arena": "models", "category": "asciiart", - "elo": 1152, - "win_rate": 41.6, - "rank": 44 + "elo": 1143, + "win_rate": 41.8, + "rank": 46 }, { "arena": "models", "category": "codecategories", - "elo": 1273, - "win_rate": 50.5, - "rank": 25 + "elo": 1269, + "win_rate": 50.3, + "rank": 31 }, { "arena": "models", "category": "dataviz", - "elo": 1283, - "win_rate": 51.3, - "rank": 19 + "elo": 1276, + "win_rate": 51.1, + "rank": 23 }, { "arena": "models", "category": "gamedev", - "elo": 1271, - "win_rate": 49.7, - "rank": 27 + "elo": 1262, + "win_rate": 49.5, + "rank": 35 }, { "arena": "models", "category": "svg", - "elo": 1209, - "win_rate": 46.8, - "rank": 22 + "elo": 1208, + "win_rate": 46.7, + "rank": 23 }, { "arena": "models", "category": "uicomponent", - "elo": 1266, - "win_rate": 49.1, - "rank": 31 + "elo": 1261, + "win_rate": 48.9, + "rank": 37 }, { "arena": "models", "category": "website", + "elo": 1269, + "win_rate": 50.5, + "rank": 31 + } + ], + "artificial_analysis": { + "intelligence_index": 25.2, + "coding_index": 55.9, + "agentic_index": 17.5 + } + }, + "reasoning": { + "mandatory": false, + "default_enabled": true + } + }, + { + "id": "qwen/qwen3.7-plus:batch", + "canonical_slug": "qwen/qwen3.7-plus-20260602", + "hugging_face_id": null, + "name": "Qwen: Qwen3.7 Plus (batch)", + "created": 1780491783, + "description": "Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...", + "context_length": 262144, + "architecture": { + "modality": "text+image->text", + "input_modalities": ["text", "image"], + "output_modalities": ["text"], + "tokenizer": "Qwen", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000023", + "completion": "0.00000092" + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 131072, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logprobs", + "max_tokens", + "presence_penalty", + "reasoning", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/qwen/qwen3.7-plus-20260602/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1239, + "win_rate": 48.5, + "rank": 38 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1143, + "win_rate": 41.8, + "rank": 46 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1269, + "win_rate": 50.3, + "rank": 31 + }, + { + "arena": "models", + "category": "dataviz", "elo": 1276, - "win_rate": 51, - "rank": 24 + "win_rate": 51.1, + "rank": 23 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1262, + "win_rate": 49.5, + "rank": 35 + }, + { + "arena": "models", + "category": "svg", + "elo": 1208, + "win_rate": 46.7, + "rank": 23 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1261, + "win_rate": 48.9, + "rank": 37 + }, + { + "arena": "models", + "category": "website", + "elo": 1269, + "win_rate": 50.5, + "rank": 31 } ], "artificial_analysis": { @@ -33494,8 +33998,8 @@ "input_cache_read": "0.00000025" }, "top_provider": { - "context_length": 1000000, - "max_completion_tokens": 131072, + "context_length": 1010000, + "max_completion_tokens": 909000, "is_moderated": false }, "per_request_limits": null, @@ -33563,14 +34067,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000000425", - "completion": "0.00000255", - "input_cache_read": "0.000000085", - "input_cache_write": "0.00000053125" + "prompt": "0.00000004", + "completion": "0.00000135", + "input_cache_read": "0.000000018" }, "top_provider": { - "context_length": 1000000, - "max_completion_tokens": 131072, + "context_length": 262144, + "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, @@ -33619,7 +34122,7 @@ "reasoning": { "mandatory": false, "default_enabled": true, - "supported_efforts": ["xhigh", "medium", "low"], + "supported_efforts": ["xhigh", "medium", "low", "none"], "default_effort": "xhigh" } }, @@ -33641,8 +34144,7 @@ "pricing": { "prompt": "0.00000015", "completion": "0.00000047", - "input_cache_read": "0.000000016", - "input_cache_write": "0.0000002" + "input_cache_read": "0.000000016" }, "top_provider": { "context_length": 1000000, @@ -33699,8 +34201,7 @@ "pricing": { "prompt": "0.000002", "completion": "0.000006", - "input_cache_read": "0.00000025", - "input_cache_write": "0.0000025" + "input_cache_read": "0.00000025" }, "top_provider": { "context_length": 1000000, @@ -33865,6 +34366,134 @@ "supports_max_tokens": true } }, + { + "id": "recursive/flint-v1.0:free", + "canonical_slug": "recursive/flint-v1.0-20261021", + "hugging_face_id": "RecursiveSI/flint", + "name": "Recursive: Flint (free)", + "created": 1792622765, + "description": "Flint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch system Eureka Machine for coding agents. It is suited...", + "context_length": 262144, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0", + "completion": "0" + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 235929, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "logprobs", + "max_tokens", + "reasoning", + "response_format", + "seed", + "stop", + "temperature", + "tools", + "top_logprobs", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/recursive/flint-v1.0-20261021/endpoints" + }, + "reasoning": { + "mandatory": true + } + }, + { + "id": "reflection/beam-1.0-501b-a23b", + "canonical_slug": "reflection/beam-1.0-501b-a23b-20261016", + "hugging_face_id": "reflection/Beam-1.0-501B-A23B", + "name": "Reflection: Beam 1.0 501B A23B", + "created": 1792160499, + "description": "Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...", + "context_length": 1048576, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000003", + "completion": "0.000001", + "input_cache_read": "0.00000004" + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 943718, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "reasoning_effort", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2026-06-30", + "expiration_date": null, + "links": { + "details": "/api/v1/models/reflection/beam-1.0-501b-a23b-20261016/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "gamedev", + "elo": 1224, + "win_rate": 44, + "rank": 47 + }, + { + "arena": "models", + "category": "website", + "elo": 1250, + "win_rate": 46.1, + "rank": 44 + } + ] + }, + "reasoning": { + "mandatory": true, + "supported_efforts": ["max", "xhigh", "high", "medium", "low"], + "default_effort": "max" + } + }, { "id": "rekaai/reka-edge", "canonical_slug": "rekaai/reka-edge-2603", @@ -34397,8 +35026,6 @@ "stop", "structured_outputs", "temperature", - "tool_choice", - "tools", "top_k", "top_p" ], @@ -34411,50 +35038,71 @@ } }, { - "id": "sao10k/l3.3-euryale-70b", - "canonical_slug": "sao10k/l3.3-euryale-70b-v2.3", - "hugging_face_id": "Sao10K/L3.3-70B-Euryale-v2.3", - "name": "Sao10K: Llama 3.3 Euryale 70B", - "created": 1734535928, - "description": "Euryale L3.3 70B is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.2](/models/sao10k/l3-euryale-70b).", - "context_length": 131072, + "id": "scaledown/extract", + "canonical_slug": "scaledown/extract-20260928", + "hugging_face_id": null, + "name": "ScaleDown: Extract", + "created": 1791893351, + "description": "Extract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want in plain English through `provider.options.scaledown.entities`, and the...", + "context_length": 1000000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], - "tokenizer": "Llama3", - "instruct_type": "llama3" + "tokenizer": "Other", + "instruct_type": null }, "pricing": { - "prompt": "0.00000065", - "completion": "0.00000075" + "prompt": "0.00000004", + "completion": "0" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": 16384, + "context_length": 1000000, + "max_completion_tokens": 900000, "is_moderated": false }, "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "logprobs", - "max_tokens", - "presence_penalty", - "repetition_penalty", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "top_logprobs", - "top_p" - ], + "supported_parameters": ["max_tokens"], "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2023-12-31", + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/scaledown/extract-20260928/endpoints" + } + }, + { + "id": "scaledown/summarize", + "canonical_slug": "scaledown/summarize-20260928", + "hugging_face_id": null, + "name": "ScaleDown: Summarize", + "created": 1791893360, + "description": "Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited for...", + "context_length": 1000000, + "architecture": { + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000004", + "completion": "0" + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 4000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": ["max_tokens"], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/sao10k/l3.3-euryale-70b-v2.3/endpoints" + "details": "/api/v1/models/scaledown/summarize-20260928/endpoints" } }, { @@ -34584,58 +35232,58 @@ { "arena": "models", "category": "3d", - "elo": 1136, - "win_rate": 40.6, - "rank": 70 + "elo": 1129, + "win_rate": 40.4, + "rank": 79 }, { "arena": "models", "category": "asciiart", - "elo": 1160, + "elo": 1153, "win_rate": 45, - "rank": 39 + "rank": 41 }, { "arena": "models", "category": "codecategories", - "elo": 1186, - "win_rate": 42.7, - "rank": 57 + "elo": 1182, + "win_rate": 42.3, + "rank": 66 }, { "arena": "models", "category": "dataviz", - "elo": 1178, - "win_rate": 43.1, - "rank": 64 + "elo": 1172, + "win_rate": 42.9, + "rank": 71 }, { "arena": "models", "category": "gamedev", - "elo": 1169, - "win_rate": 39, - "rank": 63 + "elo": 1158, + "win_rate": 38.4, + "rank": 74 }, { "arena": "models", "category": "svg", - "elo": 1081, - "win_rate": 37.2, + "elo": 1085, + "win_rate": 37.3, "rank": 64 }, { "arena": "models", "category": "uicomponent", - "elo": 1186, - "win_rate": 42.3, - "rank": 59 + "elo": 1179, + "win_rate": 41.9, + "rank": 66 }, { "arena": "models", "category": "website", - "elo": 1200, - "win_rate": 44.3, - "rank": 58 + "elo": 1196, + "win_rate": 43.9, + "rank": 66 } ], "artificial_analysis": { @@ -34650,6 +35298,82 @@ "default_effort": "medium" } }, + { + "id": "stepfun/step-5-preview", + "canonical_slug": "stepfun/step-5-preview-20261008", + "hugging_face_id": "stepfun-ai/Step-5-Preview", + "name": "StepFun: Step 5 Preview", + "created": 1791462849, + "description": "Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional...", + "context_length": 1048576, + "architecture": { + "modality": "text+image+video->text", + "input_modalities": ["text", "image", "video"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.000001", + "completion": "0.0000027", + "input_cache_read": "0.0000001" + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 64000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "reasoning_effort", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/stepfun/step-5-preview-20261008/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 43.7, + "coding_index": null, + "agentic_index": null + } + }, + "reasoning": { + "mandatory": true, + "supported_efforts": ["high", "medium", "low"], + "default_effort": "medium" + } + }, { "id": "tencent/hunyuan-a13b-instruct", "canonical_slug": "tencent/hunyuan-a13b-instruct", @@ -34900,44 +35624,44 @@ { "arena": "models", "category": "3d", - "elo": 1184, - "win_rate": 43.9, - "rank": 51 + "elo": 1176, + "win_rate": 44, + "rank": 58 }, { "arena": "models", "category": "codecategories", - "elo": 1181, - "win_rate": 41.1, - "rank": 60 + "elo": 1177, + "win_rate": 41.2, + "rank": 69 }, { "arena": "models", "category": "dataviz", - "elo": 1132, + "elo": 1125, "win_rate": 36.1, - "rank": 85 + "rank": 93 }, { "arena": "models", "category": "gamedev", - "elo": 1147, + "elo": 1136, "win_rate": 38.6, - "rank": 71 + "rank": 83 }, { "arena": "models", "category": "uicomponent", - "elo": 1170, + "elo": 1164, "win_rate": 40.2, - "rank": 67 + "rank": 74 }, { "arena": "models", "category": "website", - "elo": 1187, + "elo": 1182, "win_rate": 41.3, - "rank": 66 + "rank": 75 } ] }, @@ -35303,61 +36027,68 @@ }, "benchmarks": { "design_arena": [ + { + "arena": "agents", + "category": "webapps", + "elo": 1196, + "win_rate": 48.6, + "rank": 26 + }, { "arena": "models", "category": "3d", - "elo": 1166, - "win_rate": 39.9, - "rank": 57 + "elo": 1161, + "win_rate": 40, + "rank": 64 }, { "arena": "models", "category": "asciiart", - "elo": 1099, - "win_rate": 34, - "rank": 61 + "elo": 1089, + "win_rate": 33.6, + "rank": 64 }, { "arena": "models", "category": "codecategories", - "elo": 1209, - "win_rate": 42.1, - "rank": 50 + "elo": 1206, + "win_rate": 42.2, + "rank": 58 }, { "arena": "models", "category": "dataviz", - "elo": 1171, - "win_rate": 37.9, - "rank": 68 + "elo": 1159, + "win_rate": 37.5, + "rank": 78 }, { "arena": "models", "category": "gamedev", - "elo": 1174, - "win_rate": 37.7, - "rank": 61 + "elo": 1166, + "win_rate": 38, + "rank": 71 }, { "arena": "models", "category": "svg", - "elo": 1114, - "win_rate": 34, - "rank": 56 + "elo": 1110, + "win_rate": 34.6, + "rank": 57 }, { "arena": "models", "category": "uicomponent", - "elo": 1204, - "win_rate": 40.9, - "rank": 53 + "elo": 1201, + "win_rate": 40.5, + "rank": 58 }, { "arena": "models", "category": "website", - "elo": 1228, - "win_rate": 44.3, - "rank": 48 + "elo": 1224, + "win_rate": 44.6, + "rank": 57 } ], "artificial_analysis": { @@ -35567,61 +36298,68 @@ }, "benchmarks": { "design_arena": [ + { + "arena": "agents", + "category": "webapps", + "elo": 1196, + "win_rate": 48.6, + "rank": 26 + }, { "arena": "models", "category": "3d", - "elo": 1166, - "win_rate": 39.9, - "rank": 57 + "elo": 1161, + "win_rate": 40, + "rank": 64 }, { "arena": "models", "category": "asciiart", - "elo": 1099, - "win_rate": 34, - "rank": 61 + "elo": 1089, + "win_rate": 33.6, + "rank": 64 }, { "arena": "models", "category": "codecategories", - "elo": 1209, - "win_rate": 42.1, - "rank": 50 + "elo": 1206, + "win_rate": 42.2, + "rank": 58 }, { "arena": "models", "category": "dataviz", - "elo": 1171, - "win_rate": 37.9, - "rank": 68 + "elo": 1159, + "win_rate": 37.5, + "rank": 78 }, { "arena": "models", "category": "gamedev", - "elo": 1174, - "win_rate": 37.7, - "rank": 61 + "elo": 1166, + "win_rate": 38, + "rank": 71 }, { "arena": "models", "category": "svg", - "elo": 1114, - "win_rate": 34, - "rank": 56 + "elo": 1110, + "win_rate": 34.6, + "rank": 57 }, { "arena": "models", "category": "uicomponent", - "elo": 1204, - "win_rate": 40.9, - "rank": 53 + "elo": 1201, + "win_rate": 40.5, + "rank": 58 }, { "arena": "models", "category": "website", - "elo": 1228, - "win_rate": 44.3, - "rank": 48 + "elo": 1224, + "win_rate": 44.6, + "rank": 57 } ], "artificial_analysis": { @@ -35638,13 +36376,13 @@ } }, { - "id": "unbiased/pareto", - "canonical_slug": "unbiased/pareto-20260917", + "id": "unbiased/pareto-26.10", + "canonical_slug": "unbiased/pareto-26.10-20261015", "hugging_face_id": null, - "name": "Pareto", - "created": 1789686178, + "name": "Pareto 26.10", + "created": 1792073620, "description": "Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.", - "context_length": 262144, + "context_length": 1048576, "architecture": { "modality": "text+image->text", "input_modalities": ["text", "image"], @@ -35653,19 +36391,18 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000025", - "completion": "0.0000075", - "input_cache_read": "0.00000025" + "prompt": "0.0000008", + "completion": "0.0000032", + "input_cache_read": "0.00000003" }, "top_provider": { - "context_length": 262144, + "context_length": 1048576, "max_completion_tokens": 131072, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "max_tokens", - "response_format", "temperature", "tool_choice", "tools", @@ -35676,17 +36413,17 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/unbiased/pareto-20260917/endpoints" + "details": "/api/v1/models/unbiased/pareto-26.10-20261015/endpoints" } }, { - "id": "unbiased/pareto-26.10-preview", - "canonical_slug": "unbiased/pareto-26.10-preview-20260929", + "id": "unbiased/pareto-26.9", + "canonical_slug": "unbiased/pareto-26.9-20260917", "hugging_face_id": null, - "name": "Pareto 26.10 Preview", - "created": 1790863623, - "description": "Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks. This is a preview of the...", - "context_length": 1048576, + "name": "Pareto 26.9", + "created": 1791930537, + "description": "Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.", + "context_length": 262144, "architecture": { "modality": "text+image->text", "input_modalities": ["text", "image"], @@ -35695,18 +36432,19 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000008", - "completion": "0.0000032", - "input_cache_read": "0.00000003" + "prompt": "0.0000025", + "completion": "0.0000075", + "input_cache_read": "0.00000025" }, "top_provider": { - "context_length": 1048576, + "context_length": 262144, "max_completion_tokens": 131072, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "max_tokens", + "response_format", "temperature", "tool_choice", "tools", @@ -35717,7 +36455,7 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/unbiased/pareto-26.10-preview-20260929/endpoints" + "details": "/api/v1/models/unbiased/pareto-26.9-20260917/endpoints" } }, { @@ -35820,7 +36558,29 @@ "details": "/api/v1/models/upstage/solar-mini4-20260922/endpoints" }, "benchmarks": { - "design_arena": [], + "design_arena": [ + { + "arena": "models", + "category": "codecategories", + "elo": 1151, + "win_rate": 32, + "rank": 85 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1110, + "win_rate": 28.4, + "rank": 94 + }, + { + "arena": "models", + "category": "website", + "elo": 1159, + "win_rate": 33.3, + "rank": 90 + } + ], "artificial_analysis": { "intelligence_index": 24.1, "coding_index": null, @@ -35928,9 +36688,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000009", - "completion": "0.00000036", - "input_cache_read": "0.000000018" + "prompt": "0.00000015", + "completion": "0.0000006", + "input_cache_read": "0.00000003" }, "top_provider": { "context_length": 524288, @@ -35965,51 +36725,51 @@ { "arena": "agents", "category": "webapps", - "elo": 1098, + "elo": 1105, "win_rate": 30, - "rank": 34 + "rank": 38 }, { "arena": "models", "category": "3d", - "elo": 1186, + "elo": 1178, "win_rate": 46.4, - "rank": 50 + "rank": 57 }, { "arena": "models", "category": "codecategories", - "elo": 1187, + "elo": 1182, "win_rate": 39, - "rank": 56 + "rank": 65 }, { "arena": "models", "category": "dataviz", - "elo": 1184, + "elo": 1177, "win_rate": 41.3, - "rank": 60 + "rank": 68 }, { "arena": "models", "category": "gamedev", - "elo": 1181, + "elo": 1170, "win_rate": 39.9, - "rank": 58 + "rank": 68 }, { "arena": "models", "category": "uicomponent", - "elo": 1156, + "elo": 1150, "win_rate": 35.5, - "rank": 71 + "rank": 77 }, { "arena": "models", "category": "website", - "elo": 1183, + "elo": 1176, "win_rate": 37.5, - "rank": 69 + "rank": 78 } ], "artificial_analysis": { @@ -36145,14 +36905,14 @@ { "arena": "agents", "category": "androidnative", - "elo": 1060, + "elo": 1045, "win_rate": 35, - "rank": 35 + "rank": 36 }, { "arena": "agents", "category": "fullstack", - "elo": 1052, + "elo": 1054, "win_rate": 41.1, "rank": 34 }, @@ -36173,72 +36933,72 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1086, + "elo": 1090, "win_rate": 45.4, - "rank": 41 + "rank": 43 }, { "arena": "agents", "category": "webapps", - "elo": 1137, + "elo": 1144, "win_rate": 49.7, - "rank": 27 + "rank": 31 }, { "arena": "models", "category": "3d", - "elo": 1201, + "elo": 1193, "win_rate": 52.1, - "rank": 45 + "rank": 52 }, { "arena": "models", "category": "asciiart", - "elo": 1183, + "elo": 1175, "win_rate": 48.2, - "rank": 28 + "rank": 30 }, { "arena": "models", "category": "codecategories", - "elo": 1225, + "elo": 1221, "win_rate": 51.8, - "rank": 45 + "rank": 54 }, { "arena": "models", "category": "dataviz", - "elo": 1223, + "elo": 1217, "win_rate": 52, - "rank": 47 + "rank": 53 }, { "arena": "models", "category": "gamedev", - "elo": 1203, + "elo": 1193, "win_rate": 50.1, - "rank": 49 + "rank": 60 }, { "arena": "models", "category": "svg", - "elo": 1164, + "elo": 1165, "win_rate": 52.4, - "rank": 37 + "rank": 38 }, { "arena": "models", "category": "uicomponent", - "elo": 1206, + "elo": 1200, "win_rate": 49, - "rank": 52 + "rank": 59 }, { "arena": "models", "category": "website", - "elo": 1236, + "elo": 1229, "win_rate": 51.8, - "rank": 46 + "rank": 55 } ], "artificial_analysis": { @@ -36391,7 +37151,7 @@ "arena": "agents", "category": "agenticgamedev", "elo": 1007, - "win_rate": 28.8, + "win_rate": 28.7, "rank": 24 }, { @@ -36425,15 +37185,15 @@ { "arena": "agents", "category": "androidnative", - "elo": 975, + "elo": 962, "win_rate": 22.7, - "rank": 37 + "rank": 38 }, { "arena": "agents", "category": "fullstack", - "elo": 1004, - "win_rate": 28, + "elo": 1006, + "win_rate": 28.1, "rank": 40 }, { @@ -36446,16 +37206,16 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1008, + "elo": 1009, "win_rate": 28.4, "rank": 23 }, { "arena": "agents", "category": "mobileapps", - "elo": 1055, + "elo": 1059, "win_rate": 33.6, - "rank": 43 + "rank": 45 }, { "arena": "agents", @@ -36474,65 +37234,65 @@ { "arena": "agents", "category": "webapps", - "elo": 1120, - "win_rate": 43.3, - "rank": 29 + "elo": 1126, + "win_rate": 42.8, + "rank": 33 }, { "arena": "models", "category": "3d", - "elo": 1133, - "win_rate": 41.2, - "rank": 71 + "elo": 1125, + "win_rate": 40.8, + "rank": 82 }, { "arena": "models", "category": "asciiart", - "elo": 1136, - "win_rate": 43.1, - "rank": 50 + "elo": 1125, + "win_rate": 42.6, + "rank": 54 }, { "arena": "models", "category": "codecategories", - "elo": 1192, - "win_rate": 44.2, - "rank": 54 + "elo": 1187, + "win_rate": 43.7, + "rank": 63 }, { "arena": "models", "category": "dataviz", - "elo": 1187, - "win_rate": 45.4, - "rank": 59 + "elo": 1179, + "win_rate": 45, + "rank": 66 }, { "arena": "models", "category": "gamedev", - "elo": 1186, - "win_rate": 44.1, - "rank": 55 + "elo": 1174, + "win_rate": 43.1, + "rank": 65 }, { "arena": "models", "category": "svg", "elo": 1081, - "win_rate": 37.4, - "rank": 63 + "win_rate": 37, + "rank": 65 }, { "arena": "models", "category": "uicomponent", - "elo": 1199, - "win_rate": 45.3, - "rank": 54 + "elo": 1193, + "win_rate": 44.9, + "rank": 62 }, { "arena": "models", "category": "website", - "elo": 1201, - "win_rate": 44.6, - "rank": 57 + "elo": 1196, + "win_rate": 44.1, + "rank": 65 } ], "artificial_analysis": { @@ -36618,7 +37378,7 @@ "arena": "agents", "category": "agenticgamedev", "elo": 1007, - "win_rate": 28.8, + "win_rate": 28.7, "rank": 24 }, { @@ -36652,15 +37412,15 @@ { "arena": "agents", "category": "androidnative", - "elo": 975, + "elo": 962, "win_rate": 22.7, - "rank": 37 + "rank": 38 }, { "arena": "agents", "category": "fullstack", - "elo": 1004, - "win_rate": 28, + "elo": 1006, + "win_rate": 28.1, "rank": 40 }, { @@ -36673,16 +37433,16 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1008, + "elo": 1009, "win_rate": 28.4, "rank": 23 }, { "arena": "agents", "category": "mobileapps", - "elo": 1055, + "elo": 1059, "win_rate": 33.6, - "rank": 43 + "rank": 45 }, { "arena": "agents", @@ -36701,65 +37461,65 @@ { "arena": "agents", "category": "webapps", - "elo": 1120, - "win_rate": 43.3, - "rank": 29 + "elo": 1126, + "win_rate": 42.8, + "rank": 33 }, { "arena": "models", "category": "3d", - "elo": 1133, - "win_rate": 41.2, - "rank": 71 + "elo": 1125, + "win_rate": 40.8, + "rank": 82 }, { "arena": "models", "category": "asciiart", - "elo": 1136, - "win_rate": 43.1, - "rank": 50 + "elo": 1125, + "win_rate": 42.6, + "rank": 54 }, { "arena": "models", "category": "codecategories", - "elo": 1192, - "win_rate": 44.2, - "rank": 54 + "elo": 1187, + "win_rate": 43.7, + "rank": 63 }, { "arena": "models", "category": "dataviz", - "elo": 1187, - "win_rate": 45.4, - "rank": 59 + "elo": 1179, + "win_rate": 45, + "rank": 66 }, { "arena": "models", "category": "gamedev", - "elo": 1186, - "win_rate": 44.1, - "rank": 55 + "elo": 1174, + "win_rate": 43.1, + "rank": 65 }, { "arena": "models", "category": "svg", "elo": 1081, - "win_rate": 37.4, - "rank": 63 + "win_rate": 37, + "rank": 65 }, { "arena": "models", "category": "uicomponent", - "elo": 1199, - "win_rate": 45.3, - "rank": 54 + "elo": 1193, + "win_rate": 44.9, + "rank": 62 }, { "arena": "models", "category": "website", - "elo": 1201, - "win_rate": 44.6, - "rank": 57 + "elo": 1196, + "win_rate": 44.1, + "rank": 65 } ], "artificial_analysis": { @@ -36837,114 +37597,114 @@ { "arena": "agents", "category": "agenticgamedev", - "elo": 1235, - "win_rate": 55.9, - "rank": 6 + "elo": 1236, + "win_rate": 56, + "rank": 5 }, { "arena": "agents", "category": "androidnative", - "elo": 1250, - "win_rate": 64, + "elo": 1236, + "win_rate": 63.8, "rank": 7 }, { "arena": "agents", "category": "fullstack", - "elo": 1247, + "elo": 1249, "win_rate": 60.7, "rank": 10 }, { "arena": "agents", "category": "godotgamedev", - "elo": 1228, + "elo": 1229, "win_rate": 58.2, "rank": 11 }, { "arena": "agents", "category": "htmlslides", - "elo": 1204, + "elo": 1205, "win_rate": 52.5, "rank": 6 }, { "arena": "agents", "category": "mobileapps", - "elo": 1216, - "win_rate": 53, + "elo": 1220, + "win_rate": 52.8, "rank": 12 }, { "arena": "agents", "category": "python-pptxslides", "elo": 1230, - "win_rate": 53.9, + "win_rate": 54.2, "rank": 12 }, { "arena": "agents", "category": "webapps", - "elo": 1209, - "win_rate": 53.5, - "rank": 16 + "elo": 1218, + "win_rate": 53.4, + "rank": 19 }, { "arena": "models", "category": "3d", - "elo": 1266, - "win_rate": 50.4, - "rank": 23 + "elo": 1257, + "win_rate": 50.2, + "rank": 30 }, { "arena": "models", "category": "asciiart", - "elo": 1262, - "win_rate": 54.6, - "rank": 16 + "elo": 1256, + "win_rate": 54.4, + "rank": 14 }, { "arena": "models", "category": "codecategories", - "elo": 1281, - "win_rate": 51, - "rank": 21 + "elo": 1275, + "win_rate": 50.9, + "rank": 28 }, { "arena": "models", "category": "dataviz", - "elo": 1272, - "win_rate": 49.6, - "rank": 22 + "elo": 1266, + "win_rate": 49.7, + "rank": 28 }, { "arena": "models", "category": "gamedev", - "elo": 1272, - "win_rate": 49.2, - "rank": 26 + "elo": 1264, + "win_rate": 49.4, + "rank": 31 }, { "arena": "models", "category": "svg", - "elo": 1220, - "win_rate": 48.7, - "rank": 18 + "elo": 1215, + "win_rate": 48.1, + "rank": 22 }, { "arena": "models", "category": "uicomponent", - "elo": 1286, - "win_rate": 51.6, - "rank": 23 + "elo": 1280, + "win_rate": 51.5, + "rank": 28 }, { "arena": "models", "category": "website", - "elo": 1287, - "win_rate": 52.8, - "rank": 19 + "elo": 1281, + "win_rate": 52.4, + "rank": 24 } ], "artificial_analysis": { @@ -37024,21 +37784,21 @@ { "arena": "agents", "category": "agenticgamedev", - "elo": 1210, - "win_rate": 47.1, + "elo": 1209, + "win_rate": 46.8, "rank": 9 }, { "arena": "agents", "category": "androidnative", - "elo": 1303, - "win_rate": 61.3, + "elo": 1291, + "win_rate": 61.4, "rank": 1 }, { "arena": "agents", "category": "fullstack", - "elo": 1263, + "elo": 1264, "win_rate": 54.9, "rank": 7 }, @@ -37052,86 +37812,86 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1249, + "elo": 1250, "win_rate": 60.1, "rank": 3 }, { "arena": "agents", "category": "mobileapps", - "elo": 1233, - "win_rate": 55.8, - "rank": 7 + "elo": 1234, + "win_rate": 55.6, + "rank": 8 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1242, - "win_rate": 52.7, + "elo": 1237, + "win_rate": 52.6, "rank": 11 }, { "arena": "agents", "category": "webapps", - "elo": 1241, - "win_rate": 56, - "rank": 9 + "elo": 1248, + "win_rate": 55.8, + "rank": 12 }, { "arena": "models", "category": "3d", - "elo": 1285, - "win_rate": 52.5, - "rank": 16 + "elo": 1277, + "win_rate": 52.4, + "rank": 22 }, { "arena": "models", "category": "asciiart", - "elo": 1286, - "win_rate": 58.1, - "rank": 9 + "elo": 1279, + "win_rate": 58.3, + "rank": 7 }, { "arena": "models", "category": "codecategories", - "elo": 1297, - "win_rate": 52.6, - "rank": 13 + "elo": 1292, + "win_rate": 52.5, + "rank": 18 }, { "arena": "models", "category": "dataviz", - "elo": 1289, + "elo": 1282, "win_rate": 51.4, - "rank": 15 + "rank": 19 }, { "arena": "models", "category": "gamedev", - "elo": 1305, - "win_rate": 54.2, - "rank": 14 + "elo": 1296, + "win_rate": 54, + "rank": 20 }, { "arena": "models", "category": "svg", - "elo": 1241, - "win_rate": 48.9, + "elo": 1240, + "win_rate": 48.8, "rank": 14 }, { "arena": "models", "category": "uicomponent", - "elo": 1298, - "win_rate": 53.1, - "rank": 17 + "elo": 1294, + "win_rate": 53.3, + "rank": 21 }, { "arena": "models", "category": "website", - "elo": 1296, - "win_rate": 52.5, - "rank": 15 + "elo": 1289, + "win_rate": 52.2, + "rank": 21 } ], "artificial_analysis": { @@ -37212,37 +37972,44 @@ { "arena": "models", "category": "3d", - "elo": 1261, - "win_rate": 46.5, + "elo": 1271, + "win_rate": 47.7, "rank": 25 }, + { + "arena": "models", + "category": "codecategories", + "elo": 1271, + "win_rate": 47.7, + "rank": 30 + }, { "arena": "models", "category": "dataviz", - "elo": 1230, - "win_rate": 44.2, + "elo": 1235, + "win_rate": 45.7, "rank": 43 }, { "arena": "models", "category": "gamedev", - "elo": 1304, - "win_rate": 52.3, + "elo": 1313, + "win_rate": 52.6, "rank": 15 }, { "arena": "models", "category": "uicomponent", - "elo": 1292, - "win_rate": 50.5, - "rank": 20 + "elo": 1276, + "win_rate": 48.9, + "rank": 29 }, { "arena": "models", "category": "website", - "elo": 1237, - "win_rate": 42.9, - "rank": 43 + "elo": 1254, + "win_rate": 45.9, + "rank": 42 } ], "artificial_analysis": { @@ -37349,13 +38116,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000014", - "completion": "0.00000028", - "input_cache_read": "0.0000000028" + "prompt": "0.000000119", + "completion": "0.000000238", + "input_cache_read": "0.00000000255" }, "top_provider": { - "context_length": 1048576, - "max_completion_tokens": 131072, + "context_length": 1050000, + "max_completion_tokens": 945000, "is_moderated": false }, "per_request_limits": null, @@ -37395,62 +38162,62 @@ { "arena": "models", "category": "3d", - "elo": 1223, + "elo": 1216, "win_rate": 50.8, - "rank": 36 + "rank": 43 }, { "arena": "models", "category": "asciiart", - "elo": 1148, - "win_rate": 45, - "rank": 47 + "elo": 1140, + "win_rate": 44.8, + "rank": 50 }, { "arena": "models", "category": "codecategories", - "elo": 1264, - "win_rate": 53.6, - "rank": 30 + "elo": 1260, + "win_rate": 53.5, + "rank": 37 }, { "arena": "models", "category": "dataviz", - "elo": 1256, - "win_rate": 53.7, - "rank": 28 + "elo": 1249, + "win_rate": 53.6, + "rank": 36 }, { "arena": "models", "category": "gamedev", - "elo": 1254, + "elo": 1249, "win_rate": 52.6, - "rank": 32 + "rank": 38 }, { "arena": "models", "category": "svg", - "elo": 1178, - "win_rate": 50.5, - "rank": 33 + "elo": 1179, + "win_rate": 50.1, + "rank": 35 }, { "arena": "models", "category": "uicomponent", - "elo": 1262, - "win_rate": 53.8, - "rank": 34 + "elo": 1258, + "win_rate": 53.7, + "rank": 40 }, { "arena": "models", "category": "website", - "elo": 1271, - "win_rate": 53.8, - "rank": 29 + "elo": 1266, + "win_rate": 53.5, + "rank": 34 } ], "artificial_analysis": { - "intelligence_index": 25.2, + "intelligence_index": 21.8, "coding_index": 56.8, "agentic_index": 15.8 } @@ -37475,13 +38242,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000000435", - "completion": "0.00000087", - "input_cache_read": "0.0000000036" + "prompt": "0.0000003045", + "completion": "0.000000609", + "input_cache_read": "0.0000000028" }, "top_provider": { - "context_length": 1048576, - "max_completion_tokens": 131072, + "context_length": 1050000, + "max_completion_tokens": 945000, "is_moderated": false }, "per_request_limits": null, @@ -37523,58 +38290,58 @@ { "arena": "models", "category": "3d", - "elo": 1252, - "win_rate": 54, - "rank": 29 + "elo": 1244, + "win_rate": 53.5, + "rank": 36 }, { "arena": "models", "category": "asciiart", - "elo": 1160, - "win_rate": 45.9, + "elo": 1156, + "win_rate": 46.2, "rank": 38 }, { "arena": "models", "category": "codecategories", - "elo": 1271, - "win_rate": 51.9, - "rank": 26 + "elo": 1266, + "win_rate": 51.5, + "rank": 34 }, { "arena": "models", "category": "dataviz", - "elo": 1263, + "elo": 1257, "win_rate": 50.5, - "rank": 27 + "rank": 33 }, { "arena": "models", "category": "gamedev", - "elo": 1269, - "win_rate": 53.3, - "rank": 29 + "elo": 1262, + "win_rate": 53, + "rank": 34 }, { "arena": "models", "category": "svg", - "elo": 1178, + "elo": 1181, "win_rate": 48, "rank": 34 }, { "arena": "models", "category": "uicomponent", - "elo": 1253, - "win_rate": 50.8, - "rank": 35 + "elo": 1249, + "win_rate": 50.7, + "rank": 42 }, { "arena": "models", "category": "website", - "elo": 1273, - "win_rate": 51.1, - "rank": 27 + "elo": 1267, + "win_rate": 50.8, + "rank": 33 } ], "artificial_analysis": { @@ -37718,51 +38485,51 @@ { "arena": "agents", "category": "webapps", - "elo": 1283, + "elo": 1290, "win_rate": 58.3, - "rank": 5 + "rank": 8 }, { "arena": "models", "category": "3d", - "elo": 1340, - "win_rate": 56.9, - "rank": 8 + "elo": 1330, + "win_rate": 56.8, + "rank": 15 }, { "arena": "models", "category": "codecategories", - "elo": 1322, - "win_rate": 52.4, - "rank": 6 + "elo": 1317, + "win_rate": 52.5, + "rank": 11 }, { "arena": "models", "category": "dataviz", - "elo": 1343, + "elo": 1336, "win_rate": 58.8, - "rank": 8 + "rank": 7 }, { "arena": "models", "category": "gamedev", - "elo": 1322, - "win_rate": 52.8, - "rank": 10 + "elo": 1314, + "win_rate": 53.1, + "rank": 14 }, { "arena": "models", "category": "uicomponent", - "elo": 1345, + "elo": 1340, "win_rate": 59.3, "rank": 7 }, { "arena": "models", "category": "website", - "elo": 1314, - "win_rate": 50.6, - "rank": 8 + "elo": 1308, + "win_rate": 50.7, + "rank": 13 } ], "artificial_analysis": { @@ -37830,6 +38597,65 @@ "mandatory": false } }, + { + "id": "xingchen-agi/xing4.0-29b-a4b:free", + "canonical_slug": "xingchen-agi/xing4.0-29b-a4b-20261015", + "hugging_face_id": "XingChen-AGI/Xing4.0-29B-A4B", + "name": "XingChen: Xing4.0 29B A4B (free)", + "created": 1792177496, + "description": "Xing4.0-29B-A4B is an open-weight mixture-of-experts language model from China Telecom's AI team (TeleAI) and the successor to the TeleChat series. It has 29B total parameters with 4B active per token...", + "context_length": 262144, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0", + "completion": "0" + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 235929, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], + "default_parameters": { + "temperature": 1, + "top_p": 0.95, + "repetition_penalty": 1.05 + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/xingchen-agi/xing4.0-29b-a4b-20261015/endpoints" + }, + "reasoning": { + "mandatory": false, + "default_enabled": true + } + }, { "id": "z-ai/glm-4.5", "canonical_slug": "z-ai/glm-4.5", @@ -37883,51 +38709,51 @@ { "arena": "models", "category": "3d", - "elo": 1178, + "elo": 1170, "win_rate": 59.7, - "rank": 53 + "rank": 61 }, { "arena": "models", "category": "codecategories", - "elo": 1169, + "elo": 1165, "win_rate": 54.4, - "rank": 69 + "rank": 78 }, { "arena": "models", "category": "dataviz", - "elo": 1165, + "elo": 1159, "win_rate": 53.3, - "rank": 72 + "rank": 77 }, { "arena": "models", "category": "gamedev", - "elo": 1155, + "elo": 1145, "win_rate": 54.4, - "rank": 66 + "rank": 76 }, { "arena": "models", "category": "svg", - "elo": 1095, + "elo": 1096, "win_rate": 50.8, - "rank": 60 + "rank": 61 }, { "arena": "models", "category": "uicomponent", - "elo": 1151, + "elo": 1144, "win_rate": 55, - "rank": 73 + "rank": 80 }, { "arena": "models", "category": "website", - "elo": 1176, + "elo": 1170, "win_rate": 53.7, - "rank": 72 + "rank": 82 } ], "artificial_analysis": { @@ -37997,51 +38823,51 @@ { "arena": "models", "category": "3d", - "elo": 1130, + "elo": 1122, "win_rate": 54.1, - "rank": 73 + "rank": 83 }, { "arena": "models", "category": "codecategories", - "elo": 1141, + "elo": 1137, "win_rate": 51.4, - "rank": 83 + "rank": 94 }, { "arena": "models", "category": "dataviz", - "elo": 1193, + "elo": 1186, "win_rate": 58.5, - "rank": 56 + "rank": 63 }, { "arena": "models", "category": "gamedev", - "elo": 1104, + "elo": 1094, "win_rate": 48.4, - "rank": 87 + "rank": 99 }, { "arena": "models", "category": "svg", - "elo": 1070, + "elo": 1072, "win_rate": 50.8, - "rank": 67 + "rank": 68 }, { "arena": "models", "category": "uicomponent", - "elo": 1130, + "elo": 1123, "win_rate": 54.4, - "rank": 79 + "rank": 89 }, { "arena": "models", "category": "website", - "elo": 1153, + "elo": 1147, "win_rate": 51.3, - "rank": 82 + "rank": 93 } ], "artificial_analysis": { @@ -38135,13 +38961,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000043", - "completion": "0.00000175", - "input_cache_read": "0.00000008" + "prompt": "0.00000055", + "completion": "0.0000022", + "input_cache_read": "0.00000011" }, "top_provider": { - "context_length": 198000, - "max_completion_tokens": 16384, + "context_length": 204800, + "max_completion_tokens": 131072, "is_moderated": false }, "per_request_limits": null, @@ -38183,14 +39009,14 @@ { "arena": "agents", "category": "androidnative", - "elo": 1099, + "elo": 1084, "win_rate": 52.6, - "rank": 29 + "rank": 30 }, { "arena": "agents", "category": "fullstack", - "elo": 1028, + "elo": 1029, "win_rate": 42.3, "rank": 38 }, @@ -38204,58 +39030,58 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1093, + "elo": 1096, "win_rate": 47.2, - "rank": 36 + "rank": 38 }, { "arena": "models", "category": "3d", - "elo": 1137, + "elo": 1129, "win_rate": 54.2, - "rank": 69 + "rank": 77 }, { "arena": "models", "category": "codecategories", - "elo": 1171, + "elo": 1166, "win_rate": 54.3, - "rank": 67 + "rank": 77 }, { "arena": "models", "category": "dataviz", - "elo": 1168, + "elo": 1161, "win_rate": 52.6, - "rank": 70 + "rank": 76 }, { "arena": "models", "category": "gamedev", - "elo": 1161, + "elo": 1151, "win_rate": 54.8, - "rank": 64 + "rank": 75 }, { "arena": "models", "category": "svg", - "elo": 1108, + "elo": 1109, "win_rate": 52.1, - "rank": 57 + "rank": 58 }, { "arena": "models", "category": "uicomponent", - "elo": 1154, + "elo": 1148, "win_rate": 52.5, - "rank": 72 + "rank": 79 }, { "arena": "models", "category": "website", - "elo": 1179, + "elo": 1174, "win_rate": 54.3, - "rank": 71 + "rank": 80 } ], "artificial_analysis": { @@ -38286,7 +39112,7 @@ "pricing": { "prompt": "0.0000003", "completion": "0.0000009", - "input_cache_read": "0.00000005" + "input_cache_read": "0.000000055" }, "top_provider": { "context_length": 131072, @@ -38349,12 +39175,12 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000006", - "completion": "0.0000022", - "input_cache_read": "0.00000011" + "prompt": "0.00000054", + "completion": "0.00000198", + "input_cache_read": "0.000000099" }, "top_provider": { - "context_length": 202752, + "context_length": 204800, "max_completion_tokens": 131072, "is_moderated": false }, @@ -38389,7 +39215,7 @@ }, "supported_voices": null, "knowledge_cutoff": null, - "expiration_date": "2026-12-31", + "expiration_date": null, "links": { "details": "/api/v1/models/z-ai/glm-4.7-20251222/endpoints" }, @@ -38398,14 +39224,14 @@ { "arena": "agents", "category": "androidnative", - "elo": 1128, - "win_rate": 56.2, - "rank": 27 + "elo": 1112, + "win_rate": 56.1, + "rank": 29 }, { "arena": "agents", "category": "fullstack", - "elo": 1048, + "elo": 1050, "win_rate": 45.1, "rank": 36 }, @@ -38419,65 +39245,65 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1102, + "elo": 1105, "win_rate": 48.9, - "rank": 35 + "rank": 37 }, { "arena": "models", "category": "3d", - "elo": 1199, + "elo": 1191, "win_rate": 54.3, - "rank": 46 + "rank": 54 }, { "arena": "models", "category": "asciiart", - "elo": 1174, + "elo": 1165, "win_rate": 48.2, - "rank": 31 + "rank": 34 }, { "arena": "models", "category": "codecategories", - "elo": 1221, + "elo": 1217, "win_rate": 54.8, - "rank": 46 + "rank": 55 }, { "arena": "models", "category": "dataviz", - "elo": 1201, + "elo": 1195, "win_rate": 51.2, - "rank": 54 + "rank": 62 }, { "arena": "models", "category": "gamedev", - "elo": 1199, + "elo": 1189, "win_rate": 55.2, - "rank": 50 + "rank": 61 }, { "arena": "models", "category": "svg", - "elo": 1142, + "elo": 1143, "win_rate": 54.3, - "rank": 47 + "rank": 48 }, { "arena": "models", "category": "uicomponent", - "elo": 1206, + "elo": 1199, "win_rate": 51.1, - "rank": 51 + "rank": 60 }, { "arena": "models", "category": "website", - "elo": 1232, + "elo": 1226, "win_rate": 55.3, - "rank": 47 + "rank": 56 } ], "artificial_analysis": { @@ -38553,51 +39379,51 @@ { "arena": "models", "category": "3d", - "elo": 1128, + "elo": 1121, "win_rate": 51.2, - "rank": 74 + "rank": 84 }, { "arena": "models", "category": "codecategories", - "elo": 1183, + "elo": 1178, "win_rate": 53.1, - "rank": 59 + "rank": 68 }, { "arena": "models", "category": "dataviz", - "elo": 1130, + "elo": 1123, "win_rate": 45.3, - "rank": 87 + "rank": 96 }, { "arena": "models", "category": "gamedev", - "elo": 1145, + "elo": 1135, "win_rate": 49.7, - "rank": 72 + "rank": 84 }, { "arena": "models", "category": "svg", - "elo": 1037, + "elo": 1038, "win_rate": 44.2, - "rank": 75 + "rank": 76 }, { "arena": "models", "category": "uicomponent", - "elo": 1214, + "elo": 1208, "win_rate": 57.6, - "rank": 49 + "rank": 56 }, { "arena": "models", "category": "website", - "elo": 1199, + "elo": 1194, "win_rate": 54, - "rank": 59 + "rank": 68 } ], "artificial_analysis": { @@ -38627,13 +39453,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000006", - "completion": "0.00000192", - "input_cache_read": "0.00000012" + "prompt": "0.000001", + "completion": "0.0000032", + "input_cache_read": "0.0000002" }, "top_provider": { - "context_length": 198000, - "max_completion_tokens": 128000, + "context_length": 202752, + "max_completion_tokens": 131072, "is_moderated": false }, "per_request_limits": null, @@ -38672,14 +39498,14 @@ { "arena": "agents", "category": "androidnative", - "elo": 1161, - "win_rate": 55.1, - "rank": 24 + "elo": 1146, + "win_rate": 55.2, + "rank": 25 }, { "arena": "agents", "category": "fullstack", - "elo": 1121, + "elo": 1123, "win_rate": 51.7, "rank": 27 }, @@ -38693,72 +39519,72 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1147, + "elo": 1148, "win_rate": 45.1, "rank": 18 }, { "arena": "agents", "category": "mobileapps", - "elo": 1133, + "elo": 1136, "win_rate": 51.6, - "rank": 32 + "rank": 34 }, { "arena": "models", "category": "3d", - "elo": 1237, + "elo": 1229, "win_rate": 56.3, - "rank": 34 + "rank": 41 }, { "arena": "models", "category": "asciiart", - "elo": 1156, + "elo": 1147, "win_rate": 47.9, - "rank": 41 + "rank": 45 }, { "arena": "models", "category": "codecategories", - "elo": 1251, + "elo": 1246, "win_rate": 55.5, - "rank": 34 + "rank": 42 }, { "arena": "models", "category": "dataviz", - "elo": 1235, + "elo": 1228, "win_rate": 53, - "rank": 38 + "rank": 46 }, { "arena": "models", "category": "gamedev", - "elo": 1245, + "elo": 1234, "win_rate": 57.4, - "rank": 34 + "rank": 41 }, { "arena": "models", "category": "svg", - "elo": 1167, + "elo": 1169, "win_rate": 54.4, - "rank": 36 + "rank": 37 }, { "arena": "models", "category": "uicomponent", - "elo": 1237, + "elo": 1230, "win_rate": 53.6, - "rank": 43 + "rank": 50 }, { "arena": "models", "category": "website", - "elo": 1254, + "elo": 1247, "win_rate": 55, - "rank": 37 + "rank": 47 } ], "artificial_analysis": { @@ -38828,58 +39654,58 @@ { "arena": "models", "category": "3d", - "elo": 1257, - "win_rate": 55.9, - "rank": 26 + "elo": 1248, + "win_rate": 55.4, + "rank": 34 }, { "arena": "models", "category": "asciiart", - "elo": 1164, - "win_rate": 48.7, - "rank": 35 + "elo": 1160, + "win_rate": 48.5, + "rank": 37 }, { "arena": "models", "category": "codecategories", - "elo": 1268, - "win_rate": 53.9, - "rank": 28 + "elo": 1262, + "win_rate": 53.5, + "rank": 35 }, { "arena": "models", "category": "dataviz", - "elo": 1271, - "win_rate": 55.1, - "rank": 23 + "elo": 1264, + "win_rate": 55, + "rank": 30 }, { "arena": "models", "category": "gamedev", - "elo": 1258, - "win_rate": 53.2, - "rank": 31 + "elo": 1248, + "win_rate": 52.8, + "rank": 39 }, { "arena": "models", "category": "svg", "elo": 1206, - "win_rate": 54.6, - "rank": 23 + "win_rate": 54.3, + "rank": 24 }, { "arena": "models", "category": "uicomponent", - "elo": 1270, - "win_rate": 55.3, - "rank": 29 + "elo": 1263, + "win_rate": 54.9, + "rank": 36 }, { "arena": "models", "category": "website", - "elo": 1268, - "win_rate": 53.3, - "rank": 31 + "elo": 1262, + "win_rate": 52.9, + "rank": 37 } ], "artificial_analysis": { @@ -38909,13 +39735,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000000966", - "completion": "0.000003036", - "input_cache_read": "0.0000001794" + "prompt": "0.0000014", + "completion": "0.0000044", + "input_cache_read": "0.00000026" }, "top_provider": { - "context_length": 200000, - "max_completion_tokens": 128000, + "context_length": 202752, + "max_completion_tokens": 131072, "is_moderated": false }, "per_request_limits": null, @@ -38961,62 +39787,62 @@ "category": "3d", "elo": 1336, "win_rate": 62.6, - "rank": 9 + "rank": 12 }, { "arena": "models", "category": "asciiart", - "elo": 1140, - "win_rate": 43.4, - "rank": 49 + "elo": 1141, + "win_rate": 44.6, + "rank": 47 }, { "arena": "models", "category": "codecategories", - "elo": 1273, - "win_rate": 53.3, - "rank": 24 + "elo": 1268, + "win_rate": 53.1, + "rank": 32 }, { "arena": "models", "category": "dataviz", "elo": 1366, "win_rate": 67, - "rank": 2 + "rank": 3 }, { "arena": "models", "category": "gamedev", - "elo": 1272, - "win_rate": 55.5, - "rank": 24 + "elo": 1265, + "win_rate": 55.2, + "rank": 28 }, { "arena": "models", "category": "svg", "elo": 1218, - "win_rate": 55.6, - "rank": 20 + "win_rate": 55.4, + "rank": 19 }, { "arena": "models", "category": "uicomponent", "elo": 1292, "win_rate": 54.9, - "rank": 19 + "rank": 23 }, { "arena": "models", "category": "website", "elo": 1290, "win_rate": 55.1, - "rank": 18 + "rank": 20 }, { "arena": "agents", "category": "agenticgamedev", - "elo": 1165, - "win_rate": 49.8, + "elo": 1164, + "win_rate": 49.6, "rank": 17 }, { @@ -39050,14 +39876,14 @@ { "arena": "agents", "category": "androidnative", - "elo": 1194, - "win_rate": 52, - "rank": 15 + "elo": 1181, + "win_rate": 52.1, + "rank": 16 }, { "arena": "agents", "category": "fullstack", - "elo": 1166, + "elo": 1167, "win_rate": 53.2, "rank": 23 }, @@ -39071,16 +39897,16 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1169, + "elo": 1170, "win_rate": 48.8, "rank": 14 }, { "arena": "agents", "category": "mobileapps", - "elo": 1158, - "win_rate": 50.6, - "rank": 24 + "elo": 1162, + "win_rate": 50.4, + "rank": 26 }, { "arena": "agents", @@ -39096,12 +39922,19 @@ "win_rate": 54.2, "rank": 6 }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1315, + "win_rate": 72.4, + "rank": 3 + }, { "arena": "agents", "category": "webapps", - "elo": 1168, - "win_rate": 50.7, - "rank": 25 + "elo": 1175, + "win_rate": 50.5, + "rank": 29 } ], "artificial_analysis": { @@ -39131,13 +39964,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000000171", - "completion": "0.0000072", - "input_cache_read": "0.000000162" + "prompt": "0.0000000341", + "completion": "0.000007", + "input_cache_read": "0.000000033" }, "top_provider": { "context_length": 1048576, - "max_completion_tokens": 131072, + "max_completion_tokens": 943718, "is_moderated": false }, "per_request_limits": null, @@ -39183,21 +40016,21 @@ { "arena": "agents", "category": "agenticgamedev", - "elo": 1205, + "elo": 1206, "win_rate": 49, "rank": 10 }, { "arena": "agents", "category": "androidnative", - "elo": 1193, - "win_rate": 53.2, - "rank": 16 + "elo": 1178, + "win_rate": 52.9, + "rank": 18 }, { "arena": "agents", "category": "fullstack", - "elo": 1239, + "elo": 1241, "win_rate": 60.5, "rank": 12 }, @@ -39218,79 +40051,79 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1156, - "win_rate": 48.1, - "rank": 25 + "elo": 1159, + "win_rate": 47.9, + "rank": 27 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1194, - "win_rate": 48.7, - "rank": 16 + "elo": 1193, + "win_rate": 48.8, + "rank": 17 }, { "arena": "agents", "category": "webapps", - "elo": 1215, - "win_rate": 56, - "rank": 13 + "elo": 1222, + "win_rate": 55.8, + "rank": 17 }, { "arena": "models", "category": "3d", - "elo": 1297, - "win_rate": 53.5, - "rank": 15 + "elo": 1288, + "win_rate": 53.3, + "rank": 21 }, { "arena": "models", "category": "asciiart", - "elo": 1203, - "win_rate": 46.2, - "rank": 25 + "elo": 1190, + "win_rate": 46, + "rank": 29 }, { "arena": "models", "category": "codecategories", - "elo": 1294, - "win_rate": 50.5, - "rank": 15 + "elo": 1288, + "win_rate": 50.4, + "rank": 21 }, { "arena": "models", "category": "dataviz", - "elo": 1292, + "elo": 1285, "win_rate": 52, - "rank": 13 + "rank": 17 }, { "arena": "models", "category": "gamedev", - "elo": 1278, - "win_rate": 49.5, - "rank": 20 + "elo": 1268, + "win_rate": 49.6, + "rank": 27 }, { "arena": "models", "category": "svg", - "elo": 1219, - "win_rate": 49.2, - "rank": 19 + "elo": 1215, + "win_rate": 48.6, + "rank": 21 }, { "arena": "models", "category": "uicomponent", - "elo": 1300, - "win_rate": 55.2, - "rank": 16 + "elo": 1297, + "win_rate": 55.3, + "rank": 20 }, { "arena": "models", "category": "website", - "elo": 1292, - "win_rate": 49.6, - "rank": 16 + "elo": 1285, + "win_rate": 49.5, + "rank": 23 } ], "artificial_analysis": { @@ -39302,7 +40135,7 @@ "reasoning": { "mandatory": false, "default_enabled": true, - "supported_efforts": ["xhigh", "high"], + "supported_efforts": ["xhigh", "high", "none"], "default_effort": "high" } }, @@ -39322,9 +40155,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000007", - "completion": "0.000007", - "input_cache_read": "0.000000065" + "prompt": "0.000000079", + "completion": "0.0000014", + "input_cache_read": "0.000000078" }, "top_provider": { "context_length": 1048576, @@ -39370,58 +40203,58 @@ { "arena": "models", "category": "3d", - "elo": 1350, - "win_rate": 60.7, - "rank": 5 + "elo": 1332, + "win_rate": 59.3, + "rank": 14 }, { "arena": "models", "category": "asciiart", - "elo": 1211, - "win_rate": 46, - "rank": 22 + "elo": 1208, + "win_rate": 47, + "rank": 21 }, { "arena": "models", "category": "codecategories", - "elo": 1314, - "win_rate": 54.9, - "rank": 9 + "elo": 1304, + "win_rate": 54, + "rank": 15 }, { "arena": "models", "category": "dataviz", - "elo": 1269, - "win_rate": 52.7, - "rank": 25 + "elo": 1260, + "win_rate": 51.9, + "rank": 32 }, { "arena": "models", "category": "gamedev", - "elo": 1325, - "win_rate": 52.9, - "rank": 9 + "elo": 1311, + "win_rate": 52.5, + "rank": 17 }, { "arena": "models", "category": "svg", - "elo": 1297, - "win_rate": 57, - "rank": 7 + "elo": 1294, + "win_rate": 56.9, + "rank": 8 }, { "arena": "models", "category": "uicomponent", - "elo": 1325, - "win_rate": 57.8, - "rank": 10 + "elo": 1314, + "win_rate": 56.7, + "rank": 15 }, { "arena": "models", "category": "website", - "elo": 1306, - "win_rate": 54.9, - "rank": 11 + "elo": 1295, + "win_rate": 53.9, + "rank": 18 }, { "arena": "agents", @@ -39433,14 +40266,14 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1191, + "elo": 1194, "win_rate": 52.2, - "rank": 17 + "rank": 19 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1255, + "elo": 1251, "win_rate": 51.2, "rank": 8 } @@ -39474,13 +40307,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000015", - "completion": "0.0000005", - "input_cache_read": "0.00000003" + "prompt": "0.0000000052", + "completion": "0.0000001985", + "input_cache_read": "0.0000000052" }, "top_provider": { - "context_length": 1048575, - "max_completion_tokens": 943717, + "context_length": 1048576, + "max_completion_tokens": 943718, "is_moderated": false }, "per_request_limits": null, @@ -39522,58 +40355,58 @@ { "arena": "models", "category": "3d", - "elo": 1326, - "win_rate": 56.6, - "rank": 11 + "elo": 1316, + "win_rate": 56.2, + "rank": 17 }, { "arena": "models", "category": "asciiart", - "elo": 1273, - "win_rate": 54.8, + "elo": 1267, + "win_rate": 54.6, "rank": 12 }, { "arena": "models", "category": "codecategories", - "elo": 1288, - "win_rate": 49.4, - "rank": 17 + "elo": 1282, + "win_rate": 49.3, + "rank": 22 }, { "arena": "models", "category": "dataviz", - "elo": 1269, - "win_rate": 50.3, - "rank": 26 + "elo": 1262, + "win_rate": 50.4, + "rank": 31 }, { "arena": "models", "category": "gamedev", - "elo": 1291, - "win_rate": 47.2, - "rank": 17 + "elo": 1278, + "win_rate": 47.1, + "rank": 25 }, { "arena": "models", "category": "svg", - "elo": 1290, - "win_rate": 57.2, - "rank": 10 + "elo": 1285, + "win_rate": 56.7, + "rank": 11 }, { "arena": "models", "category": "uicomponent", - "elo": 1324, - "win_rate": 55, - "rank": 11 + "elo": 1316, + "win_rate": 54.6, + "rank": 14 }, { "arena": "models", "category": "website", - "elo": 1278, - "win_rate": 48.5, - "rank": 23 + "elo": 1272, + "win_rate": 48.4, + "rank": 28 } ], "artificial_analysis": { @@ -39605,9 +40438,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000006", - "completion": "0.0000002", - "input_cache_read": "0.000000012" + "prompt": "0.00000005", + "completion": "0.00000018", + "input_cache_read": "0.00000001" }, "top_provider": { "context_length": 1048576, @@ -39619,6 +40452,7 @@ "frequency_penalty", "include_reasoning", "logit_bias", + "logprobs", "max_tokens", "min_p", "presence_penalty", @@ -39633,6 +40467,7 @@ "tool_choice", "tools", "top_k", + "top_logprobs", "top_p" ], "default_parameters": { @@ -39650,58 +40485,58 @@ { "arena": "models", "category": "3d", - "elo": 1326, - "win_rate": 56.6, - "rank": 11 + "elo": 1316, + "win_rate": 56.2, + "rank": 17 }, { "arena": "models", "category": "asciiart", - "elo": 1273, - "win_rate": 54.8, + "elo": 1267, + "win_rate": 54.6, "rank": 12 }, { "arena": "models", "category": "codecategories", - "elo": 1288, - "win_rate": 49.4, - "rank": 17 + "elo": 1282, + "win_rate": 49.3, + "rank": 22 }, { "arena": "models", "category": "dataviz", - "elo": 1269, - "win_rate": 50.3, - "rank": 26 + "elo": 1262, + "win_rate": 50.4, + "rank": 31 }, { "arena": "models", "category": "gamedev", - "elo": 1291, - "win_rate": 47.2, - "rank": 17 + "elo": 1278, + "win_rate": 47.1, + "rank": 25 }, { "arena": "models", "category": "svg", - "elo": 1290, - "win_rate": 57.2, - "rank": 10 + "elo": 1285, + "win_rate": 56.7, + "rank": 11 }, { "arena": "models", "category": "uicomponent", - "elo": 1324, - "win_rate": 55, - "rank": 11 + "elo": 1316, + "win_rate": 54.6, + "rank": 14 }, { "arena": "models", "category": "website", - "elo": 1278, - "win_rate": 48.5, - "rank": 23 + "elo": 1272, + "win_rate": 48.4, + "rank": 28 } ], "artificial_analysis": { @@ -39894,58 +40729,58 @@ { "arena": "models", "category": "3d", - "elo": 1350, - "win_rate": 60.7, - "rank": 5 + "elo": 1332, + "win_rate": 59.3, + "rank": 14 }, { "arena": "models", "category": "asciiart", - "elo": 1211, - "win_rate": 46, - "rank": 22 + "elo": 1208, + "win_rate": 47, + "rank": 21 }, { "arena": "models", "category": "codecategories", - "elo": 1314, - "win_rate": 54.9, - "rank": 9 + "elo": 1304, + "win_rate": 54, + "rank": 15 }, { "arena": "models", "category": "dataviz", - "elo": 1269, - "win_rate": 52.7, - "rank": 25 + "elo": 1260, + "win_rate": 51.9, + "rank": 32 }, { "arena": "models", "category": "gamedev", - "elo": 1325, - "win_rate": 52.9, - "rank": 9 + "elo": 1311, + "win_rate": 52.5, + "rank": 17 }, { "arena": "models", "category": "svg", - "elo": 1297, - "win_rate": 57, - "rank": 7 + "elo": 1294, + "win_rate": 56.9, + "rank": 8 }, { "arena": "models", "category": "uicomponent", - "elo": 1325, - "win_rate": 57.8, - "rank": 10 + "elo": 1314, + "win_rate": 56.7, + "rank": 15 }, { "arena": "models", "category": "website", - "elo": 1306, - "win_rate": 54.9, - "rank": 11 + "elo": 1295, + "win_rate": 53.9, + "rank": 18 }, { "arena": "agents", @@ -39957,14 +40792,14 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1191, + "elo": 1194, "win_rate": 52.2, - "rank": 17 + "rank": 19 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1255, + "elo": 1251, "win_rate": 51.2, "rank": 8 } @@ -40039,7 +40874,7 @@ "arena": "agents", "category": "agenticgamedev", "elo": 1102, - "win_rate": 42.6, + "win_rate": 42.5, "rank": 23 }, { @@ -40075,13 +40910,13 @@ "category": "androidnative", "elo": 1267, "win_rate": 54.8, - "rank": 4 + "rank": 3 }, { "arena": "agents", "category": "fullstack", - "elo": 1147, - "win_rate": 52, + "elo": 1149, + "win_rate": 52.1, "rank": 26 }, { @@ -40094,16 +40929,16 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1120, + "elo": 1121, "win_rate": 44.6, "rank": 21 }, { "arena": "agents", "category": "mobileapps", - "elo": 1131, + "elo": 1134, "win_rate": 50.4, - "rank": 33 + "rank": 35 }, { "arena": "agents", @@ -40122,65 +40957,65 @@ { "arena": "agents", "category": "webapps", - "elo": 1117, + "elo": 1124, "win_rate": 44.7, - "rank": 31 + "rank": 35 }, { "arena": "models", "category": "3d", - "elo": 1217, - "win_rate": 52.7, - "rank": 38 + "elo": 1209, + "win_rate": 52.3, + "rank": 46 }, { "arena": "models", "category": "asciiart", - "elo": 1129, - "win_rate": 43.3, - "rank": 53 + "elo": 1117, + "win_rate": 42.4, + "rank": 56 }, { "arena": "models", "category": "codecategories", - "elo": 1233, - "win_rate": 50, - "rank": 43 + "elo": 1228, + "win_rate": 49.6, + "rank": 52 }, { "arena": "models", "category": "dataviz", - "elo": 1206, - "win_rate": 47.5, - "rank": 53 + "elo": 1202, + "win_rate": 47.7, + "rank": 59 }, { "arena": "models", "category": "gamedev", - "elo": 1229, - "win_rate": 50.7, - "rank": 39 + "elo": 1219, + "win_rate": 50, + "rank": 49 }, { "arena": "models", "category": "svg", "elo": 1151, - "win_rate": 49.1, - "rank": 42 + "win_rate": 48.8, + "rank": 43 }, { "arena": "models", "category": "uicomponent", - "elo": 1218, - "win_rate": 48.3, - "rank": 47 + "elo": 1213, + "win_rate": 48.1, + "rank": 54 }, { "arena": "models", "category": "website", - "elo": 1236, - "win_rate": 49.2, - "rank": 45 + "elo": 1230, + "win_rate": 48.9, + "rank": 54 } ], "artificial_analysis": { diff --git a/scripts/openrouter.video-models.json b/scripts/openrouter.video-models.json index 398309ecc3..ef83d6f38c 100644 --- a/scripts/openrouter.video-models.json +++ b/scripts/openrouter.video-models.json @@ -175,7 +175,7 @@ 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30 ], - "supported_frame_images": ["first_frame"], + "supported_frame_images": ["first_frame", "last_frame"], "upscale_factor": null, "creativity": null, "generate_audio": true, @@ -201,7 +201,7 @@ 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30 ], - "supported_frame_images": ["first_frame"], + "supported_frame_images": ["first_frame", "last_frame"], "upscale_factor": null, "creativity": null, "generate_audio": true, @@ -217,10 +217,10 @@ "id": "black-forest-labs/flux-3-video", "canonical_slug": "black-forest-labs/flux-3-video-20260804", "hugging_face_id": null, - "name": "Black Forest Labs: FLUX.3 Video", + "name": "Black Forest Labs: FLUX 3 Video", "created": 1785858831, "description": "FLUX.3 Video is a video generation model from Black Forest Labs. It supports text-to-video, image-guided generation with opening and closing keyframes, and video continuation workflows, making it suited for controlled...", - "supported_resolutions": ["720p", "1080p"], + "supported_resolutions": ["720p", "1080p", "2K", "4K"], "supported_aspect_ratios": ["21:9", "16:9", "4:3", "1:1", "3:4", "9:16"], "supported_sizes": null, "supported_durations": [ @@ -233,8 +233,12 @@ "seed": false, "pricing_skus": { "cents_per_second_output": "17", + "cents_per_second_output_2k": "28", + "cents_per_second_output_4k": "41", "cents_per_second_output_720p": "17", "cents_per_second_output_1080p": "29", + "cents_per_second_video_continuation_2k": "31", + "cents_per_second_video_continuation_4k": "45", "cents_per_second_video_continuation_720p": "41", "cents_per_second_video_continuation_1080p": "53" }, @@ -281,8 +285,8 @@ "generate_audio": false, "seed": false, "pricing_skus": { - "cents_per_megapixel_second_precise": "7.5", - "cents_per_megapixel_second_creative": "10.5" + "cents_per_megapixel_second_precise": "3.5", + "cents_per_megapixel_second_creative": "5" }, "allowed_passthrough_parameters": ["safety_tolerance"] }, @@ -686,14 +690,15 @@ "generate_audio": false, "seed": true, "pricing_skus": { - "duration_seconds_2k": "0.09", + "duration_seconds_2k": "0.1", "duration_seconds_480p": "0.02", - "duration_seconds_768p": "0.03", + "duration_seconds_768p": "0.036", + "reference_input_images": "0.04", "reference_duration_seconds_2k": "0.18", - "reference_duration_seconds_480p": "0.04", - "reference_duration_seconds_768p": "0.06" + "reference_duration_seconds_480p": "0.07", + "reference_duration_seconds_768p": "0.1" }, - "allowed_passthrough_parameters": [] + "allowed_passthrough_parameters": ["prompt_enhancement"] }, { "id": "kwaivgi/kling-v3.0-pro", diff --git a/scripts/vercel-gateway.models.json b/scripts/vercel-gateway.models.json index 5636769874..3f0ef046df 100644 --- a/scripts/vercel-gateway.models.json +++ b/scripts/vercel-gateway.models.json @@ -12,7 +12,7 @@ "type": "language", "zdr": "all", "no_training": "all", - "tags": ["reasoning", "tool-use", "structured-output"], + "tags": ["reasoning", "tool-use", "structured-output", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -52,9 +52,9 @@ "context_window": 262144, "max_tokens": 16384, "type": "language", - "zdr": "some", - "no_training": "some", - "tags": ["tool-use", "structured-output", "reasoning"], + "zdr": "all", + "no_training": "all", + "tags": ["tool-use", "structured-output", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -66,21 +66,10 @@ "stop", "tools", "tool_choice", - "reasoning", - "include_reasoning", "response_format", "structured_outputs" ], "temperature": true, - "reasoning_options": [ - { - "type": "toggle" - }, - { - "type": "effort", - "values": ["none", "low", "medium", "high"] - } - ], "knowledge": "2025-04", "pricing": { "input": "0.00000022", @@ -101,7 +90,7 @@ "type": "language", "zdr": "all", "no_training": "all", - "tags": ["reasoning", "tool-use", "structured-output"], + "tags": ["reasoning", "tool-use", "structured-output", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -143,7 +132,7 @@ "type": "language", "zdr": "all", "no_training": "all", - "tags": ["reasoning", "tool-use", "structured-output"], + "tags": ["reasoning", "tool-use", "structured-output", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -166,173 +155,36 @@ "type": "toggle" }, { - "type": "budget_tokens", - "min": 1, - "max": 38912 + "type": "effort", + "values": ["none", "low", "medium", "high"] } ], "knowledge": "2025-04", "pricing": { - "input": "0.00000016", - "output": "0.00000064", + "input": "0.00000015", + "output": "0.0000006", "varies_by_provider": true } }, { - "id": "alibaba/qwen-3.6-max-preview", + "id": "alibaba/qwen3-coder", "object": "model", "created": 1755815280, - "released": 1776643200, + "released": 1753142400, "owned_by": "alibaba", - "name": "Qwen 3.6 Max Preview", - "description": "Compared with the previously released Qwen3-Max and Qwen3.6-Plus, this model features enhanced vibe coding abilities, more efficient coding agent execution, and significantly improved front-end development skills. Additionally, its long-tail knowledge retention has been further upgraded.", - "context_window": 240000, - "max_tokens": 64000, + "name": "Qwen3 Coder 480B A35B Instruct", + "description": "Mixture-of-experts LLM with advanced coding and reasoning capabilities", + "context_window": 262144, + "max_tokens": 32768, "type": "language", "zdr": "all", "no_training": "all", - "tags": ["reasoning", "tool-use", "explicit-caching"], - "supported_specifications": ["v2", "v3", "v4"], - "modalities": { - "input": ["text"], - "output": ["text"] - }, - "supported_parameters": [ - "max_tokens", - "temperature", - "stop", - "tools", - "tool_choice", - "reasoning", - "include_reasoning" - ], - "temperature": true, - "reasoning_options": [ - { - "type": "toggle" - }, - { - "type": "budget_tokens", - "min": 1, - "max": 131072 - } - ], - "pricing": { - "input": "0.0000013", - "input_tiers": [ - { - "cost": "0.0000013", - "min": 0, - "max": 128000 - }, - { - "cost": "0.000002", - "min": 128000 - } - ], - "output": "0.0000078", - "output_tiers": [ - { - "cost": "0.0000078", - "min": 0, - "max": 128000 - }, - { - "cost": "0.000012", - "min": 128000 - } - ], - "input_cache_read": "0.00000013", - "input_cache_read_tiers": [ - { - "cost": "0.00000013", - "min": 0, - "max": 128000 - }, - { - "cost": "0.0000002", - "min": 128000 - } - ], - "input_cache_write": "0.000001625", - "input_cache_write_tiers": [ - { - "cost": "0.000001625", - "min": 0, - "max": 128000 - }, - { - "cost": "0.0000025", - "min": 128000 - } - ] - } - }, - { - "id": "alibaba/qwen3-235b-a22b-thinking", - "object": "model", - "created": 1755815280, - "released": 1758585600, - "owned_by": "alibaba", - "name": "Qwen3 VL 235B A22B Thinking", - "description": "Qwen3 series VL models feature significantly enhanced multimodal reasoning capabilities, with a particular focus on optimizing the model for STEM and mathematical reasoning. Visual perception and recognition abilities have been comprehensively improved, and OCR capabilities have undergone a major upgrade.", - "context_window": 131072, - "max_tokens": 32768, - "type": "language", - "zdr": "some", - "no_training": "some", "tags": [ - "vision", - "reasoning", + "implicit-caching", "tool-use", - "file-input", - "structured-output" - ], - "supported_specifications": ["v2", "v3", "v4"], - "modalities": { - "input": ["text", "image", "pdf"], - "output": ["text"] - }, - "supported_parameters": [ - "max_tokens", - "temperature", - "stop", - "tools", - "tool_choice", - "reasoning", - "include_reasoning", - "response_format", - "structured_outputs" - ], - "temperature": true, - "reasoning_options": [ - { - "type": "budget_tokens", - "min": 1, - "max": 81920 - } + "structured-output", + "open-weights" ], - "knowledge": "2025-04", - "pricing": { - "input": "0.0000004", - "output": "0.000004", - "varies_by_provider": true - } - }, - { - "id": "alibaba/qwen3-coder", - "object": "model", - "created": 1755815280, - "released": 1753142400, - "owned_by": "alibaba", - "name": "Qwen3 Coder 480B A35B Instruct", - "description": "Qwen3-Coder-480B-A35B-Instruct is a cutting-edge open coding model from Qwen, matching Claude Sonnet’s performance in agentic programming, browser automation, and core development tasks.", - "context_window": 262144, - "max_tokens": 65536, - "type": "language", - "zdr": "some", - "no_training": "some", - "tags": ["tool-use", "structured-output", "implicit-caching"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -350,58 +202,9 @@ "temperature": true, "knowledge": "2025-04", "pricing": { - "input": "0.0000015", - "input_tiers": [ - { - "cost": "0.0000015", - "min": 0, - "max": 32001 - }, - { - "cost": "0.0000027", - "min": 32001, - "max": 128001 - }, - { - "cost": "0.0000045", - "min": 128001 - } - ], - "output": "0.0000075", - "output_tiers": [ - { - "cost": "0.0000075", - "min": 0, - "max": 32001 - }, - { - "cost": "0.0000135", - "min": 32001, - "max": 128001 - }, - { - "cost": "0.0000225", - "min": 128001 - } - ], - "input_cache_read": "0.0000003", - "input_cache_read_tiers": [ - { - "cost": "0.0000003", - "min": 0, - "max": 32001 - }, - { - "cost": "0.00000054", - "min": 32001, - "max": 128001 - }, - { - "cost": "0.0000009", - "min": 128001 - } - ], - "varies_by_provider": true + "input": "0.00000022", + "output": "0.0000018", + "input_cache_read": "0.000000022" } }, { @@ -415,9 +218,9 @@ "context_window": 262144, "max_tokens": 8192, "type": "language", - "zdr": "some", - "no_training": "some", - "tags": ["tool-use", "structured-output"], + "zdr": "all", + "no_training": "all", + "tags": ["tool-use", "structured-output", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -436,8 +239,7 @@ "knowledge": "2025-04", "pricing": { "input": "0.00000015", - "output": "0.0000006", - "varies_by_provider": true + "output": "0.0000006" } }, { @@ -453,7 +255,7 @@ "type": "language", "zdr": "all", "no_training": "all", - "tags": ["tool-use", "structured-output"], + "tags": ["tool-use", "structured-output", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -476,115 +278,19 @@ } }, { - "id": "alibaba/qwen3-coder-plus", + "id": "alibaba/qwen3-embedding-0.6b", "object": "model", "created": 1755815280, - "released": 1753228800, + "released": 1763078400, "owned_by": "alibaba", - "name": "Qwen3 Coder Plus", - "description": "Powered by Qwen3 this is a powerful Coding Agent that excels in tool calling and environment interaction to achieve autonomous programming. It combines outstanding coding proficiency with versatile general-purpose abilities.", - "context_window": 1000000, - "max_tokens": 65536, - "type": "language", - "zdr": "all", - "no_training": "all", - "tags": ["implicit-caching", "tool-use"], - "supported_specifications": ["v2", "v3", "v4"], - "modalities": { - "input": ["text"], - "output": ["text"] - }, - "supported_parameters": [ - "max_tokens", - "temperature", - "stop", - "tools", - "tool_choice" - ], - "temperature": true, - "knowledge": "2025-04", - "pricing": { - "input": "0.000001", - "input_tiers": [ - { - "cost": "0.000001", - "min": 0, - "max": 32001 - }, - { - "cost": "0.0000018", - "min": 32001, - "max": 128001 - }, - { - "cost": "0.000003", - "min": 128001, - "max": 256001 - }, - { - "cost": "0.000006", - "min": 256001 - } - ], - "output": "0.000005", - "output_tiers": [ - { - "cost": "0.000005", - "min": 0, - "max": 32001 - }, - { - "cost": "0.000009", - "min": 32001, - "max": 128001 - }, - { - "cost": "0.000015", - "min": 128001, - "max": 256001 - }, - { - "cost": "0.00006", - "min": 256001 - } - ], - "input_cache_read": "0.0000002", - "input_cache_read_tiers": [ - { - "cost": "0.0000002", - "min": 0, - "max": 32001 - }, - { - "cost": "0.00000036", - "min": 32001, - "max": 128001 - }, - { - "cost": "0.0000006", - "min": 128001, - "max": 256001 - }, - { - "cost": "0.0000012", - "min": 256001 - } - ] - } - }, - { - "id": "alibaba/qwen3-embedding-0.6b", - "object": "model", - "created": 1755815280, - "released": 1763078400, - "owned_by": "alibaba", - "name": "Qwen3 Embedding 0.6B", - "description": "The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B).", - "context_window": 32768, - "max_tokens": 32768, - "type": "embedding", + "name": "Qwen3 Embedding 0.6B", + "description": "The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B).", + "context_window": 32768, + "max_tokens": 32768, + "type": "embedding", "zdr": "all", "no_training": "all", + "tags": ["open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -607,6 +313,7 @@ "type": "embedding", "zdr": "all", "no_training": "all", + "tags": ["open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -629,6 +336,7 @@ "type": "embedding", "zdr": "all", "no_training": "all", + "tags": ["open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -638,183 +346,6 @@ "input": "0.00000001" } }, - { - "id": "alibaba/qwen3-max", - "object": "model", - "created": 1755815280, - "released": 1758585600, - "owned_by": "alibaba", - "name": "Qwen3 Max", - "description": "The Qwen 3 series Max model has undergone specialized upgrades in agent programming and tool invocation compared to the preview version. The officially released model this time has achieved state-of-the-art (SOTA) performance in its field and is better suited to meet the demands of agents operating in more complex scenarios.", - "context_window": 262144, - "max_tokens": 32768, - "type": "language", - "zdr": "some", - "no_training": "some", - "tags": ["tool-use", "implicit-caching", "structured-output"], - "supported_specifications": ["v2", "v3", "v4"], - "modalities": { - "input": ["text"], - "output": ["text"] - }, - "supported_parameters": [ - "max_tokens", - "temperature", - "stop", - "tools", - "tool_choice", - "reasoning", - "include_reasoning", - "response_format", - "structured_outputs" - ], - "temperature": true, - "reasoning_options": [ - { - "type": "effort", - "values": ["none", "minimal", "low", "medium", "high", "xhigh", "max"] - } - ], - "knowledge": "2025-04", - "pricing": { - "input": "0.0000012", - "input_tiers": [ - { - "cost": "0.0000012", - "min": 0, - "max": 32001 - }, - { - "cost": "0.0000024", - "min": 32001, - "max": 128001 - }, - { - "cost": "0.000003", - "min": 128001 - } - ], - "output": "0.000006", - "output_tiers": [ - { - "cost": "0.000006", - "min": 0, - "max": 32001 - }, - { - "cost": "0.000012", - "min": 32001, - "max": 128001 - }, - { - "cost": "0.000015", - "min": 128001 - } - ], - "input_cache_read": "0.00000024", - "input_cache_read_tiers": [ - { - "cost": "0.00000024", - "min": 0, - "max": 32001 - }, - { - "cost": "0.00000048", - "min": 32001, - "max": 128001 - }, - { - "cost": "0.0000006", - "min": 128001 - } - ], - "varies_by_provider": true - } - }, - { - "id": "alibaba/qwen3-max-preview", - "object": "model", - "created": 1755815280, - "released": 1757030400, - "owned_by": "alibaba", - "name": "Qwen3 Max Preview", - "description": "Qwen3-Max-Preview shows substantial gains over the 2.5 series in overall capability, with significant enhancements in Chinese-English text understanding, complex instruction following, handling of subjective open-ended tasks, multilingual ability, and tool invocation; model knowledge hallucinations are reduced.", - "context_window": 262144, - "max_tokens": 32768, - "type": "language", - "zdr": "all", - "no_training": "all", - "tags": ["tool-use", "implicit-caching", "structured-output"], - "supported_specifications": ["v2", "v3", "v4"], - "modalities": { - "input": ["text"], - "output": ["text"] - }, - "supported_parameters": [ - "max_tokens", - "temperature", - "stop", - "tools", - "tool_choice", - "response_format", - "structured_outputs" - ], - "temperature": true, - "knowledge": "2025-04", - "pricing": { - "input": "0.0000012", - "input_tiers": [ - { - "cost": "0.0000012", - "min": 0, - "max": 32001 - }, - { - "cost": "0.0000024", - "min": 32001, - "max": 128001 - }, - { - "cost": "0.000003", - "min": 128001 - } - ], - "output": "0.000006", - "output_tiers": [ - { - "cost": "0.000006", - "min": 0, - "max": 32001 - }, - { - "cost": "0.000012", - "min": 32001, - "max": 128001 - }, - { - "cost": "0.000015", - "min": 128001 - } - ], - "input_cache_read": "0.00000024", - "input_cache_read_tiers": [ - { - "cost": "0.00000024", - "min": 0, - "max": 32001 - }, - { - "cost": "0.00000048", - "min": 32001, - "max": 128001 - }, - { - "cost": "0.0000006", - "min": 128001 - } - ] - } - }, { "id": "alibaba/qwen3-max-thinking", "object": "model", @@ -919,9 +450,9 @@ "context_window": 262114, "max_tokens": 262114, "type": "language", - "zdr": "some", - "no_training": "some", - "tags": ["tool-use", "structured-output"], + "zdr": "all", + "no_training": "all", + "tags": ["tool-use", "structured-output", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -957,7 +488,7 @@ "type": "language", "zdr": "all", "no_training": "all", - "tags": ["reasoning", "tool-use", "structured-output"], + "tags": ["reasoning", "tool-use", "structured-output", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -988,19 +519,19 @@ } }, { - "id": "alibaba/qwen3-vl-235b-a22b-instruct", + "id": "alibaba/qwen3-vl-instruct", "object": "model", "created": 1755815280, "released": 1758585600, "owned_by": "alibaba", "name": "Qwen3 VL 235B A22B Instruct", "description": "The Qwen3 series VL models has been comprehensively upgraded in areas such as visual coding and spatial perception. Its visual perception and recognition capabilities have significantly improved, supporting the understanding of ultra-long videos, and its OCR functionality has undergone a major enhancement.", - "context_window": 131072, - "max_tokens": 129024, + "context_window": 262144, + "max_tokens": 262144, "type": "language", "zdr": "all", "no_training": "all", - "tags": ["tool-use", "vision", "implicit-caching"], + "tags": ["implicit-caching", "tool-use", "vision", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text", "image"], @@ -1014,102 +545,23 @@ "tool_choice" ], "temperature": true, - "knowledge": "2025-03-31", + "knowledge": "2025-04", "pricing": { - "input": "0.0000004", - "output": "0.0000016", - "varies_by_provider": true + "input": "0.0000002", + "output": "0.00000088", + "input_cache_read": "0.00000011" } }, { - "id": "alibaba/qwen3-vl-instruct", + "id": "alibaba/qwen3.5-flash", "object": "model", "created": 1755815280, - "released": 1758585600, + "released": 1771891200, "owned_by": "alibaba", - "name": "Qwen3 VL 235B A22B Instruct", - "description": "The Qwen3 series VL models has been comprehensively upgraded in areas such as visual coding and spatial perception. Its visual perception and recognition capabilities have significantly improved, supporting the understanding of ultra-long videos, and its OCR functionality has undergone a major enhancement.", - "context_window": 131072, - "max_tokens": 129024, - "type": "language", - "zdr": "some", - "no_training": "some", - "tags": ["tool-use", "vision", "implicit-caching", "structured-output"], - "supported_specifications": ["v2", "v3", "v4"], - "modalities": { - "input": ["text", "image"], - "output": ["text"] - }, - "supported_parameters": [ - "max_tokens", - "temperature", - "stop", - "tools", - "tool_choice", - "response_format", - "structured_outputs" - ], - "temperature": true, - "knowledge": "2025-04", - "pricing": { - "input": "0.0000004", - "output": "0.0000016", - "varies_by_provider": true - } - }, - { - "id": "alibaba/qwen3-vl-thinking", - "object": "model", - "created": 1755815280, - "released": 1758585600, - "owned_by": "alibaba", - "name": "Qwen3 VL 235B A22B Thinking", - "description": "Qwen3 series VL models feature significantly enhanced multimodal reasoning capabilities, with a particular focus on optimizing the model for STEM and mathematical reasoning. Visual perception and recognition abilities have been comprehensively improved, and OCR capabilities have undergone a major upgrade.", - "context_window": 131072, - "max_tokens": 32768, - "type": "language", - "zdr": "some", - "no_training": "some", - "tags": ["vision", "reasoning", "tool-use", "file-input"], - "supported_specifications": ["v2", "v3", "v4"], - "modalities": { - "input": ["text", "image", "pdf"], - "output": ["text"] - }, - "supported_parameters": [ - "max_tokens", - "temperature", - "stop", - "tools", - "tool_choice", - "reasoning", - "include_reasoning" - ], - "temperature": true, - "reasoning_options": [ - { - "type": "budget_tokens", - "min": 1, - "max": 81920 - } - ], - "knowledge": "2025-09", - "pricing": { - "input": "0.0000004", - "output": "0.000004", - "varies_by_provider": true - } - }, - { - "id": "alibaba/qwen3.5-flash", - "object": "model", - "created": 1755815280, - "released": 1771891200, - "owned_by": "alibaba", - "name": "Qwen 3.5 Flash", - "description": "The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the 3 series, these models deliver a leap forward in performance for both pure text and multimodal tasks, offering fast response times while balancing inference speed and overall performance.", - "context_window": 1000000, - "max_tokens": 64000, + "name": "Qwen 3.5 Flash", + "description": "The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the 3 series, these models deliver a leap forward in performance for both pure text and multimodal tasks, offering fast response times while balancing inference speed and overall performance.", + "context_window": 1000000, + "max_tokens": 64000, "type": "language", "zdr": "all", "no_training": "all", @@ -1270,7 +722,7 @@ "type": "language", "zdr": "all", "no_training": "all", - "tags": ["reasoning", "tool-use", "file-input", "vision"], + "tags": ["reasoning", "tool-use", "file-input", "vision", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text", "image", "pdf"], @@ -1702,6 +1154,7 @@ "tool-use", "implicit-caching", "structured-output", + "open-weights", "vision" ], "supported_specifications": ["v2", "v3", "v4"], @@ -1755,6 +1208,7 @@ "video-input", "file-input", "explicit-caching", + "open-weights", "structured-output" ], "supported_specifications": ["v2", "v3", "v4"], @@ -2085,7 +1539,7 @@ "type": "video", "zdr": "all", "no_training": "all", - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v3", "v4"], "modalities": { "input": ["text"], "output": ["video"] @@ -2140,7 +1594,7 @@ "type": "video", "zdr": "all", "no_training": "all", - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v3", "v4"], "modalities": { "input": ["text"], "output": ["video"] @@ -2201,7 +1655,7 @@ "type": "video", "zdr": "all", "no_training": "all", - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v3", "v4"], "modalities": { "input": ["text"], "output": ["video"] @@ -2262,7 +1716,7 @@ "type": "video", "zdr": "all", "no_training": "all", - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v3", "v4"], "modalities": { "input": ["text"], "output": ["video"] @@ -2323,7 +1777,7 @@ "type": "video", "zdr": "all", "no_training": "all", - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v3", "v4"], "modalities": { "input": ["text"], "output": ["video"] @@ -2384,7 +1838,7 @@ "type": "video", "zdr": "all", "no_training": "all", - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v3", "v4"], "modalities": { "input": ["text"], "output": ["video"] @@ -2437,7 +1891,7 @@ "type": "video", "zdr": "all", "no_training": "all", - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v3", "v4"], "modalities": { "input": ["text"], "output": ["video"] @@ -2509,7 +1963,7 @@ "type": "video", "zdr": "all", "no_training": "all", - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v3", "v4"], "modalities": { "input": ["text"], "output": ["video"] @@ -2563,7 +2017,7 @@ "zdr": "all", "no_training": "all", "tags": ["vision", "video-input", "audio-input"], - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v3", "v4"], "modalities": { "input": ["text", "audio", "image", "video"], "output": ["video"] @@ -2657,7 +2111,7 @@ "zdr": "all", "no_training": "all", "tags": ["vision", "video-input", "audio-input"], - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v3", "v4"], "modalities": { "input": ["text", "audio", "image", "video"], "output": ["video"] @@ -2781,7 +2235,7 @@ }, { "type": "effort", - "values": ["low", "medium", "high"] + "values": ["none", "low", "medium", "high"] } ], "knowledge": "2024-10", @@ -2952,49 +2406,73 @@ } }, { - "id": "anthropic/claude-3-haiku", + "id": "anthropic/claude-fable-5", "object": "model", "created": 1755815280, - "released": 1710288000, + "released": 1782864000, "owned_by": "anthropic", - "name": "Claude 3 Haiku", - "description": "Claude 3 Haiku is Anthropic's fastest, most compact model for near-instant responsiveness. It answers simple queries and requests with speed. Customers will be able to build seamless AI experiences that mimic human interactions. Claude 3 Haiku can process images and return text outputs, and features a 200K context window.", - "context_window": 200000, - "max_tokens": 4096, + "name": "Claude Fable 5", + "description": "Claude Fable 5 is a Mythos-class model with robust safeguards. It can handle long-running, complex, and asynchronous tasks where previous models would have needed more frequent check-ins.", + "context_window": 1000000, + "max_tokens": 128000, "type": "language", - "zdr": "all", + "zdr": "none", "no_training": "all", - "tags": ["tool-use", "vision", "explicit-caching", "structured-output"], + "tags": [ + "reasoning", + "tool-use", + "explicit-caching", + "file-input", + "vision", + "structured-output" + ], + "regions": ["us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { - "input": ["text", "image"], + "input": ["text", "image", "pdf"], "output": ["text"] }, "supported_parameters": [ "max_tokens", - "temperature", "stop", "tools", "tool_choice", + "reasoning", + "include_reasoning", "response_format", "structured_outputs" ], - "temperature": true, - "knowledge": "2023-08-31", + "temperature": false, + "reasoning_options": [ + { + "type": "effort", + "values": ["low", "medium", "high", "xhigh", "max"] + } + ], + "knowledge": "2026-01-31", "pricing": { - "input": "0.00000025", - "output": "0.00000125", - "input_cache_read": "0.00000003", - "input_cache_write": "0.0000003" + "input": "0.00001", + "output": "0.00005", + "input_cache_read": "0.000001", + "input_cache_write": "0.0000125", + "web_search": "10", + "regional": { + "us": { + "input": "0.000011", + "output": "0.000055", + "input_cache_read": "0.0000011", + "input_cache_write": "0.00001375" + } + } } }, { - "id": "anthropic/claude-fable-5", + "id": "anthropic/claude-fable-5-batch", "object": "model", "created": 1755815280, "released": 1782864000, "owned_by": "anthropic", - "name": "Claude Fable 5", + "name": "Claude Fable 5 (Batch)", "description": "Claude Fable 5 is a Mythos-class model with robust safeguards. It can handle long-running, complex, and asynchronous tasks where previous models would have needed more frequent check-ins.", "context_window": 1000000, "max_tokens": 128000, @@ -3009,8 +2487,7 @@ "vision", "structured-output" ], - "regions": ["us"], - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v4"], "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] @@ -3027,32 +2504,17 @@ ], "temperature": false, "reasoning_options": [ - { - "type": "toggle" - }, { "type": "effort", - "values": ["none", "low", "medium", "high", "xhigh", "max"] - }, - { - "type": "budget_tokens" + "values": ["low", "medium", "high", "xhigh", "max"] } ], "knowledge": "2026-01-31", "pricing": { - "input": "0.00001", - "output": "0.00005", - "input_cache_read": "0.000001", - "input_cache_write": "0.0000125", - "web_search": "10", - "regional": { - "us": { - "input": "0.000011", - "output": "0.000055", - "input_cache_read": "0.0000011", - "input_cache_write": "0.00001375" - } - } + "input": "0.000005", + "output": "0.000025", + "input_cache_read": "0.0000005", + "input_cache_write": "0.00000625" } }, { @@ -3095,15 +2557,9 @@ ], "temperature": true, "reasoning_options": [ - { - "type": "toggle" - }, { "type": "effort", - "values": ["none", "low", "medium", "high", "xhigh", "max"] - }, - { - "type": "budget_tokens" + "values": ["low", "medium", "high", "xhigh", "max"] } ], "knowledge": "2026-06", @@ -3123,6 +2579,58 @@ } } }, + { + "id": "anthropic/claude-fable-5.1-batch", + "object": "model", + "created": 1755815280, + "released": 1788134400, + "owned_by": "anthropic", + "name": "Claude Fable 5.1 (Batch)", + "description": "Claude Fable 5.1 improves on Fable 5 across long-running agentic coding, knowledge work, and research, following instructions precisely over sessions that run unattended for hours.", + "context_window": 1000000, + "max_tokens": 128000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "reasoning", + "tool-use", + "explicit-caching", + "file-input", + "vision", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "effort", + "values": ["low", "medium", "high", "xhigh", "max"] + } + ], + "knowledge": "2026-06", + "pricing": { + "input": "0.000005", + "output": "0.000025", + "input_cache_read": "0.000000125", + "input_cache_write": "0.00000625" + } + }, { "id": "anthropic/claude-haiku-4.5", "object": "model", @@ -3197,26 +2705,27 @@ } }, { - "id": "anthropic/claude-opus-4", + "id": "anthropic/claude-haiku-4.5-batch", "object": "model", "created": 1755815280, - "released": 1747872000, + "released": 1760486400, "owned_by": "anthropic", - "name": "Claude Opus 4", - "description": "Claude Opus 4 is Anthropic's most powerful model yet and the state-of-the-art coding model. It delivers sustained performance on long-running tasks that require focused effort and thousands of steps, significantly expanding what AI agents can solve. Claude Opus 4 is ideal for powering frontier agent products and features.", + "name": "Claude Haiku 4.5 (Batch)", + "description": "Claude Haiku 4.5 matches Sonnet 4's performance on coding, computer use, and agent tasks at substantially lower cost and faster speeds. It delivers near-frontier performance and Claude’s unique character at a price point that works for scaled sub-agent deployments, free tier products, and intelligence-sensitive applications with budget constraints.", "context_window": 200000, - "max_tokens": 32000, + "max_tokens": 64000, "type": "language", - "zdr": "all", + "zdr": "none", "no_training": "all", "tags": [ + "explicit-caching", "file-input", "reasoning", "tool-use", "vision", - "explicit-caching" + "structured-output" ], - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v4"], "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] @@ -3228,7 +2737,9 @@ "tools", "tool_choice", "reasoning", - "include_reasoning" + "include_reasoning", + "response_format", + "structured_outputs" ], "temperature": true, "reasoning_options": [ @@ -3240,39 +2751,653 @@ "min": 1024 } ], - "knowledge": "2025-03-31", + "knowledge": "2025-02-28", + "interleaved": true, "pricing": { - "input": "0.000015", - "output": "0.000075", - "input_cache_read": "0.0000015", - "input_cache_write": "0.00001875", - "web_search": "10" + "input": "0.0000005", + "output": "0.0000025", + "input_cache_read": "0.00000005", + "input_cache_write": "0.000000625" + } + }, + { + "id": "anthropic/claude-haiku-5.5", + "object": "model", + "created": 1755815280, + "released": 1791331200, + "owned_by": "anthropic", + "name": "Claude Haiku 5.5", + "description": "Claude Haiku 5.5 brings adaptive reasoning to Anthropic’s low-cost Haiku family for everyday tasks, tool use, and scaled sub-agent deployments. It is the first Haiku with adjustable effort levels, letting developers balance reasoning depth and token usage for each task, with the option to turn thinking off for simpler requests.", + "context_window": 1000000, + "max_tokens": 128000, + "type": "language", + "zdr": "all", + "no_training": "all", + "tags": [ + "explicit-caching", + "file-input", + "reasoning", + "tool-use", + "vision", + "web-search", + "structured-output" + ], + "regions": ["au", "eu", "jp", "us"], + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": false, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high", "xhigh", "max"] + } + ], + "pricing": { + "input": "0.0000001", + "input_tiers": [ + { + "cost": "0.0000001", + "min": 0, + "max": 100001 + }, + { + "cost": "0.0000005", + "min": 100001 + } + ], + "output": "0.0000005", + "output_tiers": [ + { + "cost": "0.0000005", + "min": 0, + "max": 100001 + }, + { + "cost": "0.0000025", + "min": 100001 + } + ], + "input_cache_read": "0.00000001", + "input_cache_read_tiers": [ + { + "cost": "0.00000001", + "min": 0, + "max": 100001 + }, + { + "cost": "0.00000005", + "min": 100001 + } + ], + "input_cache_write": "0.000000125", + "input_cache_write_tiers": [ + { + "cost": "0.000000125", + "min": 0, + "max": 100001 + }, + { + "cost": "0.000000625", + "min": 100001 + } + ], + "web_search": "10", + "regional": { + "au": { + "input": "0.00000011", + "input_tiers": [ + { + "cost": "0.00000011", + "min": 0, + "max": 100001 + }, + { + "cost": "0.00000055", + "min": 100001 + } + ], + "output": "0.00000055", + "output_tiers": [ + { + "cost": "0.00000055", + "min": 0, + "max": 100001 + }, + { + "cost": "0.00000275", + "min": 100001 + } + ], + "input_cache_read": "0.000000011", + "input_cache_read_tiers": [ + { + "cost": "0.000000011", + "min": 0, + "max": 100001 + }, + { + "cost": "0.000000055", + "min": 100001 + } + ], + "input_cache_write": "0.0000001375", + "input_cache_write_tiers": [ + { + "cost": "0.0000001375", + "min": 0, + "max": 100001 + }, + { + "cost": "0.0000006875", + "min": 100001 + } + ] + }, + "eu": { + "input": "0.00000011", + "input_tiers": [ + { + "cost": "0.00000011", + "min": 0, + "max": 100001 + }, + { + "cost": "0.00000055", + "min": 100001 + } + ], + "output": "0.00000055", + "output_tiers": [ + { + "cost": "0.00000055", + "min": 0, + "max": 100001 + }, + { + "cost": "0.00000275", + "min": 100001 + } + ], + "input_cache_read": "0.000000011", + "input_cache_read_tiers": [ + { + "cost": "0.000000011", + "min": 0, + "max": 100001 + }, + { + "cost": "0.000000055", + "min": 100001 + } + ], + "input_cache_write": "0.0000001375", + "input_cache_write_tiers": [ + { + "cost": "0.0000001375", + "min": 0, + "max": 100001 + }, + { + "cost": "0.0000006875", + "min": 100001 + } + ] + }, + "jp": { + "input": "0.00000011", + "input_tiers": [ + { + "cost": "0.00000011", + "min": 0, + "max": 100001 + }, + { + "cost": "0.00000055", + "min": 100001 + } + ], + "output": "0.00000055", + "output_tiers": [ + { + "cost": "0.00000055", + "min": 0, + "max": 100001 + }, + { + "cost": "0.00000275", + "min": 100001 + } + ], + "input_cache_read": "0.000000011", + "input_cache_read_tiers": [ + { + "cost": "0.000000011", + "min": 0, + "max": 100001 + }, + { + "cost": "0.000000055", + "min": 100001 + } + ], + "input_cache_write": "0.0000001375", + "input_cache_write_tiers": [ + { + "cost": "0.0000001375", + "min": 0, + "max": 100001 + }, + { + "cost": "0.0000006875", + "min": 100001 + } + ] + }, + "us": { + "input": "0.00000011", + "input_tiers": [ + { + "cost": "0.00000011", + "min": 0, + "max": 100001 + }, + { + "cost": "0.00000055", + "min": 100001 + } + ], + "output": "0.00000055", + "output_tiers": [ + { + "cost": "0.00000055", + "min": 0, + "max": 100001 + }, + { + "cost": "0.00000275", + "min": 100001 + } + ], + "input_cache_read": "0.000000011", + "input_cache_read_tiers": [ + { + "cost": "0.000000011", + "min": 0, + "max": 100001 + }, + { + "cost": "0.000000055", + "min": 100001 + } + ], + "input_cache_write": "0.0000001375", + "input_cache_write_tiers": [ + { + "cost": "0.0000001375", + "min": 0, + "max": 100001 + }, + { + "cost": "0.0000006875", + "min": 100001 + } + ] + } + } + } + }, + { + "id": "anthropic/claude-haiku-5.5-batch", + "object": "model", + "created": 1755815280, + "released": 1791331200, + "owned_by": "anthropic", + "name": "Claude Haiku 5.5 (Batch)", + "description": "Claude Haiku 5.5 brings adaptive reasoning to Anthropic’s low-cost Haiku family for everyday tasks, tool use, and scaled sub-agent deployments. It is the first Haiku with adjustable effort levels, letting developers balance reasoning depth and token usage for each task, with the option to turn thinking off for simpler requests.", + "context_window": 1000000, + "max_tokens": 128000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "explicit-caching", + "file-input", + "reasoning", + "tool-use", + "vision", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": false, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high", "xhigh", "max"] + } + ], + "pricing": { + "input": "0.00000005", + "input_tiers": [ + { + "cost": "0.00000005", + "min": 0, + "max": 100001 + }, + { + "cost": "0.00000025", + "min": 100001 + } + ], + "output": "0.00000025", + "output_tiers": [ + { + "cost": "0.00000025", + "min": 0, + "max": 100001 + }, + { + "cost": "0.00000125", + "min": 100001 + } + ], + "input_cache_read": "0.000000005", + "input_cache_read_tiers": [ + { + "cost": "0.000000005", + "min": 0, + "max": 100001 + }, + { + "cost": "0.000000025", + "min": 100001 + } + ], + "input_cache_write": "0.0000000625", + "input_cache_write_tiers": [ + { + "cost": "0.0000000625", + "min": 0, + "max": 100001 + }, + { + "cost": "0.0000003125", + "min": 100001 + } + ] + } + }, + { + "id": "anthropic/claude-opus-4.5", + "object": "model", + "created": 1755815280, + "released": 1763942400, + "owned_by": "anthropic", + "name": "Claude Opus 4.5", + "description": "Claude Opus 4.5 is Anthropic’s latest model in the Opus series, meant for demanding reasoning tasks and complex problem solving. This model has improvements in general intelligence and vision compared to previous iterations. In addition, it is suited for difficult coding tasks and agentic workflows, especially those with computer use and tool use, and can effectively handle context usage and external memory files.", + "context_window": 200000, + "max_tokens": 64000, + "type": "language", + "zdr": "all", + "no_training": "all", + "tags": [ + "explicit-caching", + "file-input", + "reasoning", + "tool-use", + "vision", + "web-search", + "structured-output" + ], + "regions": ["eu", "us"], + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high"] + }, + { + "type": "budget_tokens" + } + ], + "knowledge": "2025-05", + "interleaved": true, + "pricing": { + "input": "0.000005", + "output": "0.000025", + "input_cache_read": "0.0000005", + "input_cache_write": "0.00000625", + "web_search": "10", + "regional": { + "eu": { + "input": "0.0000055", + "output": "0.0000275", + "input_cache_read": "0.00000055", + "input_cache_write": "0.000006875" + }, + "us": { + "input": "0.0000055", + "output": "0.0000275", + "input_cache_read": "0.00000055", + "input_cache_write": "0.000006875" + } + } + } + }, + { + "id": "anthropic/claude-opus-4.5-batch", + "object": "model", + "created": 1755815280, + "released": 1763942400, + "owned_by": "anthropic", + "name": "Claude Opus 4.5 (Batch)", + "description": "Claude Opus 4.5 is Anthropic’s latest model in the Opus series, meant for demanding reasoning tasks and complex problem solving. This model has improvements in general intelligence and vision compared to previous iterations. In addition, it is suited for difficult coding tasks and agentic workflows, especially those with computer use and tool use, and can effectively handle context usage and external memory files.", + "context_window": 200000, + "max_tokens": 64000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "explicit-caching", + "file-input", + "reasoning", + "tool-use", + "vision", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high"] + }, + { + "type": "budget_tokens" + } + ], + "knowledge": "2025-05", + "interleaved": true, + "pricing": { + "input": "0.0000025", + "output": "0.0000125", + "input_cache_read": "0.00000025", + "input_cache_write": "0.000003125" + } + }, + { + "id": "anthropic/claude-opus-4.6", + "object": "model", + "created": 1755815280, + "released": 1770249600, + "owned_by": "anthropic", + "name": "Claude Opus 4.6", + "description": "Opus 4.6 is the world’s best model for coding and professional work, built to power agents that take on whole categories of real-world work. It excels across the entire SDLC, breaking through on hard problems, identifying complex bugs, and demonstrating deeper codebase understanding. It also delivers a step-change in knowledge work, with near-production-ready documents, presentations, and spreadsheets on the first pass.", + "context_window": 1000000, + "max_tokens": 128000, + "type": "language", + "zdr": "all", + "no_training": "all", + "tags": [ + "tool-use", + "reasoning", + "vision", + "file-input", + "explicit-caching", + "web-search", + "structured-output" + ], + "regions": ["eu", "us"], + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high", "max"] + }, + { + "type": "budget_tokens" + } + ], + "knowledge": "2025-05-31", + "interleaved": true, + "pricing": { + "input": "0.000005", + "output": "0.000025", + "input_cache_read": "0.0000005", + "input_cache_write": "0.00000625", + "web_search": "10", + "regional": { + "eu": { + "input": "0.0000055", + "output": "0.0000275", + "input_cache_read": "0.00000055", + "input_cache_write": "0.000006875" + }, + "us": { + "input": "0.0000055", + "output": "0.0000275", + "input_cache_read": "0.00000055", + "input_cache_write": "0.000006875", + "fast": { + "input": "0.000033", + "output": "0.000165", + "input_cache_read": "0.0000033", + "input_cache_write": "0.00004125" + } + } + } } }, { - "id": "anthropic/claude-opus-4.5", + "id": "anthropic/claude-opus-4.6-batch", "object": "model", "created": 1755815280, - "released": 1763942400, + "released": 1770249600, "owned_by": "anthropic", - "name": "Claude Opus 4.5", - "description": "Claude Opus 4.5 is Anthropic’s latest model in the Opus series, meant for demanding reasoning tasks and complex problem solving. This model has improvements in general intelligence and vision compared to previous iterations. In addition, it is suited for difficult coding tasks and agentic workflows, especially those with computer use and tool use, and can effectively handle context usage and external memory files.", - "context_window": 200000, - "max_tokens": 64000, + "name": "Claude Opus 4.6 (Batch)", + "description": "Opus 4.6 is the world’s best model for coding and professional work, built to power agents that take on whole categories of real-world work. It excels across the entire SDLC, breaking through on hard problems, identifying complex bugs, and demonstrating deeper codebase understanding. It also delivers a step-change in knowledge work, with near-production-ready documents, presentations, and spreadsheets on the first pass.", + "context_window": 1000000, + "max_tokens": 128000, "type": "language", - "zdr": "all", + "zdr": "none", "no_training": "all", "tags": [ - "explicit-caching", - "file-input", - "reasoning", "tool-use", + "reasoning", "vision", - "web-search", + "file-input", + "explicit-caching", "structured-output" ], - "regions": ["eu", "us"], - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v4"], "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] @@ -3295,44 +3420,29 @@ }, { "type": "effort", - "values": ["none", "low", "medium", "high"] + "values": ["none", "low", "medium", "high", "max"] }, { "type": "budget_tokens" } ], - "knowledge": "2025-05", + "knowledge": "2025-05-31", "interleaved": true, "pricing": { - "input": "0.000005", - "output": "0.000025", - "input_cache_read": "0.0000005", - "input_cache_write": "0.00000625", - "web_search": "10", - "regional": { - "eu": { - "input": "0.0000055", - "output": "0.0000275", - "input_cache_read": "0.00000055", - "input_cache_write": "0.000006875" - }, - "us": { - "input": "0.0000055", - "output": "0.0000275", - "input_cache_read": "0.00000055", - "input_cache_write": "0.000006875" - } - } + "input": "0.0000025", + "output": "0.0000125", + "input_cache_read": "0.00000025", + "input_cache_write": "0.000003125" } }, { - "id": "anthropic/claude-opus-4.6", + "id": "anthropic/claude-opus-4.7", "object": "model", "created": 1755815280, - "released": 1770249600, + "released": 1776297600, "owned_by": "anthropic", - "name": "Claude Opus 4.6", - "description": "Opus 4.6 is the world’s best model for coding and professional work, built to power agents that take on whole categories of real-world work. It excels across the entire SDLC, breaking through on hard problems, identifying complex bugs, and demonstrating deeper codebase understanding. It also delivers a step-change in knowledge work, with near-production-ready documents, presentations, and spreadsheets on the first pass.", + "name": "Claude Opus 4.7", + "description": "Opus 4.7 builds on the coding and agentic strengths of Opus 4.6 with stronger performance on complex, multi-step tasks and more reliable agentic execution. It also brings improved performance on knowledge work, from drafting documents to building presentations and analyzing data.", "context_window": 1000000, "max_tokens": 128000, "type": "language", @@ -3371,14 +3481,13 @@ }, { "type": "effort", - "values": ["none", "low", "medium", "high", "max"] + "values": ["none", "low", "medium", "high", "xhigh", "max"] }, { "type": "budget_tokens" } ], - "knowledge": "2025-05-31", - "interleaved": true, + "knowledge": "2026-01-31", "pricing": { "input": "0.000005", "output": "0.000025", @@ -3408,17 +3517,17 @@ } }, { - "id": "anthropic/claude-opus-4.7", + "id": "anthropic/claude-opus-4.7-batch", "object": "model", "created": 1755815280, "released": 1776297600, "owned_by": "anthropic", - "name": "Claude Opus 4.7", + "name": "Claude Opus 4.7 (Batch)", "description": "Opus 4.7 builds on the coding and agentic strengths of Opus 4.6 with stronger performance on complex, multi-step tasks and more reliable agentic execution. It also brings improved performance on knowledge work, from drafting documents to building presentations and analyzing data.", "context_window": 1000000, "max_tokens": 128000, "type": "language", - "zdr": "all", + "zdr": "none", "no_training": "all", "tags": [ "tool-use", @@ -3426,11 +3535,9 @@ "vision", "file-input", "explicit-caching", - "web-search", "structured-output" ], - "regions": ["eu", "us"], - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v4"], "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] @@ -3461,31 +3568,10 @@ ], "knowledge": "2026-01-31", "pricing": { - "input": "0.000005", - "output": "0.000025", - "input_cache_read": "0.0000005", - "input_cache_write": "0.00000625", - "web_search": "10", - "regional": { - "eu": { - "input": "0.0000055", - "output": "0.0000275", - "input_cache_read": "0.00000055", - "input_cache_write": "0.000006875" - }, - "us": { - "input": "0.0000055", - "output": "0.0000275", - "input_cache_read": "0.00000055", - "input_cache_write": "0.000006875", - "fast": { - "input": "0.000033", - "output": "0.000165", - "input_cache_read": "0.0000033", - "input_cache_write": "0.00004125" - } - } - } + "input": "0.0000025", + "output": "0.0000125", + "input_cache_read": "0.00000025", + "input_cache_write": "0.000003125" } }, { @@ -3576,6 +3662,64 @@ } } }, + { + "id": "anthropic/claude-opus-4.8-batch", + "object": "model", + "created": 1755815280, + "released": 1779926400, + "owned_by": "anthropic", + "name": "Claude Opus 4.8 (Batch)", + "description": "Opus 4.8 is a focused upgrade to Opus 4.7 and is Anthropic's best generally available model for coding, agentic tasks, and enterprise workflows. It builds on the strengths of previous Opus models with stronger performance on complex, multi-step coding tasks. Anthropic recommends using it on long-horizon coding and agentic tasks. It is also stronger on professional work, including document drafting, data analysis, and presentations.", + "context_window": 1000000, + "max_tokens": 128000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "tool-use", + "reasoning", + "vision", + "file-input", + "explicit-caching", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high", "xhigh", "max"] + }, + { + "type": "budget_tokens" + } + ], + "knowledge": "2026-01", + "pricing": { + "input": "0.0000025", + "output": "0.0000125", + "input_cache_read": "0.00000025", + "input_cache_write": "0.000003125" + } + }, { "id": "anthropic/claude-opus-4.8-fast", "object": "model", @@ -3669,7 +3813,7 @@ "fast", "structured-output" ], - "regions": ["eu", "us"], + "regions": ["au", "eu", "us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text", "image", "pdf"], @@ -3712,6 +3856,12 @@ "input_cache_write": "0.0000125" }, "regional": { + "au": { + "input": "0.0000055", + "output": "0.0000275", + "input_cache_read": "0.00000055", + "input_cache_write": "0.000006875" + }, "eu": { "input": "0.0000055", "output": "0.0000275", @@ -3733,6 +3883,63 @@ } } }, + { + "id": "anthropic/claude-opus-5-batch", + "object": "model", + "created": 1755815280, + "released": 1784851200, + "owned_by": "anthropic", + "name": "Claude Opus 5 (Batch)", + "description": "Claude Opus 5 is the latest model in Anthropic's Opus family and a step-change improvement over Opus 4.8. It delivers major gains over Opus 4.8 in agentic coding, professional knowledge work, and long-horizon reasoning, and it is stronger per token across effort levels.", + "context_window": 1000000, + "max_tokens": 128000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "tool-use", + "reasoning", + "vision", + "file-input", + "explicit-caching", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": false, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high", "xhigh", "max"] + }, + { + "type": "budget_tokens" + } + ], + "knowledge": "2026-05", + "pricing": { + "input": "0.0000025", + "output": "0.0000125", + "input_cache_read": "0.00000025", + "input_cache_write": "0.000003125" + } + }, { "id": "anthropic/claude-opus-5-fast", "object": "model", @@ -3756,7 +3963,7 @@ "fast", "structured-output" ], - "regions": ["eu", "us"], + "regions": ["au", "eu", "us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text", "image", "pdf"], @@ -3825,7 +4032,7 @@ "web-search", "structured-output" ], - "regions": ["eu", "us"], + "regions": ["au", "eu", "jp", "us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text", "image", "pdf"], @@ -3862,12 +4069,24 @@ "input_cache_write": "0.00001" }, "regional": { + "au": { + "input": "0.0000044", + "output": "0.000022", + "input_cache_read": "0.00000022", + "input_cache_write": "0.0000055" + }, "eu": { "input": "0.0000044", "output": "0.000022", "input_cache_read": "0.00000022", "input_cache_write": "0.0000055" }, + "jp": { + "input": "0.0000044", + "output": "0.000022", + "input_cache_read": "0.00000022", + "input_cache_write": "0.0000055" + }, "us": { "input": "0.0000044", "output": "0.000022", @@ -3884,30 +4103,27 @@ } }, { - "id": "anthropic/claude-opus-5.5-fast", + "id": "anthropic/claude-opus-5.5-batch", "object": "model", "created": 1755815280, "released": 1790035200, "owned_by": "anthropic", - "name": "Claude Opus 5.5 (Fast)", + "name": "Claude Opus 5.5 (Batch)", "description": "Claude Opus 5.5 is a step-change improvement over Opus 5 for agentic coding, long-running agentic tasks, knowledge work, communication, and vision. It is more token-efficient per completed task and reports progress, findings, and next steps in clear language.", "context_window": 1000000, "max_tokens": 128000, "type": "language", - "zdr": "all", + "zdr": "none", "no_training": "all", "tags": [ "explicit-caching", - "fast", "file-input", "reasoning", "tool-use", "vision", - "web-search", "structured-output" ], - "regions": ["eu", "us"], - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v4"], "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] @@ -3921,52 +4137,46 @@ "include_reasoning", "response_format", "structured_outputs" - ], - "temperature": false, - "reasoning_options": [ - { - "type": "effort", - "values": ["low", "medium", "high", "xhigh", "max"] - } - ], - "knowledge": "2026-06", - "pricing": { - "input": "0.000008", - "output": "0.00004", - "input_cache_read": "0.0000004", - "input_cache_write": "0.00001", - "web_search": "10", - "regional": { - "us": { - "input": "0.0000088", - "output": "0.000044", - "input_cache_read": "0.00000044", - "input_cache_write": "0.000011" - } + ], + "temperature": false, + "reasoning_options": [ + { + "type": "effort", + "values": ["low", "medium", "high", "xhigh", "max"] } + ], + "knowledge": "2026-06", + "pricing": { + "input": "0.000002", + "output": "0.00001", + "input_cache_read": "0.0000001", + "input_cache_write": "0.0000025" } }, { - "id": "anthropic/claude-sonnet-4", + "id": "anthropic/claude-opus-5.5-fast", "object": "model", "created": 1755815280, - "released": 1747872000, + "released": 1790035200, "owned_by": "anthropic", - "name": "Claude Sonnet 4", - "description": "Claude Sonnet 4 balances impressive performance for coding with the right speed and cost for high-volume use cases: Coding: Handle everyday development tasks with enhanced performance-power code reviews, bug fixes, API integrations, and feature development with immediate feedback loops.", + "name": "Claude Opus 5.5 (Fast)", + "description": "Claude Opus 5.5 is a step-change improvement over Opus 5 for agentic coding, long-running agentic tasks, knowledge work, communication, and vision. It is more token-efficient per completed task and reports progress, findings, and next steps in clear language.", "context_window": 1000000, - "max_tokens": 64000, + "max_tokens": 128000, "type": "language", "zdr": "all", "no_training": "all", "tags": [ + "explicit-caching", + "fast", "file-input", "reasoning", "tool-use", "vision", - "explicit-caching", + "web-search", "structured-output" ], + "regions": ["au", "eu", "jp", "us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text", "image", "pdf"], @@ -3974,7 +4184,6 @@ }, "supported_parameters": [ "max_tokens", - "temperature", "stop", "tools", "tool_choice", @@ -3983,66 +4192,28 @@ "response_format", "structured_outputs" ], - "temperature": true, + "temperature": false, "reasoning_options": [ { - "type": "toggle" - }, - { - "type": "budget_tokens", - "min": 1024 + "type": "effort", + "values": ["low", "medium", "high", "xhigh", "max"] } ], - "knowledge": "2025-03-31", + "knowledge": "2026-06", "pricing": { - "input": "0.000003", - "input_tiers": [ - { - "cost": "0.000003", - "min": 0, - "max": 200001 - }, - { - "cost": "0.000006", - "min": 200001 - } - ], - "output": "0.000015", - "output_tiers": [ - { - "cost": "0.000015", - "min": 0, - "max": 200001 - }, - { - "cost": "0.0000225", - "min": 200001 - } - ], - "input_cache_read": "0.0000003", - "input_cache_read_tiers": [ - { - "cost": "0.0000003", - "min": 0, - "max": 200001 - }, - { - "cost": "0.0000006", - "min": 200001 - } - ], - "input_cache_write": "0.00000375", - "input_cache_write_tiers": [ - { - "cost": "0.00000375", - "min": 0, - "max": 200001 - }, - { - "cost": "0.0000075", - "min": 200001 + "input": "0.000008", + "output": "0.00004", + "input_cache_read": "0.0000004", + "input_cache_write": "0.00001", + "web_search": "10", + "regional": { + "us": { + "input": "0.0000088", + "output": "0.000044", + "input_cache_read": "0.00000044", + "input_cache_write": "0.000011" } - ] + } } }, { @@ -4249,6 +4420,105 @@ } } }, + { + "id": "anthropic/claude-sonnet-4.5-batch", + "object": "model", + "created": 1755815280, + "released": 1759104000, + "owned_by": "anthropic", + "name": "Claude Sonnet 4.5 (Batch)", + "description": "Claude Sonnet 4.5 is the newest model in the Sonnet series, offering improvements and updates over Sonnet 4.", + "context_window": 1000000, + "max_tokens": 64000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "explicit-caching", + "file-input", + "reasoning", + "tool-use", + "vision", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "budget_tokens", + "min": 1024 + } + ], + "knowledge": "2025-07-31", + "pricing": { + "input": "0.0000015", + "input_tiers": [ + { + "cost": "0.0000015", + "min": 0, + "max": 200001 + }, + { + "cost": "0.000003", + "min": 200001 + } + ], + "output": "0.0000075", + "output_tiers": [ + { + "cost": "0.0000075", + "min": 0, + "max": 200001 + }, + { + "cost": "0.00001125", + "min": 200001 + } + ], + "input_cache_read": "0.00000015", + "input_cache_read_tiers": [ + { + "cost": "0.00000015", + "min": 0, + "max": 200001 + }, + { + "cost": "0.0000003", + "min": 200001 + } + ], + "input_cache_write": "0.000001875", + "input_cache_write_tiers": [ + { + "cost": "0.000001875", + "min": 0, + "max": 200001 + }, + { + "cost": "0.00000375", + "min": 200001 + } + ] + } + }, { "id": "anthropic/claude-sonnet-4.6", "object": "model", @@ -4304,25 +4574,84 @@ "knowledge": "2025-08-31", "interleaved": true, "pricing": { - "input": "0.000003", - "output": "0.000015", - "input_cache_read": "0.0000003", - "input_cache_write": "0.00000375", - "web_search": "10", - "regional": { - "eu": { - "input": "0.0000033", - "output": "0.0000165", - "input_cache_read": "0.00000033", - "input_cache_write": "0.000004125" - }, - "us": { - "input": "0.0000033", - "output": "0.0000165", - "input_cache_read": "0.00000033", - "input_cache_write": "0.000004125" - } - } + "input": "0.000003", + "output": "0.000015", + "input_cache_read": "0.0000003", + "input_cache_write": "0.00000375", + "web_search": "10", + "regional": { + "eu": { + "input": "0.0000033", + "output": "0.0000165", + "input_cache_read": "0.00000033", + "input_cache_write": "0.000004125" + }, + "us": { + "input": "0.0000033", + "output": "0.0000165", + "input_cache_read": "0.00000033", + "input_cache_write": "0.000004125" + } + } + } + }, + { + "id": "anthropic/claude-sonnet-4.6-batch", + "object": "model", + "created": 1755815280, + "released": 1771286400, + "owned_by": "anthropic", + "name": "Claude Sonnet 4.6 (Batch)", + "description": "Claude Sonnet 4.6 is the most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation.", + "context_window": 1000000, + "max_tokens": 128000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "file-input", + "reasoning", + "tool-use", + "vision", + "explicit-caching", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high", "max"] + }, + { + "type": "budget_tokens" + } + ], + "knowledge": "2025-08-31", + "interleaved": true, + "pricing": { + "input": "0.0000015", + "output": "0.0000075", + "input_cache_read": "0.00000015", + "input_cache_write": "0.000001875" } }, { @@ -4347,7 +4676,7 @@ "web-search", "structured-output" ], - "regions": ["eu", "us"], + "regions": ["au", "eu", "us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text", "image", "pdf"], @@ -4384,6 +4713,12 @@ "input_cache_write": "0.0000025", "web_search": "10", "regional": { + "au": { + "input": "0.0000022", + "output": "0.000011", + "input_cache_read": "0.00000022", + "input_cache_write": "0.00000275" + }, "eu": { "input": "0.0000022", "output": "0.000011", @@ -4399,6 +4734,63 @@ } } }, + { + "id": "anthropic/claude-sonnet-5-batch", + "object": "model", + "created": 1755815280, + "released": 1782691200, + "owned_by": "anthropic", + "name": "Claude Sonnet 5 (Batch)", + "description": "Sonnet 5 is an upgrade to Sonnet 4.6, with gains across agentic coding and professional work. It builds on the strengths of previous Sonnet models, bringing top-tier intelligence at Sonnet pricing for coding, agents, and everyday professional work at scale.", + "context_window": 1000000, + "max_tokens": 128000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "reasoning", + "tool-use", + "explicit-caching", + "file-input", + "vision", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": false, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high", "xhigh", "max"] + }, + { + "type": "budget_tokens" + } + ], + "knowledge": "2026-01-31", + "pricing": { + "input": "0.000001", + "output": "0.000005", + "input_cache_read": "0.0000001", + "input_cache_write": "0.00000125" + } + }, { "id": "anthropic/claude-sonnet-5.5", "object": "model", @@ -4421,7 +4813,7 @@ "web-search", "structured-output" ], - "regions": ["eu", "us"], + "regions": ["au", "eu", "us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text", "image", "pdf"], @@ -4448,25 +4840,82 @@ "pricing": { "input": "0.000002", "output": "0.00001", - "input_cache_read": "0.0000002", + "input_cache_read": "0.0000001", "input_cache_write": "0.0000025", "web_search": "10", "regional": { + "au": { + "input": "0.0000022", + "output": "0.000011", + "input_cache_read": "0.00000011", + "input_cache_write": "0.00000275" + }, "eu": { "input": "0.0000022", "output": "0.000011", - "input_cache_read": "0.00000022", + "input_cache_read": "0.00000011", "input_cache_write": "0.00000275" }, "us": { "input": "0.0000022", "output": "0.000011", - "input_cache_read": "0.00000022", + "input_cache_read": "0.00000011", "input_cache_write": "0.00000275" } } } }, + { + "id": "anthropic/claude-sonnet-5.5-batch", + "object": "model", + "created": 1755815280, + "released": 1790553600, + "owned_by": "anthropic", + "name": "Claude Sonnet 5.5 (Batch)", + "description": "Claude Sonnet 5.5 is a step-change improvement over Sonnet 5 for well-scoped everyday work like building features, fixing bugs, and creating polished documents, slides, and spreadsheets. It also writes more clearly than Sonnet 5.", + "context_window": 1000000, + "max_tokens": 128000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "explicit-caching", + "file-input", + "reasoning", + "tool-use", + "vision", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": false, + "reasoning_options": [ + { + "type": "effort", + "values": ["low", "medium", "high", "xhigh", "max"] + } + ], + "knowledge": "2026-06", + "pricing": { + "input": "0.000001", + "output": "0.000005", + "input_cache_read": "0.00000005", + "input_cache_write": "0.00000125" + } + }, { "id": "arcee-ai/trinity-large-thinking", "object": "model", @@ -4480,7 +4929,7 @@ "type": "language", "zdr": "none", "no_training": "none", - "tags": ["reasoning", "tool-use", "structured-output"], + "tags": ["reasoning", "tool-use", "structured-output", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -4509,7 +4958,56 @@ ], "pricing": { "input": "0.00000025", - "output": "0.0000008" + "output": "0.0000008", + "input_cache_read": "0.00000006" + } + }, + { + "id": "baseten/elephant-1", + "object": "model", + "created": 1755815280, + "released": 1792540800, + "owned_by": "baseten", + "name": "Elephant-1", + "description": "Elephant-1 is a 9B decision model from Baseten's Base Labs for classification, routing, and scoring. It evaluates structured context against choice, yes/no, and ordered scoring questions and returns answer probabilities and confidence in a single forward pass, without generating free-form text. Applications can use these probabilities to select answers or set confidence thresholds.", + "context_window": 16384, + "max_tokens": 0, + "type": "evaluation", + "zdr": "all", + "no_training": "all", + "tags": ["open-weights"], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text"], + "output": ["text"] + }, + "pricing": { + "input": "0", + "output": "0" + } + }, + { + "id": "baseten/mammoth-1", + "object": "model", + "created": 1755815280, + "released": 1792540800, + "owned_by": "baseten", + "name": "Mammoth-1", + "description": "Mammoth-1 is a 27B decision model from Baseten's Base Labs, fine-tuned from Qwen3.5-27B for classification, routing, and scoring. It answers multiple-choice, yes/no, and ordered scoring questions with probabilities over predefined options rather than generated text. Shared-prefix caching reuses context across questions, while per-option probabilities support confidence thresholds and escalation decisions.", + "context_window": 16384, + "max_tokens": 0, + "type": "evaluation", + "zdr": "all", + "no_training": "all", + "tags": ["open-weights"], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text"], + "output": ["text"] + }, + "pricing": { + "input": "0", + "output": "0" } }, { @@ -4546,7 +5044,7 @@ "type": "image", "zdr": "none", "no_training": "none", - "tags": ["image-generation"], + "tags": ["image-generation", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -4567,7 +5065,7 @@ "type": "image", "zdr": "none", "no_training": "none", - "tags": ["image-generation"], + "tags": ["image-generation", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -4631,33 +5129,78 @@ "zdr": "none", "no_training": "none", "tags": ["image-generation"], - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v3", "v4"], + "modalities": { + "input": ["text"], + "output": ["image"] + }, + "pricing": { + "image": "0.048", + "image_dimension_quality_pricing": [ + { + "size": "768x768", + "cost": "0.041" + }, + { + "size": "1024x1024", + "cost": "0.048" + }, + { + "size": "1536x1536", + "cost": "0.07" + }, + { + "size": "2048x2048", + "cost": "0.1" + }, + { + "size": "4096x4096", + "cost": "0.607" + } + ] + } + }, + { + "id": "bfl/flux-3-image-klein", + "object": "model", + "created": 1755815280, + "released": 1792022400, + "owned_by": "bfl", + "name": "FLUX 3 Image Klein", + "description": "FLUX 3 Image Klein is Black Forest Labs’ smaller, faster image generation and editing model, with 5.6 billion parameters and open weights. It supports text-to-image generation, image editing, multiple reference images, and layouts specified with bounding boxes. The hosted API produces images across five resolution classes from 768 × 768 to 4K.", + "context_window": 0, + "max_tokens": 0, + "type": "image", + "zdr": "none", + "no_training": "none", + "tags": ["image-generation", "open-weights"], + "supported_specifications": ["v3", "v4"], "modalities": { "input": ["text"], "output": ["image"] }, "pricing": { - "image": "0.024", + "image": "0.009", "image_dimension_quality_pricing": [ { "size": "768x768", - "cost": "0.0205" + "cost": "0.008" }, { "size": "1024x1024", - "cost": "0.024" + "cost": "0.009" }, { "size": "1536x1536", - "cost": "0.035" + "cost": "0.011" }, { "size": "2048x2048", - "cost": "0.05" + "cost": "0.014" }, { "size": "4096x4096", - "cost": "0.3035" + "cost": "0.036" } ] } @@ -4676,7 +5219,7 @@ "zdr": "none", "no_training": "none", "tags": ["video-generation"], - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v3", "v4"], "modalities": { "input": ["text"], "output": ["video"] @@ -5020,7 +5563,7 @@ "zdr": "none", "no_training": "all", "tags": ["video-generation", "vision"], - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v3", "v4"], "modalities": { "input": ["text", "image"], "output": ["video"] @@ -5125,7 +5668,7 @@ "zdr": "none", "no_training": "all", "tags": ["vision", "video-generation"], - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v3", "v4"], "modalities": { "input": ["text", "image"], "output": ["video"] @@ -5212,7 +5755,7 @@ "zdr": "none", "no_training": "all", "tags": ["vision", "video-generation"], - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v3", "v4"], "modalities": { "input": ["text", "image"], "output": ["video"] @@ -5298,7 +5841,7 @@ "type": "video", "zdr": "none", "no_training": "all", - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v3", "v4"], "modalities": { "input": ["text"], "output": ["video"] @@ -5417,7 +5960,7 @@ "zdr": "none", "no_training": "all", "tags": ["video-generation"], - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v3", "v4"], "modalities": { "input": ["text"], "output": ["video"] @@ -5477,7 +6020,7 @@ "zdr": "none", "no_training": "all", "tags": ["video-generation"], - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v3", "v4"], "modalities": { "input": ["text"], "output": ["video"] @@ -5533,7 +6076,7 @@ "zdr": "none", "no_training": "all", "tags": ["video-generation"], - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v3", "v4"], "modalities": { "input": ["text"], "output": ["video"] @@ -5695,8 +6238,52 @@ "output": ["image"] }, "pricing": { - "input": "0.000000003", - "image": "0.035" + "input": "0.000000003", + "image": "0.035" + } + }, + { + "id": "callstack/apex", + "object": "model", + "created": 1755815280, + "released": 1791417600, + "owned_by": "callstack", + "name": "Apex", + "description": "Apex is Callstack’s agentic coding model for mobile and web development, optimized for React Native, React, and Next.js. With a 256K context window, it supports feature development, debugging, code reviews, testing, and large refactors.", + "context_window": 262144, + "max_tokens": 131072, + "type": "language", + "zdr": "none", + "no_training": "none", + "tags": ["implicit-caching", "reasoning", "vision", "tool-use"], + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["text", "image"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "xhigh"] + } + ], + "pricing": { + "input": "0.0000005", + "output": "0.000003", + "input_cache_read": "0.0000002" } }, { @@ -5712,7 +6299,7 @@ "type": "language", "zdr": "none", "no_training": "all", - "tags": ["tool-use", "structured-output"], + "tags": ["tool-use", "structured-output", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -5867,6 +6454,50 @@ }, "pricing": {} }, + { + "id": "cohere/rerank-v5-fast", + "object": "model", + "created": 1755815280, + "released": 1792540800, + "owned_by": "cohere", + "name": "Cohere Rerank 5 Fast", + "description": "Cohere Rerank 5 Fast is a multilingual text reranking model optimized for low latency and high throughput in search and agent workflows. It ranks documents and semi-structured data across more than 100 languages, with calibrated relevance scores and a 32,768-token context window per query-document pair.", + "context_window": 32768, + "max_tokens": 32768, + "type": "reranking", + "zdr": "none", + "no_training": "all", + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["text"], + "output": ["text"] + }, + "pricing": { + "input": "0.00000002" + } + }, + { + "id": "cohere/rerank-v5-pro", + "object": "model", + "created": 1755815280, + "released": 1792540800, + "owned_by": "cohere", + "name": "Cohere Rerank 5 Pro", + "description": "Cohere Rerank 5 Pro is a multilingual text reranking model for complex queries and long or domain-specific documents. It ranks documents and semi-structured data across more than 100 languages, with calibrated relevance scores and a 32,768-token context window per query-document pair.", + "context_window": 32768, + "max_tokens": 32768, + "type": "reranking", + "zdr": "none", + "no_training": "all", + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["text"], + "output": ["text"] + }, + "pricing": { + "input": "0.00000005" + } + }, { "id": "convaiinnovations/laya", "object": "model", @@ -5928,7 +6559,7 @@ "type": "language", "zdr": "all", "no_training": "all", - "tags": ["reasoning", "tool-use", "implicit-caching"], + "tags": ["reasoning", "tool-use", "open-weights", "implicit-caching"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -5973,7 +6604,13 @@ "type": "language", "zdr": "some", "no_training": "some", - "tags": ["implicit-caching", "reasoning", "tool-use", "structured-output"], + "tags": [ + "implicit-caching", + "reasoning", + "tool-use", + "structured-output", + "open-weights" + ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -6007,53 +6644,6 @@ "varies_by_provider": true } }, - { - "id": "deepseek/deepseek-v3.1-terminus", - "object": "model", - "created": 1755815280, - "released": 1758499200, - "owned_by": "deepseek", - "name": "DeepSeek V3.1 Terminus", - "description": "DeepSeek-V3.1-Terminus delivers more stable & reliable outputs across benchmarks compared to the previous version and addresses user feedback (i.e. language consistency and agent upgrades).", - "context_window": 131072, - "max_tokens": 65536, - "type": "language", - "zdr": "none", - "no_training": "none", - "tags": ["implicit-caching", "reasoning", "tool-use", "structured-output"], - "supported_specifications": ["v2", "v3", "v4"], - "modalities": { - "input": ["text"], - "output": ["text"] - }, - "supported_parameters": [ - "max_tokens", - "temperature", - "stop", - "tools", - "tool_choice", - "reasoning", - "include_reasoning", - "response_format", - "structured_outputs" - ], - "temperature": true, - "reasoning_options": [ - { - "type": "toggle" - }, - { - "type": "effort", - "values": ["none", "low", "medium", "high"] - } - ], - "knowledge": "2025-07", - "pricing": { - "input": "0.00000027", - "output": "0.000001", - "input_cache_read": "0.000000135" - } - }, { "id": "deepseek/deepseek-v3.2", "object": "model", @@ -6065,9 +6655,9 @@ "context_window": 128000, "max_tokens": 8000, "type": "language", - "zdr": "some", - "no_training": "some", - "tags": ["tool-use", "implicit-caching"], + "zdr": "all", + "no_training": "all", + "tags": ["tool-use", "open-weights", "implicit-caching"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -6110,9 +6700,9 @@ "context_window": 128000, "max_tokens": 8000, "type": "language", - "zdr": "some", - "no_training": "some", - "tags": ["tool-use", "implicit-caching"], + "zdr": "all", + "no_training": "all", + "tags": ["tool-use", "open-weights", "implicit-caching"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -6158,7 +6748,13 @@ "type": "language", "zdr": "some", "no_training": "some", - "tags": ["reasoning", "tool-use", "implicit-caching", "structured-output"], + "tags": [ + "reasoning", + "tool-use", + "implicit-caching", + "open-weights", + "structured-output" + ], "regions": ["us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { @@ -6214,7 +6810,13 @@ "type": "language", "zdr": "some", "no_training": "some", - "tags": ["reasoning", "tool-use", "implicit-caching", "structured-output"], + "tags": [ + "reasoning", + "tool-use", + "implicit-caching", + "open-weights", + "structured-output" + ], "regions": ["us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { @@ -6275,11 +6877,144 @@ "tool-use", "implicit-caching", "vision", - "structured-output" + "structured-output", + "open-weights" + ], + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["text", "image"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high"] + } + ], + "pricing": { + "input": "0.0000002156", + "output": "0.0000006468", + "input_cache_read": "0.0000000068", + "varies_by_provider": true + } + }, + { + "id": "deepseek/deepseek-v4-pro", + "object": "model", + "created": 1755815280, + "released": 1776902400, + "owned_by": "deepseek", + "name": "DeepSeek V4 Pro", + "description": "DeepSeek-V4 series incorporate several key upgrades in architecture and optimization: (1) a hybrid attention architecture that combines Compressed Sparse Attention (CSA)\nand Heavily Compressed Attention (HCA) to improve long-context efficiency; (2) ManifoldConstrained Hyper-Connections (mHC) that enhance conventional residual connections; (3)\nand the Muon optimizer for faster convergence and greater training stability", + "context_window": 1000000, + "max_tokens": 384000, + "type": "language", + "zdr": "some", + "no_training": "some", + "tags": [ + "implicit-caching", + "reasoning", + "tool-use", + "structured-output", + "open-weights" + ], + "regions": ["us"], + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["text"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "high", "max"] + } + ], + "knowledge": "2025-05", + "pricing": { + "input": "0.00000066", + "output": "0.00000198", + "input_cache_read": "0.000000022", + "peak_pricing": { + "multiplier": 2, + "windows": [ + { + "start_minute_utc": 60, + "end_minute_utc": 240, + "days_of_week": [1, 2, 3, 4, 5] + }, + { + "start_minute_utc": 360, + "end_minute_utc": 600, + "days_of_week": [1, 2, 3, 4, 5] + } + ], + "holiday_calendar": "cn" + }, + "varies_by_provider": true, + "regional": { + "us": { + "input": "0.00000132", + "output": "0.00000396", + "input_cache_read": "0.000000132" + } + } + } + }, + { + "id": "deepseek/deepseek-v4-pro-0813", + "object": "model", + "created": 1755815280, + "released": 1786492800, + "owned_by": "deepseek", + "name": "DeepSeek V4 Pro 0813", + "description": "This is the 8/13 updated weights version of DeepSeek V4 Pro.", + "context_window": 1000000, + "max_tokens": 384000, + "type": "language", + "zdr": "some", + "no_training": "some", + "tags": [ + "reasoning", + "tool-use", + "implicit-caching", + "structured-output", + "open-weights" ], + "regions": ["us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { - "input": ["text", "image"], + "input": ["text"], "output": ["text"] }, "supported_parameters": [ @@ -6300,34 +7035,58 @@ }, { "type": "effort", - "values": ["none", "low", "medium", "high"] + "values": ["none", "low", "high", "max"] } ], "pricing": { - "input": "0.0000002156", - "output": "0.0000006468", - "input_cache_read": "0.0000000068", - "varies_by_provider": true + "input": "0.00000066", + "output": "0.00000198", + "input_cache_read": "0.000000066", + "peak_pricing": { + "multiplier": 2, + "windows": [ + { + "start_minute_utc": 0, + "end_minute_utc": 840 + } + ] + }, + "varies_by_provider": true, + "regional": { + "us": { + "input": "0.00000132", + "output": "0.00000396", + "input_cache_read": "0.000000132" + } + } } }, { - "id": "deepseek/deepseek-v4-pro", + "id": "deepseek/deepseek-v4.1-flash", "object": "model", "created": 1755815280, - "released": 1776902400, + "released": 1788825600, "owned_by": "deepseek", - "name": "DeepSeek V4 Pro", - "description": "DeepSeek-V4 series incorporate several key upgrades in architecture and optimization: (1) a hybrid attention architecture that combines Compressed Sparse Attention (CSA)\nand Heavily Compressed Attention (HCA) to improve long-context efficiency; (2) ManifoldConstrained Hyper-Connections (mHC) that enhance conventional residual connections; (3)\nand the Muon optimizer for faster convergence and greater training stability", - "context_window": 1000000, - "max_tokens": 384000, + "name": "DeepSeek V4.1 Flash", + "description": "DeepSeek V4.1 Flash is an AI model from DeepSeek designed for fast, efficient multimodal interactions. It combines native multimodal capabilities with a new architecture focused on stronger performance, faster responses, and lower computational cost.", + "context_window": 1048576, + "max_tokens": 32768, "type": "language", "zdr": "some", "no_training": "some", - "tags": ["implicit-caching", "reasoning", "tool-use", "structured-output"], + "tags": [ + "reasoning", + "tool-use", + "implicit-caching", + "vision", + "structured-output", + "open-weights", + "file-input" + ], "regions": ["us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { - "input": ["text"], + "input": ["text", "image", "pdf"], "output": ["text"] }, "supported_parameters": [ @@ -6351,11 +7110,10 @@ "values": ["none", "low", "high", "max"] } ], - "knowledge": "2025-05", "pricing": { - "input": "0.00000066", - "output": "0.00000198", - "input_cache_read": "0.000000022", + "input": "0.000000075", + "output": "0.0000003", + "input_cache_read": "0.0000000015", "peak_pricing": { "multiplier": 2, "windows": [ @@ -6369,37 +7127,48 @@ "end_minute_utc": 600, "days_of_week": [1, 2, 3, 4, 5] } - ], - "holiday_calendar": "cn" + ] }, "varies_by_provider": true, + "fast": { + "input": "0.0000006", + "output": "0.0000024", + "input_cache_read": "0.000000014" + }, "regional": { "us": { - "input": "0.00000132", - "output": "0.00000396", - "input_cache_read": "0.000000132" + "input": "0.0000003", + "output": "0.0000012", + "input_cache_read": "0.000000007" } } } }, { - "id": "deepseek/deepseek-v4-pro-0813", + "id": "deepseek/deepseek-v4.1-flash-1017", "object": "model", "created": 1755815280, - "released": 1786492800, + "released": 1792195200, "owned_by": "deepseek", - "name": "DeepSeek V4 Pro 0813", - "description": "This is the 8/13 updated weights version of DeepSeek V4 Pro.", - "context_window": 1000000, - "max_tokens": 384000, + "name": "DeepSeek V4.1 Flash 1017", + "description": "DeepSeek V4.1 Flash 1017 served by Fireworks for multimodal reasoning, coding, tool calling, and structured output, with automatic prefix caching.", + "context_window": 1048576, + "max_tokens": 1048576, "type": "language", "zdr": "some", "no_training": "some", - "tags": ["reasoning", "tool-use", "implicit-caching", "structured-output"], + "tags": [ + "implicit-caching", + "reasoning", + "structured-output", + "tool-use", + "vision", + "open-weights" + ], "regions": ["us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { - "input": ["text"], + "input": ["text", "image"], "output": ["text"] }, "supported_parameters": [ @@ -6424,47 +7193,59 @@ } ], "pricing": { - "input": "0.00000066", - "output": "0.00000198", - "input_cache_read": "0.000000066", + "input": "0.000000075", + "output": "0.0000003", + "input_cache_read": "0.0000000015", "peak_pricing": { "multiplier": 2, "windows": [ { - "start_minute_utc": 0, - "end_minute_utc": 840 + "start_minute_utc": 60, + "end_minute_utc": 240, + "days_of_week": [1, 2, 3, 4, 5] + }, + { + "start_minute_utc": 360, + "end_minute_utc": 600, + "days_of_week": [1, 2, 3, 4, 5] } ] }, "varies_by_provider": true, + "fast": { + "input": "0.0000006", + "output": "0.0000024", + "input_cache_read": "0.000000014" + }, "regional": { "us": { - "input": "0.00000132", - "output": "0.00000396", - "input_cache_read": "0.000000132" + "input": "0.00000045", + "output": "0.0000018", + "input_cache_read": "0.000000009" } } } }, { - "id": "deepseek/deepseek-v4.1-flash", + "id": "deepseek/deepseek-v4.1-flash-1017-fast", "object": "model", "created": 1755815280, - "released": 1788825600, + "released": 1792195200, "owned_by": "deepseek", - "name": "DeepSeek V4.1 Flash", - "description": "DeepSeek V4.1 Flash is an AI model from DeepSeek designed for fast, efficient multimodal interactions. It combines native multimodal capabilities with a new architecture focused on stronger performance, faster responses, and lower computational cost.", + "name": "DeepSeek V4.1 Flash 1017 Fast", + "description": "Higher-throughput variant of DeepSeek V4.1 Flash 1017 served by Baseten for multimodal reasoning, tool calling, and structured output, with automatic prefix caching.", "context_window": 1048576, - "max_tokens": 32768, + "max_tokens": 262144, "type": "language", - "zdr": "some", - "no_training": "some", + "zdr": "all", + "no_training": "all", "tags": [ + "implicit-caching", "reasoning", + "structured-output", "tool-use", - "implicit-caching", "vision", - "structured-output" + "open-weights" ], "regions": ["us"], "supported_specifications": ["v2", "v3", "v4"], @@ -6490,24 +7271,18 @@ }, { "type": "effort", - "values": ["none", "low", "high", "max"] + "values": ["none", "low", "medium", "high"] } ], "pricing": { - "input": "0.0000003", - "output": "0.0000012", - "input_cache_read": "0.000000007", - "varies_by_provider": true, - "fast": { - "input": "0.0000003", - "output": "0.0000012", - "input_cache_read": "0.000000006" - }, + "input": "0.0000006", + "output": "0.0000024", + "input_cache_read": "0.000000014", "regional": { "us": { - "input": "0.0000003", - "output": "0.0000012", - "input_cache_read": "0.000000007" + "input": "0.0000006", + "output": "0.0000024", + "input_cache_read": "0.000000014" } } } @@ -6519,19 +7294,21 @@ "released": 1790640000, "owned_by": "deepseek", "name": "DeepSeek V4.1 Flash Fast", - "description": "Speed-optimized deployment of DeepSeek V4.1 Flash using tensor parallelism and DSpark speculative decoding for faster token output and lower latency.", + "description": "Higher-throughput variant of DeepSeek V4.1 Flash for responsive coding, reasoning, and agentic workloads.", "context_window": 1048576, - "max_tokens": 1000000, + "max_tokens": 32768, "type": "language", "zdr": "all", "no_training": "all", "tags": [ - "implicit-caching", "reasoning", - "structured-output", "tool-use", - "vision" + "implicit-caching", + "vision", + "structured-output", + "open-weights" ], + "regions": ["us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text", "image"], @@ -6559,9 +7336,55 @@ } ], "pricing": { - "input": "0.0000003", - "output": "0.0000012", - "input_cache_read": "0.000000006" + "input": "0.0000006", + "output": "0.0000024", + "input_cache_read": "0.000000014", + "regional": { + "us": { + "input": "0.0000006", + "output": "0.0000024", + "input_cache_read": "0.000000014" + } + } + } + }, + { + "id": "elorian/glimpse", + "object": "model", + "created": 1755815280, + "released": 1792108800, + "owned_by": "elorian", + "name": "Glimpse", + "description": "Glimpse is Elorian's visual reasoning model for image and video understanding, with a 220,000-token context window. It tracks objects across motion and viewpoints, interprets spatial relationships, and reasons about physical cause and effect. Designed for scientific chart analysis, video captioning, robotics planning, and visual counting, it combines multimodal understanding with an agent trained to use code and visual inspection tools.", + "context_window": 220000, + "max_tokens": 4096, + "type": "language", + "zdr": "none", + "no_training": "none", + "tags": ["implicit-caching", "reasoning", "video-input", "vision"], + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["text", "image", "video"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "reasoning", + "include_reasoning" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "effort", + "values": ["low", "medium", "xhigh"] + } + ], + "pricing": { + "input": "0.0000006", + "output": "0.000003", + "input_cache_read": "0.00000006" } }, { @@ -6612,6 +7435,27 @@ "input_cache_read": "0.0000003" } }, + { + "id": "fish-audio/drama-3", + "object": "model", + "created": 1755815280, + "released": 1791849600, + "owned_by": "fish-audio", + "name": "Drama 3", + "description": "Drama 3 is Fish Audio’s text-to-speech model, currently in preview, that lets you direct voice performances using natural-language instructions. It supports control over emotion, pacing, pauses, and vocal sounds, with tags that apply effects to specific words. Multi-speaker dialogue and directions written in different languages make it well suited to expressive voiceovers, character dialogue, and audio storytelling.", + "type": "speech", + "zdr": "none", + "no_training": "none", + "supported_specifications": ["v3", "v4"], + "modalities": { + "input": ["text"], + "output": ["audio"] + }, + "pricing": { + "input": "0.00001", + "speech_input_character_cost": "0.00001" + } + }, { "id": "fish-audio/s1", "object": "model", @@ -6766,18 +7610,75 @@ "output": "0.00000125" } }, - "regional": { - "eu": { - "input": "0.0000003", - "output": "0.0000025", - "input_cache_read": "0.00000003" - }, - "us": { - "input": "0.0000003", - "output": "0.0000025", - "input_cache_read": "0.00000003" - } + "regional": { + "eu": { + "input": "0.0000003", + "output": "0.0000025", + "input_cache_read": "0.00000003" + }, + "us": { + "input": "0.0000003", + "output": "0.0000025", + "input_cache_read": "0.00000003" + } + } + } + }, + { + "id": "google/gemini-2.5-flash-batch", + "object": "model", + "created": 1755815280, + "released": 1742428800, + "owned_by": "google", + "name": "Gemini 2.5 Flash (Batch)", + "description": "Gemini 2.5 Flash is a thinking model that offers great, well-rounded capabilities. It is designed to offer a balance between price and performance with multimodal support and a 1M token context window.", + "context_window": 1000000, + "max_tokens": 64000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "file-input", + "reasoning", + "tool-use", + "vision", + "implicit-caching", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high"] + }, + { + "type": "budget_tokens" } + ], + "knowledge": "2025-01", + "pricing": { + "input": "0.00000015", + "output": "0.00000125", + "input_cache_read": "0.00000003" } }, { @@ -6936,6 +7837,63 @@ } } }, + { + "id": "google/gemini-2.5-flash-lite-batch", + "object": "model", + "created": 1755815280, + "released": 1750118400, + "owned_by": "google", + "name": "Gemini 2.5 Flash Lite (Batch)", + "description": "Gemini 2.5 Flash-Lite is a balanced, low-latency model with configurable thinking budgets and tool connectivity (e.g., Google Search grounding and code execution). It supports multimodal input and offers a 1M-token context window.", + "context_window": 1048576, + "max_tokens": 65535, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "file-input", + "reasoning", + "tool-use", + "vision", + "implicit-caching", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high"] + }, + { + "type": "budget_tokens" + } + ], + "knowledge": "2025-01", + "pricing": { + "input": "0.00000005", + "output": "0.0000002", + "input_cache_read": "0.00000001" + } + }, { "id": "google/gemini-2.5-pro", "object": "model", @@ -7131,28 +8089,215 @@ } }, { - "id": "google/gemini-3-flash", + "id": "google/gemini-2.5-pro-batch", + "object": "model", + "created": 1755815280, + "released": 1742428800, + "owned_by": "google", + "name": "Gemini 2.5 Pro (Batch)", + "description": "Gemini 2.5 Pro is our most advanced reasoning Gemini model, capable of solving complex problems. Gemini 2.5 Pro can comprehend vast datasets and challenging problems from different information sources, including text, audio, images, video, and even entire code repositories.", + "context_window": 1048576, + "max_tokens": 65535, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "file-input", + "reasoning", + "tool-use", + "vision", + "implicit-caching", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high"] + }, + { + "type": "budget_tokens" + } + ], + "knowledge": "2025-01", + "pricing": { + "input": "0.000000625", + "input_tiers": [ + { + "cost": "0.000000625", + "min": 0, + "max": 200001 + }, + { + "cost": "0.00000125", + "min": 200001 + } + ], + "output": "0.000005", + "output_tiers": [ + { + "cost": "0.000005", + "min": 0, + "max": 200001 + }, + { + "cost": "0.0000075", + "min": 200001 + } + ], + "input_cache_read": "0.000000125", + "input_cache_read_tiers": [ + { + "cost": "0.000000125", + "min": 0, + "max": 200001 + }, + { + "cost": "0.00000025", + "min": 200001 + } + ] + } + }, + { + "id": "google/gemini-3-flash", + "object": "model", + "created": 1755815280, + "released": 1765929600, + "owned_by": "google", + "name": "Gemini 3 Flash", + "description": "Google's most intelligent model built for speed, combining frontier intelligence with superior search and grounding.", + "context_window": 1000000, + "max_tokens": 65000, + "type": "language", + "zdr": "some", + "no_training": "all", + "tags": [ + "reasoning", + "file-input", + "vision", + "tool-use", + "web-search", + "implicit-caching", + "structured-output" + ], + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "effort", + "values": ["low", "high"] + } + ], + "knowledge": "2025-03", + "pricing": { + "input": "0.0000005", + "input_tiers": [ + { + "cost": "0.0000005", + "min": 0, + "max": 200001 + }, + { + "cost": "0.0000005", + "min": 200001 + } + ], + "output": "0.000003", + "output_tiers": [ + { + "cost": "0.000003", + "min": 0, + "max": 200001 + }, + { + "cost": "0.000003", + "min": 200001 + } + ], + "input_cache_read": "0.00000005", + "input_cache_read_tiers": [ + { + "cost": "0.00000005", + "min": 0, + "max": 200001 + }, + { + "cost": "0.00000005", + "min": 200001 + } + ], + "web_search": "14", + "maps_search": "14", + "service_tiers": { + "priority": { + "input": "0.0000009", + "output": "0.0000054", + "input_cache_read": "0.00000009" + }, + "flex": { + "input": "0.00000025", + "output": "0.0000015" + } + } + } + }, + { + "id": "google/gemini-3-flash-batch", "object": "model", "created": 1755815280, "released": 1765929600, "owned_by": "google", - "name": "Gemini 3 Flash", + "name": "Gemini 3 Flash (Batch)", "description": "Google's most intelligent model built for speed, combining frontier intelligence with superior search and grounding.", "context_window": 1000000, - "max_tokens": 65000, + "max_tokens": 64000, "type": "language", - "zdr": "some", + "zdr": "none", "no_training": "all", "tags": [ "reasoning", "file-input", "vision", "tool-use", - "web-search", "implicit-caching", "structured-output" ], - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v4"], "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] @@ -7177,27 +8322,27 @@ ], "knowledge": "2025-03", "pricing": { - "input": "0.0000005", + "input": "0.00000025", "input_tiers": [ { - "cost": "0.0000005", + "cost": "0.00000025", "min": 0, "max": 200001 }, { - "cost": "0.0000005", + "cost": "0.00000025", "min": 200001 } ], - "output": "0.000003", + "output": "0.0000015", "output_tiers": [ { - "cost": "0.000003", + "cost": "0.0000015", "min": 0, "max": 200001 }, { - "cost": "0.000003", + "cost": "0.0000015", "min": 200001 } ], @@ -7212,20 +8357,7 @@ "cost": "0.00000005", "min": 200001 } - ], - "web_search": "14", - "maps_search": "14", - "service_tiers": { - "priority": { - "input": "0.0000009", - "output": "0.0000054", - "input_cache_read": "0.00000009" - }, - "flex": { - "input": "0.00000025", - "output": "0.0000015" - } - } + ] } }, { @@ -7532,6 +8664,57 @@ } } }, + { + "id": "google/gemini-3.1-flash-lite-batch", + "object": "model", + "created": 1755815280, + "released": 1778112000, + "owned_by": "google", + "name": "Gemini 3.1 Flash Lite (Batch)", + "description": "Gemini 3.1 Flash Lite outperforms 2.5 Flash Lite on overall quality and lands close to 2.5 Flash performance across key capability areas. It is a workhorse model for high-volume use cases, with improvements across audio input/ASR, RAG snippet ranking, translation, data extraction, and code completion.", + "context_window": 1000000, + "max_tokens": 65000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "reasoning", + "tool-use", + "implicit-caching", + "file-input", + "vision", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "effort", + "values": ["low", "high"] + } + ], + "knowledge": "2025-01", + "pricing": { + "input": "0.000000125", + "output": "0.00000075", + "input_cache_read": "0.000000015" + } + }, { "id": "google/gemini-3.1-flash-lite-image", "object": "model", @@ -7700,30 +8883,192 @@ } }, { - "id": "google/gemini-3.5-flash", + "id": "google/gemini-3.1-pro-preview-batch", + "object": "model", + "created": 1755815280, + "released": 1771459200, + "owned_by": "google", + "name": "Gemini 3.1 Pro Preview (Batch)", + "description": "Improved SWE and agentic capabilities, improved token efficiency and thinking, and expanded thinking levels.", + "context_window": 1000000, + "max_tokens": 64000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "file-input", + "tool-use", + "reasoning", + "vision", + "implicit-caching", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "effort", + "values": ["low", "high"] + } + ], + "knowledge": "2025-01", + "pricing": { + "input": "0.000001", + "input_tiers": [ + { + "cost": "0.000001", + "min": 0, + "max": 200001 + }, + { + "cost": "0.000002", + "min": 200001 + } + ], + "output": "0.000006", + "output_tiers": [ + { + "cost": "0.000006", + "min": 0, + "max": 200001 + }, + { + "cost": "0.000009", + "min": 200001 + } + ], + "input_cache_read": "0.0000002", + "input_cache_read_tiers": [ + { + "cost": "0.0000002", + "min": 0, + "max": 200001 + }, + { + "cost": "0.0000004", + "min": 200001 + } + ] + } + }, + { + "id": "google/gemini-3.5-flash", + "object": "model", + "created": 1755815280, + "released": 1779148800, + "owned_by": "google", + "name": "Gemini 3.5 Flash", + "description": "Google's latest model, highly optimized for coding proficiency and parallel agentic execution loops. Defaults to medium thinking effort for faster and more cost-efficient responses.", + "context_window": 1000000, + "max_tokens": 64000, + "type": "language", + "zdr": "some", + "no_training": "all", + "tags": [ + "reasoning", + "file-input", + "vision", + "tool-use", + "web-search", + "implicit-caching", + "video-input", + "structured-output" + ], + "regions": ["eu", "us"], + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["text", "image", "pdf", "video"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "effort", + "values": ["low", "high"] + } + ], + "knowledge": "2025-01", + "pricing": { + "input": "0.0000015", + "output": "0.000009", + "input_cache_read": "0.00000015", + "web_search": "14", + "maps_search": "14", + "service_tiers": { + "priority": { + "input": "0.0000027", + "output": "0.0000162", + "input_cache_read": "0.00000027" + }, + "flex": { + "input": "0.00000075", + "output": "0.0000045", + "input_cache_read": "0.00000008" + } + }, + "regional": { + "eu": { + "input": "0.00000165", + "output": "0.0000099", + "input_cache_read": "0.000000165" + }, + "us": { + "input": "0.00000165", + "output": "0.0000099", + "input_cache_read": "0.000000165" + } + } + } + }, + { + "id": "google/gemini-3.5-flash-batch", "object": "model", "created": 1755815280, "released": 1779148800, "owned_by": "google", - "name": "Gemini 3.5 Flash", + "name": "Gemini 3.5 Flash (Batch)", "description": "Google's latest model, highly optimized for coding proficiency and parallel agentic execution loops. Defaults to medium thinking effort for faster and more cost-efficient responses.", "context_window": 1000000, "max_tokens": 64000, "type": "language", - "zdr": "some", + "zdr": "none", "no_training": "all", "tags": [ "reasoning", "file-input", "vision", "tool-use", - "web-search", "implicit-caching", "video-input", "structured-output" ], - "regions": ["eu", "us"], - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v4"], "modalities": { "input": ["text", "image", "pdf", "video"], "output": ["text"] @@ -7748,35 +9093,9 @@ ], "knowledge": "2025-01", "pricing": { - "input": "0.0000015", - "output": "0.000009", - "input_cache_read": "0.00000015", - "web_search": "14", - "maps_search": "14", - "service_tiers": { - "priority": { - "input": "0.0000027", - "output": "0.0000162", - "input_cache_read": "0.00000027" - }, - "flex": { - "input": "0.00000075", - "output": "0.0000045", - "input_cache_read": "0.00000008" - } - }, - "regional": { - "eu": { - "input": "0.00000165", - "output": "0.0000099", - "input_cache_read": "0.000000165" - }, - "us": { - "input": "0.00000165", - "output": "0.0000099", - "input_cache_read": "0.000000165" - } - } + "input": "0.00000075", + "output": "0.0000045", + "input_cache_read": "0.000000075" } }, { @@ -7859,6 +9178,58 @@ } } }, + { + "id": "google/gemini-3.5-flash-lite-batch", + "object": "model", + "created": 1755815280, + "released": 1784592000, + "owned_by": "google", + "name": "Gemini 3.5 Flash Lite (Batch)", + "description": "Gemini 3.5 Flash Lite features upgraded agentic capabilities, making the model ideal for subagents in complex workflows.", + "context_window": 1000000, + "max_tokens": 65000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "reasoning", + "tool-use", + "implicit-caching", + "file-input", + "vision", + "video-input", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf", "video"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "effort", + "values": ["low", "high"] + } + ], + "knowledge": "2026-03", + "pricing": { + "input": "0.00000015", + "output": "0.00000125", + "input_cache_read": "0.000000015" + } + }, { "id": "google/gemini-3.5-transcribe", "object": "model", @@ -7995,6 +9366,58 @@ } } }, + { + "id": "google/gemini-3.6-flash-batch", + "object": "model", + "created": 1755815280, + "released": 1784592000, + "owned_by": "google", + "name": "Gemini 3.6 Flash (Batch)", + "description": "Gemini 3.6 Flash delivers higher quality across coding, agentic workflows, and web development with reduced token consumption and fewer model calls compared to previous model iterations.", + "context_window": 1000000, + "max_tokens": 64000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "reasoning", + "file-input", + "tool-use", + "vision", + "implicit-caching", + "video-input", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf", "video"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "effort", + "values": ["low", "high"] + } + ], + "knowledge": "2026-03", + "pricing": { + "input": "0.000000375", + "output": "0.000001875", + "input_cache_read": "0.0000000375" + } + }, { "id": "google/gemini-3.7-flash", "object": "model", @@ -8075,6 +9498,58 @@ } } }, + { + "id": "google/gemini-3.7-flash-batch", + "object": "model", + "created": 1755815280, + "released": 1786579200, + "owned_by": "google", + "name": "Gemini 3.7 Flash (Batch)", + "description": "Gemini 3.7 Flash is the next iteration in the Gemini 3 model family, featuring algorithmic improvements to its core reasoning foundation. It supports customizable thinking configurations to control the mix of quality, cost and latency.", + "context_window": 1000000, + "max_tokens": 65535, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "reasoning", + "file-input", + "vision", + "tool-use", + "implicit-caching", + "video-input", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf", "video"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "effort", + "values": ["low", "high"] + } + ], + "knowledge": "2026-03", + "pricing": { + "input": "0.000000375", + "output": "0.000001875", + "input_cache_read": "0.0000000375" + } + }, { "id": "google/gemini-3.8-flash", "object": "model", @@ -8282,12 +9757,91 @@ "type": "effort", "values": ["low", "high"] } - ], - "pricing": { - "input": "0.00000075", - "output": "0.0000045", - "audio_input_token_cost": "0.000003", - "audio_output_token_cost": "0.000012" + ], + "pricing": { + "input": "0.00000075", + "output": "0.0000045", + "audio_input_token_cost": "0.000003", + "audio_output_token_cost": "0.000012" + } + }, + { + "id": "google/gemini-4-argon", + "object": "model", + "created": 1755815280, + "released": 1791849600, + "owned_by": "google", + "name": "Gemini 4 Argon", + "description": "Gemini 4 Argon is Google’s multimodal reasoning model, supporting text, image, and file inputs with configurable reasoning levels. It combines tool calling, structured outputs, and Google Search and Maps grounding to support document analysis and agent workflows. Long-form generation supports continuation across requests, allowing applications to resume output beyond a single request’s token limit.", + "context_window": 1000000, + "max_tokens": 1000000, + "type": "language", + "zdr": "some", + "no_training": "all", + "tags": [ + "reasoning", + "file-input", + "vision", + "tool-use", + "web-search", + "implicit-caching", + "video-input", + "structured-output" + ], + "regions": ["eu", "us"], + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["text", "image", "pdf", "video"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "effort", + "values": ["low", "medium", "high"] + } + ], + "pricing": { + "input": "0.000002", + "output": "0.00001", + "input_cache_read": "0.0000001", + "web_search": "14", + "maps_search": "14", + "service_tiers": { + "priority": { + "input": "0.0000036", + "output": "0.000018", + "input_cache_read": "0.00000018" + }, + "flex": { + "input": "0.000001", + "output": "0.000005", + "input_cache_read": "0.00000005" + } + }, + "regional": { + "eu": { + "input": "0.0000022", + "output": "0.000011", + "input_cache_read": "0.00000011" + }, + "us": { + "input": "0.0000022", + "output": "0.000011", + "input_cache_read": "0.00000011" + } + } } }, { @@ -8484,6 +10038,7 @@ "tool-use", "vision", "structured-output", + "open-weights", "implicit-caching" ], "supported_specifications": ["v2", "v3", "v4"], @@ -8528,7 +10083,8 @@ "vision", "file-input", "reasoning", - "structured-output" + "structured-output", + "open-weights" ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { @@ -8549,7 +10105,8 @@ "temperature": true, "pricing": { "input": "0.00000014", - "output": "0.0000004" + "output": "0.0000004", + "varies_by_provider": true } }, { @@ -8609,7 +10166,7 @@ "type": "video", "zdr": "all", "no_training": "all", - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v3", "v4"], "modalities": { "input": ["text"], "output": ["video"] @@ -8669,7 +10226,7 @@ "type": "video", "zdr": "all", "no_training": "all", - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v3", "v4"], "modalities": { "input": ["text"], "output": ["video"] @@ -8729,7 +10286,7 @@ "type": "video", "zdr": "all", "no_training": "all", - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v3", "v4"], "modalities": { "input": ["text"], "output": ["video"] @@ -8810,7 +10367,7 @@ "type": "video", "zdr": "all", "no_training": "all", - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v3", "v4"], "modalities": { "input": ["text"], "output": ["video"] @@ -8891,7 +10448,7 @@ "type": "video", "zdr": "all", "no_training": "all", - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v3", "v4"], "modalities": { "input": ["text"], "output": ["video"] @@ -8942,6 +10499,118 @@ ] } }, + { + "id": "heygen/heygen-video-1", + "object": "model", + "created": 1755815280, + "released": 1791504000, + "owned_by": "heygen", + "name": "HeyGen Video", + "description": "HeyGen Video generates 5–15 second clips with synchronized dialogue, ambience, and sound effects from text, a first-frame image, or image and video references. It supports 480p, 768p, 1080p, and 2K output. Reference mode charges for input video seconds plus output video seconds; image and audio references have no additional charge.", + "context_window": 0, + "max_tokens": 0, + "type": "video", + "zdr": "none", + "no_training": "none", + "tags": ["vision", "video-generation"], + "supported_specifications": ["v3", "v4"], + "modalities": { + "input": ["text", "image"], + "output": ["video"] + }, + "video_capabilities": { + "supported_operations": [ + "text-to-video", + "image-to-video", + "reference-to-video" + ], + "supported_resolutions": ["480p", "768p", "1080p", "2k"], + "supported_aspect_ratios": ["21:9", "16:9", "4:3", "1:1", "3:4", "9:16"], + "supported_durations_seconds": [5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15], + "generate_audio": true, + "supported_fps": [24], + "max_sample_count": 1, + "input_limits": { + "image": { + "max_count": 9, + "supported_sources": ["url", "base64", "buffer"] + }, + "video": { + "max_count": 3, + "max_file_size_mb": 16, + "supported_sources": ["url", "base64", "buffer"], + "max_duration_seconds": 5 + }, + "audio": { + "supported_sources": ["url", "base64", "buffer"] + } + } + }, + "pricing": { + "video_duration_pricing": [ + { + "resolution": "480p", + "mode": "text_to_video", + "cost_per_second": "0.01" + }, + { + "resolution": "768p", + "mode": "text_to_video", + "cost_per_second": "0.018" + }, + { + "resolution": "1080p", + "mode": "text_to_video", + "cost_per_second": "0.05" + }, + { + "resolution": "2k", + "mode": "text_to_video", + "cost_per_second": "0.05" + }, + { + "resolution": "480p", + "mode": "image_to_video", + "cost_per_second": "0.01" + }, + { + "resolution": "768p", + "mode": "image_to_video", + "cost_per_second": "0.018" + }, + { + "resolution": "1080p", + "mode": "image_to_video", + "cost_per_second": "0.05" + }, + { + "resolution": "2k", + "mode": "image_to_video", + "cost_per_second": "0.05" + }, + { + "resolution": "480p", + "mode": "reference_to_video", + "cost_per_second": "0.035" + }, + { + "resolution": "768p", + "mode": "reference_to_video", + "cost_per_second": "0.05" + }, + { + "resolution": "1080p", + "mode": "reference_to_video", + "cost_per_second": "0.09" + }, + { + "resolution": "2k", + "mode": "reference_to_video", + "cost_per_second": "0.09" + } + ] + } + }, { "id": "inception/mercury-2", "object": "model", @@ -9028,6 +10697,49 @@ "input_cache_read": "0.000000004" } }, + { + "id": "inception/mercury-3", + "object": "model", + "created": 1755815280, + "released": 1792368000, + "owned_by": "inception", + "name": "Mercury 3", + "description": "Mercury 3 is Inception’s most capable model for agentic workflows and real-time applications. It is one of the world’s fastest models, powered by diffusion.", + "context_window": 1000000, + "max_tokens": 131072, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": ["implicit-caching", "reasoning", "structured-output", "tool-use"], + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["text"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "effort", + "values": ["instant", "low", "medium", "high"] + } + ], + "pricing": { + "input": "0.0000001", + "output": "0.00000035", + "input_cache_read": "0.00000001" + } + }, { "id": "inception/mercury-coder-small", "object": "model", @@ -9075,7 +10787,7 @@ "type": "language", "zdr": "none", "no_training": "none", - "tags": ["reasoning", "tool-use", "implicit-caching"], + "tags": ["reasoning", "tool-use", "implicit-caching", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -9115,7 +10827,13 @@ "type": "language", "zdr": "some", "no_training": "some", - "tags": ["implicit-caching", "reasoning", "tool-use", "structured-output"], + "tags": [ + "implicit-caching", + "reasoning", + "tool-use", + "structured-output", + "open-weights" + ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -9158,7 +10876,7 @@ "type": "language", "zdr": "none", "no_training": "none", - "tags": ["reasoning", "tool-use", "implicit-caching"], + "tags": ["reasoning", "tool-use", "implicit-caching", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -9202,7 +10920,7 @@ "type": "language", "zdr": "none", "no_training": "none", - "tags": ["reasoning", "tool-use", "video-input", "vision"], + "tags": ["reasoning", "tool-use", "video-input", "vision", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text", "image", "video"], @@ -9242,50 +10960,7 @@ "type": "language", "zdr": "none", "no_training": "none", - "tags": ["free", "reasoning", "tool-use", "implicit-caching"], - "supported_specifications": ["v2", "v3", "v4"], - "modalities": { - "input": ["text"], - "output": ["text"] - }, - "supported_parameters": [ - "max_tokens", - "temperature", - "stop", - "tools", - "tool_choice", - "reasoning", - "include_reasoning" - ], - "temperature": true, - "reasoning_options": [ - { - "type": "toggle" - }, - { - "type": "effort", - "values": ["none", "low", "medium", "high"] - } - ], - "pricing": { - "input": "0", - "output": "0" - } - }, - { - "id": "inclusionai/ling-3.1-flash-free", - "object": "model", - "created": 1755815280, - "released": 1790640000, - "owned_by": "inclusionai", - "name": "Ling 3.1 Flash (Free)", - "description": "Ling 3.1 Flash is InclusionAI's hybrid reasoning language model for coding, multi-step analysis, and tool-using agents. It has 560B total parameters with 25B activated parameters and supports long-context text workflows.", - "context_window": 262144, - "max_tokens": 32768, - "type": "language", - "zdr": "none", - "no_training": "none", - "tags": ["free", "reasoning", "tool-use", "implicit-caching"], + "tags": ["reasoning", "tool-use", "implicit-caching", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -9311,8 +10986,9 @@ } ], "pricing": { - "input": "0", - "output": "0" + "input": "0.0000003", + "output": "0.0000009", + "input_cache_read": "0.00000006" } }, { @@ -9934,14 +11610,82 @@ "type": "evaluation", "zdr": "none", "no_training": "none", + "tags": ["vision"], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image"], + "output": ["text"] + }, + "pricing": { + "input": "0.00000002", + "output": "0" + } + }, + { + "id": "liquid/d1-ultra", + "object": "model", + "created": 1755815280, + "released": 1792022400, + "owned_by": "liquid", + "name": "Liquid d1 Ultra", + "description": "Liquid d1-ultra is a multimodal decision model for classification, routing, and scoring across text and images, with a 32,768-token context window. It returns calibrated probabilities for yes/no, multiple-choice, and scale-based questions in a single forward pass without generating output tokens. It is designed for demanding real-world tasks such as visual defect inspection and evaluating damage claims against customer photos.", + "context_window": 32768, + "max_tokens": 0, + "type": "evaluation", + "zdr": "none", + "no_training": "none", + "tags": ["vision"], "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image"], + "output": ["text"] + }, + "pricing": { + "input": "0.000000042", + "output": "0" + } + }, + { + "id": "liquid/lfm2.5-24b-a2b", + "object": "model", + "created": 1755815280, + "released": 1791849600, + "owned_by": "liquid", + "name": "LFM2.5-24B-A2B", + "description": "LFM2.5-24B-A2B is a text-generation model from Liquid AI with a 128,000-token context window.", + "context_window": 128000, + "max_tokens": 8200, + "type": "language", + "zdr": "none", + "no_training": "none", + "tags": ["implicit-caching", "reasoning", "structured-output", "tool-use"], + "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], "output": ["text"] }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "effort", + "values": ["minimal", "low", "medium", "high", "xhigh", "max"] + } + ], "pricing": { - "input": "0.00000004", - "output": "0" + "input": "0.00000005", + "output": "0.0000007", + "input_cache_read": "0.000000025" } }, { @@ -10005,7 +11749,7 @@ "type": "language", "zdr": "all", "no_training": "all", - "tags": ["tool-use", "structured-output"], + "tags": ["tool-use", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -10018,9 +11762,7 @@ "tools", "tool_choice", "reasoning", - "include_reasoning", - "response_format", - "structured_outputs" + "include_reasoning" ], "temperature": true, "reasoning_options": [ @@ -10035,8 +11777,7 @@ "knowledge": "2023-12", "pricing": { "input": "0.00000072", - "output": "0.00000072", - "varies_by_provider": true + "output": "0.00000072" } }, { @@ -10052,7 +11793,7 @@ "type": "language", "zdr": "some", "no_training": "some", - "tags": ["tool-use", "structured-output"], + "tags": ["tool-use", "open-weights", "structured-output"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -10099,7 +11840,7 @@ "type": "language", "zdr": "all", "no_training": "all", - "tags": ["tool-use"], + "tags": ["tool-use", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -10143,7 +11884,7 @@ "type": "language", "zdr": "all", "no_training": "all", - "tags": ["tool-use", "vision", "structured-output"], + "tags": ["tool-use", "vision", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text", "image"], @@ -10156,9 +11897,7 @@ "tools", "tool_choice", "reasoning", - "include_reasoning", - "response_format", - "structured_outputs" + "include_reasoning" ], "temperature": true, "reasoning_options": [ @@ -10173,8 +11912,7 @@ "knowledge": "2024-08", "pricing": { "input": "0.00000024", - "output": "0.00000097", - "varies_by_provider": true + "output": "0.00000097" } }, { @@ -10190,7 +11928,7 @@ "type": "language", "zdr": "all", "no_training": "all", - "tags": ["tool-use", "vision", "structured-output"], + "tags": ["tool-use", "vision", "open-weights", "structured-output"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text", "image"], @@ -10497,7 +12235,7 @@ "reasoning_options": [ { "type": "effort", - "values": ["minimal", "low", "medium", "high", "xhigh"] + "values": ["minimal", "low", "medium", "high", "xhigh", "max"] } ], "pricing": { @@ -10547,7 +12285,7 @@ "reasoning_options": [ { "type": "effort", - "values": ["minimal", "low", "medium", "high", "xhigh"] + "values": ["minimal", "low", "medium", "high", "xhigh", "max"] } ], "pricing": { @@ -10556,6 +12294,175 @@ "input_cache_read": "0.000000002" } }, + { + "id": "meta/muse-spark-open", + "object": "model", + "created": 1755815280, + "released": 1792022400, + "owned_by": "meta", + "name": "Muse Spark Open", + "description": "Muse Spark Open is Meta’s open-weight reasoning model for coding and agentic workflows. Its sparse mixture-of-experts architecture has 816 billion total parameters with approximately 42 billion active per token, combining code generation, tool use, and image understanding. A one-million-token context window supports repository analysis, multi-file changes, debugging, and long-running agent tasks. This provider also documents audio and video input with text output.", + "context_window": 1048576, + "max_tokens": 1048576, + "type": "language", + "zdr": "all", + "no_training": "all", + "tags": [ + "audio-input", + "implicit-caching", + "reasoning", + "structured-output", + "tool-use", + "video-input", + "vision" + ], + "regions": ["us"], + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["text", "audio", "image", "video"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "effort", + "values": ["low", "medium", "high", "xhigh"] + } + ], + "pricing": { + "input": "0.00000125", + "output": "0.00000425", + "input_cache_read": "0.00000015", + "regional": { + "us": { + "input": "0.00000125", + "output": "0.00000425", + "input_cache_read": "0.00000015" + } + } + } + }, + { + "id": "meta/muse-wonder-1.0", + "object": "model", + "created": 1755815280, + "released": 1791763200, + "owned_by": "meta", + "name": "Muse Wonder", + "description": "Muse Wonder is Meta’s model for frontier coding, long-running agents, and advanced computer use. It plans long tasks, delegates work to sub-agents, and recovers from errors.", + "context_window": 1048576, + "max_tokens": 1048576, + "type": "language", + "zdr": "all", + "no_training": "all", + "tags": [ + "reasoning", + "tool-use", + "implicit-caching", + "file-input", + "vision", + "structured-output" + ], + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "effort", + "values": ["minimal", "low", "medium", "high", "xhigh", "max"] + } + ], + "pricing": { + "input": "0.000004", + "output": "0.00002", + "input_cache_read": "0.0000002" + } + }, + { + "id": "microsoft/mai-image-2.6", + "object": "model", + "created": 1755815280, + "released": 1791849600, + "owned_by": "microsoft", + "name": "MAI-Image-2.6", + "description": "MAI-Image-2.6 is a diffusion-based generative model designed for both high-quality text-to-image synthesis and precise, controllable image-to-image editing. It progressively transforms random noise into a coherent image aligned with a given text prompt, leveraging a flow-matching loss to learn a continuous transformation between the noise distribution and the data distribution. MAI-Image-2.6 excels at precise, surgical edits with consistency - enabling users and developers to make targeted object edits, adapt layouts, update text, clean up artifacts like motion blur, and preserve visual consistency across iterations.", + "context_window": 0, + "max_tokens": 0, + "type": "image", + "zdr": "all", + "no_training": "all", + "tags": ["image-generation"], + "supported_specifications": ["v3", "v4"], + "modalities": { + "input": ["text"], + "output": ["image"] + }, + "pricing": { + "input": "0.000005", + "output": "0.000038", + "image_dimension_quality_pricing": [ + { + "operation": "web-grounding", + "cost": "0.014" + } + ] + } + }, + { + "id": "microsoft/mai-image-2.6-flash", + "object": "model", + "created": 1755815280, + "released": 1791849600, + "owned_by": "microsoft", + "name": "MAI-Image-2.6-Flash", + "description": "MAI-Image-2.6 is a diffusion-based generative model designed for both high-quality text-to-image synthesis and precise, controllable image-to-image editing. It progressively transforms random noise into a coherent image aligned with a given text prompt, leveraging a flow-matching loss to learn a continuous transformation between the noise distribution and the data distribution. MAI-Image-2.6 excels at precise, surgical edits with consistency - enabling users and developers to make targeted object edits, adapt layouts, update text, clean up artifacts like motion blur, and preserve visual consistency across iterations.", + "context_window": 0, + "max_tokens": 0, + "type": "image", + "zdr": "all", + "no_training": "all", + "tags": ["image-generation"], + "supported_specifications": ["v3", "v4"], + "modalities": { + "input": ["text"], + "output": ["image"] + }, + "pricing": { + "input": "0.00000175", + "output": "0.000019", + "image_dimension_quality_pricing": [ + { + "operation": "web-grounding", + "cost": "0.014" + } + ] + } + }, { "id": "microsoft/mai-transcribe-2", "object": "model", @@ -10680,6 +12587,29 @@ "speech_input_character_cost": "0.000015" } }, + { + "id": "microsoft/microsoft-decision-1", + "object": "model", + "created": 1755815280, + "released": 1791504000, + "owned_by": "microsoft", + "name": "Decision-1", + "description": "Microsoft Decision-1 is a text decision model from Microsoft AI for classification, routing, and evaluation. It answers yes/no questions, selects among predefined options, and scores inputs against custom criteria, returning calibrated probabilities and confidence values. With support for multiple questions per request and a 32,768-token context window, it helps developers triage support requests, guide automated workflows, and evaluate AI responses against a rubric.", + "context_window": 32768, + "max_tokens": 0, + "type": "evaluation", + "zdr": "all", + "no_training": "all", + "supported_specifications": ["v4"], + "modalities": { + "input": ["text"], + "output": ["text"] + }, + "pricing": { + "input": "0.000000042", + "output": "0" + } + }, { "id": "minimax/minimax-h3", "object": "model", @@ -10693,8 +12623,8 @@ "type": "video", "zdr": "none", "no_training": "none", - "tags": ["video-generation", "vision"], - "supported_specifications": ["v2", "v3", "v4"], + "tags": ["video-generation", "vision", "open-weights"], + "supported_specifications": ["v3", "v4"], "modalities": { "input": ["text", "image"], "output": ["video"] @@ -10776,8 +12706,8 @@ "type": "video", "zdr": "none", "no_training": "none", - "tags": ["video-generation", "vision"], - "supported_specifications": ["v2", "v3", "v4"], + "tags": ["video-generation", "vision", "open-weights"], + "supported_specifications": ["v3", "v4"], "modalities": { "input": ["text", "image"], "output": ["video"] @@ -10840,7 +12770,13 @@ "type": "language", "zdr": "none", "no_training": "none", - "tags": ["reasoning", "tool-use", "explicit-caching", "structured-output"], + "tags": [ + "reasoning", + "tool-use", + "explicit-caching", + "structured-output", + "open-weights" + ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -10865,6 +12801,7 @@ ], "knowledge": "2024-10", "interleaved": true, + "deprecated_at": 1794960000000, "pricing": { "input": "0.0000003", "output": "0.0000012", @@ -10889,6 +12826,7 @@ "reasoning", "tool-use", "structured-output", + "open-weights", "implicit-caching", "explicit-caching" ], @@ -10941,7 +12879,8 @@ "tool-use", "implicit-caching", "explicit-caching", - "structured-output" + "structured-output", + "open-weights" ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { @@ -10966,6 +12905,7 @@ } ], "knowledge": "2024-10", + "deprecated_at": 1794960000000, "pricing": { "input": "0.0000003", "output": "0.0000024", @@ -10990,6 +12930,7 @@ "reasoning", "tool-use", "structured-output", + "open-weights", "implicit-caching", "explicit-caching" ], @@ -11046,7 +12987,8 @@ "tool-use", "implicit-caching", "explicit-caching", - "structured-output" + "structured-output", + "open-weights" ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { @@ -11070,6 +13012,7 @@ "type": "budget_tokens" } ], + "deprecated_at": 1794960000000, "pricing": { "input": "0.0000006", "output": "0.0000024", @@ -11094,6 +13037,7 @@ "reasoning", "tool-use", "implicit-caching", + "open-weights", "explicit-caching", "structured-output" ], @@ -11151,7 +13095,8 @@ "tool-use", "implicit-caching", "explicit-caching", - "structured-output" + "structured-output", + "open-weights" ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { @@ -11175,37 +13120,89 @@ "type": "budget_tokens" } ], + "deprecated_at": 1794960000000, + "pricing": { + "input": "0.0000006", + "output": "0.0000024", + "input_cache_read": "0.00000006", + "input_cache_write": "0.000000375" + } + }, + { + "id": "minimax/minimax-m3", + "object": "model", + "created": 1755815280, + "released": 1780185600, + "owned_by": "minimax", + "name": "MiniMax M3", + "description": "MiniMax-M3 is a frontier-class foundation model that unites the three capabilities defining today's frontier: a 1M-token context window, frontier coding and agentic performance, and native multimodality — the first open-weight model to deliver all three in a single system.", + "context_window": 512000, + "max_tokens": 512000, + "type": "language", + "zdr": "some", + "no_training": "some", + "tags": [ + "reasoning", + "tool-use", + "vision", + "implicit-caching", + "structured-output", + "open-weights", + "file-input" + ], + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "budget_tokens" + } + ], "pricing": { - "input": "0.0000006", - "output": "0.0000024", + "input": "0.0000003", + "output": "0.0000012", "input_cache_read": "0.00000006", - "input_cache_write": "0.000000375" + "varies_by_provider": true } }, { - "id": "minimax/minimax-m3", + "id": "minimax/minimax-m3.1-flash", "object": "model", "created": 1755815280, - "released": 1780185600, + "released": 1792368000, "owned_by": "minimax", - "name": "MiniMax M3", - "description": "MiniMax-M3 is a frontier-class foundation model that unites the three capabilities defining today's frontier: a 1M-token context window, frontier coding and agentic performance, and native multimodality — the first open-weight model to deliver all three in a single system.", - "context_window": 512000, - "max_tokens": 512000, + "name": "MiniMax-M3.1-Flash", + "description": "MiniMax-M3.1-Flash is MiniMax's M-series language model for agent reasoning, tool use, coding, and long-context tasks, with a 1,000,000-token context window. Compared with MiniMax-M3, it adds always-on reasoning and adjustable reasoning effort, allowing developers to tune reasoning effort for different tasks.", + "context_window": 1000000, + "max_tokens": 524288, "type": "language", - "zdr": "some", - "no_training": "some", + "zdr": "none", + "no_training": "none", "tags": [ + "implicit-caching", "reasoning", "tool-use", "vision", - "implicit-caching", "structured-output", - "file-input" + "open-weights" ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { - "input": ["text", "image", "pdf"], + "input": ["text", "image"], "output": ["text"] }, "supported_parameters": [ @@ -11222,14 +13219,13 @@ "temperature": true, "reasoning_options": [ { - "type": "budget_tokens" + "type": "effort", + "values": ["low", "medium", "high", "xhigh", "max"] } ], "pricing": { - "input": "0.0000003", - "output": "0.0000012", - "input_cache_read": "0.00000006", - "varies_by_provider": true + "input": "0", + "output": "0" } }, { @@ -11304,7 +13300,13 @@ "type": "language", "zdr": "all", "no_training": "all", - "tags": ["file-input", "tool-use", "vision", "structured-output"], + "tags": [ + "file-input", + "tool-use", + "vision", + "structured-output", + "open-weights" + ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text", "image", "pdf"], @@ -11340,7 +13342,7 @@ "type": "language", "zdr": "all", "no_training": "all", - "tags": ["tool-use", "vision"], + "tags": ["tool-use", "vision", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text", "image"], @@ -11374,7 +13376,7 @@ "type": "language", "zdr": "all", "no_training": "all", - "tags": ["tool-use", "vision", "structured-output"], + "tags": ["tool-use", "vision", "structured-output", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text", "image"], @@ -11432,7 +13434,7 @@ "type": "language", "zdr": "all", "no_training": "all", - "tags": ["tool-use", "vision", "structured-output"], + "tags": ["tool-use", "vision", "structured-output", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text", "image"], @@ -11492,13 +13494,13 @@ }, { "type": "effort", - "values": ["none", "low", "medium", "high"] + "values": ["none", "high"] } ], "pricing": { - "input": "0.00000068", - "output": "0.00000209", - "input_cache_read": "0.00000007" + "input": "0.00000136", + "output": "0.00000418", + "input_cache_read": "0.00000014" } }, { @@ -11533,6 +13535,9 @@ ], "temperature": true, "reasoning_options": [ + { + "type": "toggle" + }, { "type": "effort", "values": ["none", "high"] @@ -11551,13 +13556,13 @@ "released": 1721260800, "owned_by": "mistral", "name": "Mistral Nemo 12B", - "description": "A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, and Hindi. It supports function calling and is released under the Apache 2.0 license.", - "context_window": 60288, - "max_tokens": 16000, + "description": "12B model trained jointly by Mistral AI and NVIDIA, it significantly outperforms existing models smaller or similar in size.", + "context_window": 131072, + "max_tokens": 131072, "type": "language", - "zdr": "some", - "no_training": "some", - "tags": ["tool-use", "structured-output"], + "zdr": "all", + "no_training": "all", + "tags": ["tool-use", "structured-output", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -11575,9 +13580,8 @@ "temperature": true, "knowledge": "2024-04", "pricing": { - "input": "0.00000004", - "output": "0.00000017", - "varies_by_provider": true + "input": "0.000000029", + "output": "0.00000003" } }, { @@ -11593,7 +13597,7 @@ "type": "language", "zdr": "all", "no_training": "all", - "tags": ["tool-use", "vision", "structured-output"], + "tags": ["tool-use", "vision", "structured-output", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text", "image"], @@ -11616,6 +13620,69 @@ "input_cache_read": "0.000000015" } }, + { + "id": "mistral/voxtral-mini-transcribe-3", + "object": "model", + "created": 1755815280, + "released": 1792454400, + "owned_by": "mistral", + "name": "Voxtral Mini Transcribe 3", + "description": "Fast, cost-efficient multilingual transcription with speaker diarization and vocabulary biasing, designed for high-volume audio processing.", + "type": "transcription", + "zdr": "all", + "no_training": "all", + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["audio"], + "output": ["text"] + }, + "pricing": { + "input": "0", + "transcription_duration_cost_per_second": "0.00005834" + } + }, + { + "id": "mistral/voxtral-mini-tts-3", + "object": "model", + "created": 1755815280, + "released": 1792454400, + "owned_by": "mistral", + "name": "Voxtral TTS 3", + "description": "Generates natural, expressive speech with preset or cloned voices and inline controls for emotion and pace.", + "type": "speech", + "zdr": "all", + "no_training": "all", + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["text"], + "output": ["audio"] + }, + "pricing": { + "input": "0.000016", + "speech_input_character_cost": "0.000016" + } + }, + { + "id": "mistral/voxtral-small-transcribe-3", + "object": "model", + "created": 1755815280, + "released": 1792454400, + "owned_by": "mistral", + "name": "Voxtral Small Transcribe 3", + "description": "Mistral’s flagship transcription model, optimized for multilingual accuracy, speaker diarization, and domain-specific vocabulary.", + "type": "transcription", + "zdr": "all", + "no_training": "all", + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["audio"], + "output": ["text"] + }, + "pricing": { + "input": "0", + "transcription_duration_cost_per_second": "0.00006667" + } + }, { "id": "mixedbread/toast-1", "object": "model", @@ -11664,7 +13731,7 @@ "type": "language", "zdr": "none", "no_training": "none", - "tags": ["tool-use"], + "tags": ["tool-use", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -11683,54 +13750,6 @@ "output": "0.0000023" } }, - { - "id": "moonshotai/kimi-k2-thinking", - "object": "model", - "created": 1755815280, - "released": 1762387200, - "owned_by": "moonshotai", - "name": "Kimi K2 Thinking", - "description": "Kimi K2 Thinking is an advanced open-source thinking model by Moonshot AI. It can execute up to 200 – 300 sequential tool calls without human interference, reasoning coherently across hundreds of steps to solve complex problems. Built as a thinking agent, it reasons step by step while using tools, achieving state-of-the-art performance on Humanity's Last Exam (HLE), BrowseComp, and other benchmarks, with major gains in reasoning, agentic search, coding, writing, and general capabilities.", - "context_window": 216144, - "max_tokens": 216144, - "type": "language", - "zdr": "all", - "no_training": "all", - "tags": ["reasoning", "tool-use", "implicit-caching", "structured-output"], - "supported_specifications": ["v2", "v3", "v4"], - "modalities": { - "input": ["text"], - "output": ["text"] - }, - "supported_parameters": [ - "max_tokens", - "temperature", - "stop", - "tools", - "tool_choice", - "reasoning", - "include_reasoning", - "response_format", - "structured_outputs" - ], - "temperature": true, - "reasoning_options": [ - { - "type": "toggle" - }, - { - "type": "effort", - "values": ["none", "low", "medium", "high"] - } - ], - "knowledge": "2024-08", - "interleaved": true, - "pricing": { - "input": "0.00000047", - "output": "0.000002", - "input_cache_read": "0.000000141" - } - }, { "id": "moonshotai/kimi-k2.5", "object": "model", @@ -11749,6 +13768,7 @@ "vision", "tool-use", "structured-output", + "open-weights", "implicit-caching" ], "supported_specifications": ["v2", "v3", "v4"], @@ -11771,6 +13791,10 @@ "reasoning_options": [ { "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high"] } ], "knowledge": "2025-01", @@ -11799,6 +13823,7 @@ "tool-use", "vision", "video-input", + "open-weights", "structured-output" ], "supported_specifications": ["v2", "v3", "v4"], @@ -11851,7 +13876,8 @@ "file-input", "vision", "video-input", - "structured-output" + "structured-output", + "open-weights" ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { @@ -11911,7 +13937,8 @@ "file-input", "implicit-caching", "video-input", - "structured-output" + "structured-output", + "open-weights" ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { @@ -11966,6 +13993,7 @@ "file-input", "vision", "structured-output", + "open-weights", "explicit-caching", "video-input" ], @@ -11987,12 +14015,9 @@ ], "temperature": false, "reasoning_options": [ - { - "type": "toggle" - }, { "type": "effort", - "values": ["none", "low", "high", "max"] + "values": ["low", "high", "max"] } ], "pricing": { @@ -12033,7 +14058,8 @@ "implicit-caching", "file-input", "vision", - "structured-output" + "structured-output", + "open-weights" ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { @@ -12142,7 +14168,7 @@ "type": "language", "zdr": "all", "no_training": "all", - "tags": ["reasoning", "tool-use"], + "tags": ["reasoning", "tool-use", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -12161,28 +14187,144 @@ "reasoning_options": [ { "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high"] + } + ], + "pricing": { + "input": "0.00000005", + "output": "0.0000002", + "input_cache_read": "0.000000025" + } + }, + { + "id": "nvidia/nemotron-3-super-120b-a12b", + "object": "model", + "created": 1755815280, + "released": 1773187200, + "owned_by": "nvidia", + "name": "NVIDIA Nemotron 3 Super 120B A12B", + "description": "NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. It delivers up to 7x higher throughput, providing fast, cost-efficient inference for agentic tasks. Additionally, a long context window gives the model long-term memory, preventing AI agents from losing focus on long, multi-step tasks and ensuring high-accuracy results. Fully open with weights, datasets, and recipes, Super allows easy customization and secure deployment anywhere.", + "context_window": 256000, + "max_tokens": 32000, + "type": "language", + "zdr": "all", + "no_training": "all", + "tags": ["reasoning", "tool-use", "structured-output", "open-weights"], + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["text"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high"] + } + ], + "pricing": { + "input": "0.00000015", + "output": "0.00000065" + } + }, + { + "id": "nvidia/nemotron-3-ultra-550b-a55b", + "object": "model", + "created": 1755815280, + "released": 1780531200, + "owned_by": "nvidia", + "name": "Nemotron 3 Ultra", + "description": "A 550B parameter (55B active) open reasoning model from NVIDIA, built for long-running agent workflows. It uses a hybrid Mamba-Transformer MoE architecture and supports a 1M token context window.", + "context_window": 1000000, + "max_tokens": 65000, + "type": "language", + "zdr": "all", + "no_training": "all", + "tags": [ + "reasoning", + "tool-use", + "structured-output", + "open-weights", + "implicit-caching" + ], + "regions": ["us"], + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["text"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high"] } ], "pricing": { - "input": "0.00000005", - "output": "0.0000002", - "input_cache_read": "0.000000025" + "input": "0.0000006", + "output": "0.0000024", + "input_cache_read": "0.00000012", + "varies_by_provider": true, + "regional": { + "us": { + "input": "0.0000006", + "output": "0.0000024", + "input_cache_read": "0.00000012" + } + } } }, { - "id": "nvidia/nemotron-3-super-120b-a12b", + "id": "nvidia/nemotron-3.5-lightning", "object": "model", "created": 1755815280, - "released": 1773187200, + "released": 1786406400, "owned_by": "nvidia", - "name": "NVIDIA Nemotron 3 Super 120B A12B", - "description": "NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. It delivers up to 7x higher throughput, providing fast, cost-efficient inference for agentic tasks. Additionally, a long context window gives the model long-term memory, preventing AI agents from losing focus on long, multi-step tasks and ensuring high-accuracy results. Fully open with weights, datasets, and recipes, Super allows easy customization and secure deployment anywhere.", - "context_window": 256000, - "max_tokens": 32000, + "name": "Nemotron 3.5 Lightning 30B", + "description": "NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 is a large language model (LLM) trained by NVIDIA.\n\nThe model employs a hybrid Mixture-of-Experts architecture, utilizing interleaved Mamba-2 and MoE layers, along with select Attention layers. The Lightning 3.5 model is released alongside a number of speculative decoding methods for faster text generation. The model has 3B active parameters and 30B parameters in total.", + "context_window": 262144, + "max_tokens": 131072, "type": "language", - "zdr": "all", - "no_training": "all", - "tags": ["reasoning", "tool-use", "structured-output"], + "zdr": "some", + "no_training": "some", + "tags": [ + "reasoning", + "tool-use", + "implicit-caching", + "structured-output", + "open-weights" + ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -12206,29 +14348,36 @@ }, { "type": "effort", - "values": ["none", "low", "high"] + "values": ["none", "low", "medium", "high"] } ], "pricing": { - "input": "0.00000015", - "output": "0.00000065" + "input": "0.00000005", + "output": "0.0000002", + "input_cache_read": "0.00000001", + "varies_by_provider": true } }, { - "id": "nvidia/nemotron-3-ultra-550b-a55b", + "id": "nvidia/nemotron-3.5-lightning-free", "object": "model", "created": 1755815280, - "released": 1780531200, + "released": 1791936000, "owned_by": "nvidia", - "name": "Nemotron 3 Ultra", - "description": "A 550B parameter (55B active) open reasoning model from NVIDIA, built for long-running agent workflows. It uses a hybrid Mamba-Transformer MoE architecture and supports a 1M token context window.", + "name": "Nemotron 3.5 Lightning Free", + "description": "Nemotron 3.5 Lightning is an open-weight reasoning and chat model for long-running agents, sub-agent work, chatbots, and RAG systems. The model has 30B parameters with 3B active per token, in a hybrid Mixture-of-Experts design that interleaves Mamba-2 and MoE layers with a few attention layers. It has a 1M token context window and supports tool calling and structured outputs. The provider may retain prompts and responses for model improvement.", "context_window": 1000000, "max_tokens": 65000, "type": "language", - "zdr": "all", - "no_training": "all", - "tags": ["reasoning", "tool-use", "structured-output", "implicit-caching"], - "regions": ["us"], + "zdr": "none", + "no_training": "none", + "tags": [ + "reasoning", + "tool-use", + "structured-output", + "implicit-caching", + "open-weights" + ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -12252,40 +14401,40 @@ }, { "type": "effort", - "values": ["none", "medium", "high"] + "values": ["none", "low", "medium", "high"] } ], "pricing": { - "input": "0.0000006", - "output": "0.0000024", - "input_cache_read": "0.00000012", - "varies_by_provider": true, - "regional": { - "us": { - "input": "0.0000006", - "output": "0.0000024", - "input_cache_read": "0.00000012" - } - } + "input": "0", + "output": "0" } }, { - "id": "nvidia/nemotron-3.5-lightning", + "id": "nvidia/nemotron-3.5-super-vl", "object": "model", "created": 1755815280, - "released": 1786406400, + "released": 1792022400, "owned_by": "nvidia", - "name": "Nemotron 3.5 Lightning 30B", - "description": "NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 is a large language model (LLM) trained by NVIDIA.\n\nThe model employs a hybrid Mixture-of-Experts architecture, utilizing interleaved Mamba-2 and MoE layers, along with select Attention layers. The Lightning 3.5 model is released alongside a number of speculative decoding methods for faster text generation. The model has 3B active parameters and 30B parameters in total.", - "context_window": 262144, - "max_tokens": 131072, + "name": "NVIDIA Nemotron 3.5 Super VL", + "description": "NVIDIA Nemotron 3.5 Super VL is a vision-language model for reasoning, coding, tool use, and document understanding. Its hybrid Mamba-2, attention, and Mixture-of-Experts architecture has 120B total parameters with 12B active per token. Baseten serves text and image inputs with up to one million tokens of context for long conversations and agent workflows.", + "context_window": 1048576, + "max_tokens": 1048576, "type": "language", "zdr": "some", "no_training": "some", - "tags": ["reasoning", "tool-use", "implicit-caching", "structured-output"], + "tags": [ + "implicit-caching", + "reasoning", + "structured-output", + "tool-use", + "vision", + "open-weights", + "video-input" + ], + "regions": ["us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { - "input": ["text"], + "input": ["text", "image", "video"], "output": ["text"] }, "supported_parameters": [ @@ -12305,16 +14454,22 @@ "type": "toggle" }, { - "type": "budget_tokens", - "min": 1, - "max": 32768 + "type": "effort", + "values": ["none", "low", "medium", "high"] } ], "pricing": { - "input": "0.00000005", - "output": "0.0000002", - "input_cache_read": "0.00000001", - "varies_by_provider": true + "input": "0.0000002", + "output": "0.0000005", + "input_cache_read": "0.00000004", + "varies_by_provider": true, + "regional": { + "us": { + "input": "0.0000002", + "output": "0.0000005", + "input_cache_read": "0.00000004" + } + } } }, { @@ -12330,7 +14485,7 @@ "type": "language", "zdr": "all", "no_training": "all", - "tags": ["vision", "reasoning", "tool-use", "structured-output"], + "tags": ["vision", "reasoning", "tool-use", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text", "image"], @@ -12343,14 +14498,16 @@ "tools", "tool_choice", "reasoning", - "include_reasoning", - "response_format", - "structured_outputs" + "include_reasoning" ], "temperature": true, "reasoning_options": [ { "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high"] } ], "pricing": { @@ -12371,7 +14528,7 @@ "type": "language", "zdr": "all", "no_training": "all", - "tags": ["reasoning", "tool-use"], + "tags": ["reasoning", "tool-use", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -12390,12 +14547,15 @@ "reasoning_options": [ { "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high"] } ], "pricing": { "input": "0.00000006", - "output": "0.00000023", - "varies_by_provider": true + "output": "0.00000023" } }, { @@ -12521,6 +14681,48 @@ } } }, + { + "id": "openai/gpt-4.1-batch", + "object": "model", + "created": 1755815280, + "released": 1744588800, + "owned_by": "openai", + "name": "GPT-4.1 (Batch)", + "description": "GPT 4.1 is OpenAI's flagship model for complex tasks. It is well suited for problem solving across domains.", + "context_window": 1047576, + "max_tokens": 32768, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "file-input", + "implicit-caching", + "tool-use", + "vision", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "response_format", + "structured_outputs" + ], + "temperature": true, + "knowledge": "2024-06-01", + "pricing": { + "input": "0.000001", + "output": "0.000004", + "input_cache_read": "0.00000025" + } + }, { "id": "openai/gpt-4.1-fast", "object": "model", @@ -12623,6 +14825,48 @@ } } }, + { + "id": "openai/gpt-4.1-mini-batch", + "object": "model", + "created": 1755815280, + "released": 1747180800, + "owned_by": "openai", + "name": "GPT-4.1 mini (Batch)", + "description": "GPT 4.1 mini provides a balance between intelligence, speed, and cost that makes it an attractive model for many use cases.", + "context_window": 1047576, + "max_tokens": 32768, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "file-input", + "implicit-caching", + "tool-use", + "vision", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "response_format", + "structured_outputs" + ], + "temperature": true, + "knowledge": "2024-06-01", + "pricing": { + "input": "0.0000002", + "output": "0.0000008", + "input_cache_read": "0.00000005" + } + }, { "id": "openai/gpt-4.1-mini-fast", "object": "model", @@ -12726,6 +14970,48 @@ } } }, + { + "id": "openai/gpt-4.1-nano-batch", + "object": "model", + "created": 1755815280, + "released": 1744588800, + "owned_by": "openai", + "name": "GPT-4.1 nano (Batch)", + "description": "GPT-4.1 nano is the fastest, most cost-effective GPT 4.1 model.", + "context_window": 1047576, + "max_tokens": 32768, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "file-input", + "implicit-caching", + "tool-use", + "vision", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "response_format", + "structured_outputs" + ], + "temperature": true, + "knowledge": "2024-06-01", + "pricing": { + "input": "0.00000005", + "output": "0.0000002", + "input_cache_read": "0.0000000125" + } + }, { "id": "openai/gpt-4.1-nano-fast", "object": "model", @@ -12841,6 +15127,48 @@ } } }, + { + "id": "openai/gpt-4o-batch", + "object": "model", + "created": 1755815280, + "released": 1715558400, + "owned_by": "openai", + "name": "GPT-4o (Batch)", + "description": "GPT-4o from OpenAI has broad general knowledge and domain expertise allowing it to follow complex instructions in natural language and solve difficult problems accurately. It matches GPT-4 Turbo performance with a faster and cheaper API.", + "context_window": 128000, + "max_tokens": 16384, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "file-input", + "implicit-caching", + "tool-use", + "vision", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "response_format", + "structured_outputs" + ], + "temperature": true, + "knowledge": "2023-10-01", + "pricing": { + "input": "0.00000125", + "output": "0.000005", + "input_cache_read": "0.000000625" + } + }, { "id": "openai/gpt-4o-fast", "object": "model", @@ -12969,6 +15297,48 @@ } } }, + { + "id": "openai/gpt-4o-mini-batch", + "object": "model", + "created": 1755815280, + "released": 1721260800, + "owned_by": "openai", + "name": "GPT-4o mini (Batch)", + "description": "GPT-4o mini from OpenAI is their most advanced and cost-efficient small model. It is multi-modal (accepting text or image inputs and outputting text) and has higher intelligence than gpt-3.5-turbo but is just as fast.", + "context_window": 128000, + "max_tokens": 16384, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "file-input", + "implicit-caching", + "tool-use", + "vision", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "response_format", + "structured_outputs" + ], + "temperature": true, + "knowledge": "2023-10-01", + "pricing": { + "input": "0.000000075", + "output": "0.0000003", + "input_cache_read": "0.0000000375" + } + }, { "id": "openai/gpt-4o-mini-fast", "object": "model", @@ -13146,6 +15516,56 @@ } } }, + { + "id": "openai/gpt-5-batch", + "object": "model", + "created": 1755815280, + "released": 1754524800, + "owned_by": "openai", + "name": "GPT-5 (Batch)", + "description": "GPT-5 is OpenAI's flagship language model that excels at complex reasoning, broad real-world knowledge, code-intensive, and multi-step agentic tasks.", + "context_window": 400000, + "max_tokens": 128000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "file-input", + "implicit-caching", + "reasoning", + "tool-use", + "vision", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": false, + "reasoning_options": [ + { + "type": "effort", + "values": ["minimal", "low", "medium", "high"] + } + ], + "knowledge": "2024-09-30", + "pricing": { + "input": "0.000000625", + "output": "0.000005", + "input_cache_read": "0.0000000625" + } + }, { "id": "openai/gpt-5-codex", "object": "model", @@ -13322,6 +15742,56 @@ } } }, + { + "id": "openai/gpt-5-mini-batch", + "object": "model", + "created": 1755815280, + "released": 1754524800, + "owned_by": "openai", + "name": "GPT-5 mini (Batch)", + "description": "GPT-5 mini is a cost optimized model that excels at reasoning/chat tasks. It offers an optimal balance between speed, cost, and capability.", + "context_window": 400000, + "max_tokens": 128000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "file-input", + "implicit-caching", + "reasoning", + "tool-use", + "vision", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": false, + "reasoning_options": [ + { + "type": "effort", + "values": ["minimal", "low", "medium", "high"] + } + ], + "knowledge": "2024-05-31", + "pricing": { + "input": "0.000000125", + "output": "0.000001", + "input_cache_read": "0.0000000125" + } + }, { "id": "openai/gpt-5-mini-fast", "object": "model", @@ -13416,40 +15886,132 @@ "reasoning_options": [ { "type": "effort", - "values": ["minimal", "low", "medium", "high"] + "values": ["minimal", "low", "medium", "high"] + } + ], + "knowledge": "2024-05-31", + "pricing": { + "input": "0.00000005", + "output": "0.0000004", + "input_cache_read": "0.000000005", + "web_search": "10", + "service_tiers": { + "flex": { + "input": "0.000000025", + "output": "0.0000002", + "input_cache_read": "0.0000000025" + } + }, + "varies_by_provider": true + } + }, + { + "id": "openai/gpt-5-nano-batch", + "object": "model", + "created": 1755815280, + "released": 1754524800, + "owned_by": "openai", + "name": "GPT-5 nano (Batch)", + "description": "GPT-5 nano is a high throughput model that excels at simple instruction or classification tasks.", + "context_window": 400000, + "max_tokens": 128000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "file-input", + "implicit-caching", + "reasoning", + "tool-use", + "vision", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": false, + "reasoning_options": [ + { + "type": "effort", + "values": ["minimal", "low", "medium", "high"] + } + ], + "knowledge": "2024-05-31", + "pricing": { + "input": "0.000000025", + "output": "0.0000002", + "input_cache_read": "0.0000000025" + } + }, + { + "id": "openai/gpt-5-pro", + "object": "model", + "created": 1755815280, + "released": 1759708800, + "owned_by": "openai", + "name": "GPT-5 pro", + "description": "GPT-5 pro uses more compute to think harder and provide consistently better answers. Since GPT-5 pro is designed to tackle tough problems, some requests may take several minutes to finish.", + "context_window": 400000, + "max_tokens": 272000, + "type": "language", + "zdr": "all", + "no_training": "all", + "tags": ["file-input", "reasoning", "tool-use", "vision", "web-search"], + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "effort", + "values": ["high"] } ], - "knowledge": "2024-05-31", + "knowledge": "2024-09-30", "pricing": { - "input": "0.00000005", - "output": "0.0000004", - "input_cache_read": "0.000000005", - "web_search": "10", - "service_tiers": { - "flex": { - "input": "0.000000025", - "output": "0.0000002", - "input_cache_read": "0.0000000025" - } - }, - "varies_by_provider": true + "input": "0.000015", + "output": "0.00012", + "web_search": "10" } }, { - "id": "openai/gpt-5-pro", + "id": "openai/gpt-5-pro-batch", "object": "model", "created": 1755815280, "released": 1759708800, "owned_by": "openai", - "name": "GPT-5 pro", + "name": "GPT-5 pro (Batch)", "description": "GPT-5 pro uses more compute to think harder and provide consistently better answers. Since GPT-5 pro is designed to tackle tough problems, some requests may take several minutes to finish.", "context_window": 400000, "max_tokens": 272000, "type": "language", - "zdr": "all", + "zdr": "none", "no_training": "all", - "tags": ["file-input", "reasoning", "tool-use", "vision", "web-search"], - "supported_specifications": ["v2", "v3", "v4"], + "tags": ["file-input", "reasoning", "tool-use", "vision"], + "supported_specifications": ["v4"], "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] @@ -13472,9 +16034,8 @@ ], "knowledge": "2024-09-30", "pricing": { - "input": "0.000015", - "output": "0.00012", - "web_search": "10" + "input": "0.0000075", + "output": "0.00006" } }, { @@ -13853,6 +16414,60 @@ } } }, + { + "id": "openai/gpt-5.2-batch", + "object": "model", + "created": 1755815280, + "released": 1765411200, + "owned_by": "openai", + "name": "GPT 5.2 (Batch)", + "description": "GPT-5.2 is OpenAI's best general-purpose model, part of the GPT-5 flagship model family. It's their most intelligent model yet for both general and agentic tasks.", + "context_window": 400000, + "max_tokens": 128000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "file-input", + "implicit-caching", + "reasoning", + "tool-use", + "vision", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "minimal", "low", "medium", "high", "xhigh"] + } + ], + "knowledge": "2025-08-31", + "pricing": { + "input": "0.000000875", + "output": "0.000007", + "input_cache_read": "0.0000000875" + } + }, { "id": "openai/gpt-5.2-codex", "object": "model", @@ -14306,6 +16921,93 @@ } } }, + { + "id": "openai/gpt-5.4-batch", + "object": "model", + "created": 1755815280, + "released": 1772668800, + "owned_by": "openai", + "name": "GPT 5.4 (Batch)", + "description": "GPT-5.4 is OpenAI's best general-purpose model, part of the GPT-5 flagship model family. It's their most intelligent model yet for both general and agentic tasks.", + "context_window": 1050000, + "max_tokens": 128000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "file-input", + "implicit-caching", + "reasoning", + "tool-use", + "vision", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "minimal", "low", "medium", "high", "xhigh"] + } + ], + "knowledge": "2025-08-31", + "pricing": { + "input": "0.00000125", + "input_tiers": [ + { + "cost": "0.00000125", + "min": 0, + "max": 272000 + }, + { + "cost": "0.0000025", + "min": 272000 + } + ], + "output": "0.0000075", + "output_tiers": [ + { + "cost": "0.0000075", + "min": 0, + "max": 272000 + }, + { + "cost": "0.00001125", + "min": 272000 + } + ], + "input_cache_read": "0.000000125", + "input_cache_read_tiers": [ + { + "cost": "0.000000125", + "min": 0, + "max": 272000 + }, + { + "cost": "0.00000025", + "min": 272000 + } + ] + } + }, { "id": "openai/gpt-5.4-fast", "object": "model", @@ -14460,6 +17162,60 @@ } } }, + { + "id": "openai/gpt-5.4-mini-batch", + "object": "model", + "created": 1755815280, + "released": 1773705600, + "owned_by": "openai", + "name": "GPT 5.4 Mini (Batch)", + "description": "GPT-5.4 Mini brings the strengths of GPT-5.4 to a faster, more efficient model designed for high-volume workloads.", + "context_window": 400000, + "max_tokens": 128000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "file-input", + "implicit-caching", + "reasoning", + "tool-use", + "vision", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "minimal", "low", "medium", "high", "xhigh"] + } + ], + "knowledge": "2025-08-31", + "pricing": { + "input": "0.000000375", + "output": "0.00000225", + "input_cache_read": "0.0000000375" + } + }, { "id": "openai/gpt-5.4-mini-fast", "object": "model", @@ -14589,13 +17345,67 @@ "input_cache_read": "0.00000001" } }, - "regional": { - "us": { - "input": "0.00000022", - "output": "0.000001375", - "input_cache_read": "0.000000022" - } + "regional": { + "us": { + "input": "0.00000022", + "output": "0.000001375", + "input_cache_read": "0.000000022" + } + } + } + }, + { + "id": "openai/gpt-5.4-nano-batch", + "object": "model", + "created": 1755815280, + "released": 1773705600, + "owned_by": "openai", + "name": "GPT 5.4 Nano (Batch)", + "description": "GPT-5.4 Nano is designed for tasks where speed and cost matter most like classification, data extraction, ranking, and sub-agents.", + "context_window": 400000, + "max_tokens": 128000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "file-input", + "implicit-caching", + "reasoning", + "tool-use", + "vision", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "minimal", "low", "medium", "high", "xhigh"] } + ], + "knowledge": "2025-08-31", + "pricing": { + "input": "0.0000001", + "output": "0.000000625", + "input_cache_read": "0.00000001" } }, { @@ -14875,6 +17685,93 @@ } } }, + { + "id": "openai/gpt-5.5-batch", + "object": "model", + "created": 1755815280, + "released": 1776988800, + "owned_by": "openai", + "name": "GPT 5.5 (Batch)", + "description": "GPT‑5.5 understands what you’re trying to do faster and can carry more of the work itself. It excels at writing and debugging code, researching online, analyzing data, creating documents and spreadsheets, operating software, and moving across tools until a task is finished. Instead of carefully managing every step, you can give GPT‑5.5 a messy, multi-part task and trust it to plan, use tools, check its work, navigate through ambiguity, and keep going.", + "context_window": 1000000, + "max_tokens": 128000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "file-input", + "implicit-caching", + "reasoning", + "tool-use", + "vision", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "minimal", "low", "medium", "high", "xhigh"] + } + ], + "knowledge": "2025-12-01", + "pricing": { + "input": "0.0000025", + "input_tiers": [ + { + "cost": "0.0000025", + "min": 0, + "max": 272000 + }, + { + "cost": "0.000005", + "min": 272000 + } + ], + "output": "0.000015", + "output_tiers": [ + { + "cost": "0.000015", + "min": 0, + "max": 272000 + }, + { + "cost": "0.0000225", + "min": 272000 + } + ], + "input_cache_read": "0.00000025", + "input_cache_read_tiers": [ + { + "cost": "0.00000025", + "min": 0, + "max": 272000 + }, + { + "cost": "0.0000005", + "min": 272000 + } + ] + } + }, { "id": "openai/gpt-5.5-fast", "object": "model", @@ -15049,6 +17946,77 @@ } } }, + { + "id": "openai/gpt-5.5-pro-batch", + "object": "model", + "created": 1755815280, + "released": 1776988800, + "owned_by": "openai", + "name": "GPT 5.5 Pro (Batch)", + "description": "", + "context_window": 1000000, + "max_tokens": 128000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "reasoning", + "tool-use", + "file-input", + "vision", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "effort", + "values": ["medium", "high", "xhigh"] + } + ], + "knowledge": "2025-12-01", + "pricing": { + "input": "0.000015", + "input_tiers": [ + { + "cost": "0.000015", + "min": 0, + "max": 272000 + }, + { + "cost": "0.00003", + "min": 272000 + } + ], + "output": "0.00009", + "output_tiers": [ + { + "cost": "0.00009", + "min": 0, + "max": 272000 + }, + { + "cost": "0.000135", + "min": 272000 + } + ] + } + }, { "id": "openai/gpt-5.6-luna", "object": "model", @@ -15374,7 +18342,106 @@ ] } } - } + } + } + }, + { + "id": "openai/gpt-5.6-luna-batch", + "object": "model", + "created": 1755815280, + "released": 1783555200, + "owned_by": "openai", + "name": "GPT 5.6 Luna (Batch)", + "description": "GPT-5.6 Luna is a fast, affordable GPT-5.6 model that brings strong capability at the lowest cost in the series.", + "context_window": 1050000, + "max_tokens": 128000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "reasoning", + "file-input", + "tool-use", + "vision", + "implicit-caching", + "explicit-caching", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high", "xhigh", "max"] + } + ], + "knowledge": "2026-02-16", + "pricing": { + "input": "0.0000001", + "input_tiers": [ + { + "cost": "0.0000001", + "min": 0, + "max": 272000 + }, + { + "cost": "0.0000002", + "min": 272000 + } + ], + "output": "0.0000006", + "output_tiers": [ + { + "cost": "0.0000006", + "min": 0, + "max": 272000 + }, + { + "cost": "0.0000009", + "min": 272000 + } + ], + "input_cache_read": "0.00000001", + "input_cache_read_tiers": [ + { + "cost": "0.00000001", + "max": 272000 + }, + { + "cost": "0.00000002", + "min": 272000 + } + ], + "input_cache_write": "0.000000125", + "input_cache_write_tiers": [ + { + "cost": "0.000000125", + "min": 0, + "max": 272000 + }, + { + "cost": "0.00000025", + "min": 272000 + } + ] } }, { @@ -15915,6 +18982,106 @@ } } }, + { + "id": "openai/gpt-5.6-sol-batch", + "object": "model", + "created": 1755815280, + "released": 1783555200, + "owned_by": "openai", + "name": "GPT 5.6 Sol (Batch)", + "description": "GPT-5.6 Sol is the flagship of OpenAI's GPT-5.6 series, its most capable model for long-horizon agentic work across coding, biology, and cybersecurity.", + "context_window": 1050000, + "max_tokens": 128000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "reasoning", + "tool-use", + "implicit-caching", + "file-input", + "vision", + "explicit-caching", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "minimal", "low", "medium", "high", "xhigh", "max"] + } + ], + "knowledge": "2026-02-16", + "pricing": { + "input": "0.000002", + "input_tiers": [ + { + "cost": "0.000002", + "min": 0, + "max": 272000 + }, + { + "cost": "0.000004", + "min": 272000 + } + ], + "output": "0.00001", + "output_tiers": [ + { + "cost": "0.00001", + "min": 0, + "max": 272000 + }, + { + "cost": "0.000015", + "min": 272000 + } + ], + "input_cache_read": "0.0000002", + "input_cache_read_tiers": [ + { + "cost": "0.0000002", + "min": 0, + "max": 272000 + }, + { + "cost": "0.0000004", + "min": 272000 + } + ], + "input_cache_write": "0.0000025", + "input_cache_write_tiers": [ + { + "cost": "0.0000025", + "min": 0, + "max": 272000 + }, + { + "cost": "0.000005", + "min": 272000 + } + ] + } + }, { "id": "openai/gpt-5.6-sol-fast", "object": "model", @@ -16452,6 +19619,106 @@ } } }, + { + "id": "openai/gpt-5.6-terra-batch", + "object": "model", + "created": 1755815280, + "released": 1783555200, + "owned_by": "openai", + "name": "GPT 5.6 Terra (Batch)", + "description": "GPT-5.6 Terra is a balanced GPT-5.6 model for everyday work, with performance comparable to the previous generation at half the cost.", + "context_window": 1050000, + "max_tokens": 128000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "reasoning", + "file-input", + "tool-use", + "vision", + "implicit-caching", + "explicit-caching", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "minimal", "low", "medium", "high", "xhigh", "max"] + } + ], + "knowledge": "2026-02-16", + "pricing": { + "input": "0.000001", + "input_tiers": [ + { + "cost": "0.000001", + "min": 0, + "max": 272000 + }, + { + "cost": "0.000002", + "min": 272000 + } + ], + "output": "0.000006", + "output_tiers": [ + { + "cost": "0.000006", + "min": 0, + "max": 272000 + }, + { + "cost": "0.000009", + "min": 272000 + } + ], + "input_cache_read": "0.0000001", + "input_cache_read_tiers": [ + { + "cost": "0.0000001", + "min": 0, + "max": 272000 + }, + { + "cost": "0.0000002", + "min": 272000 + } + ], + "input_cache_write": "0.00000125", + "input_cache_write_tiers": [ + { + "cost": "0.00000125", + "min": 0, + "max": 272000 + }, + { + "cost": "0.0000025", + "min": 272000 + } + ] + } + }, { "id": "openai/gpt-5.6-terra-fast", "object": "model", @@ -16979,7 +20246,99 @@ ] } } - } + } + } + }, + { + "id": "openai/gpt-6-astra-batch", + "object": "model", + "created": 1755815280, + "released": 1788480000, + "owned_by": "openai", + "name": "GPT-6 Astra (Batch)", + "description": "GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.", + "context_window": 1050000, + "max_tokens": 128000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "file-input", + "implicit-caching", + "reasoning", + "tool-use", + "vision", + "explicit-caching", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": false, + "reasoning_options": [ + { + "type": "effort", + "values": ["low", "medium", "high", "xhigh", "max"] + } + ], + "knowledge": "2026-04-30", + "pricing": { + "input": "0.000005", + "input_tiers": [ + { + "cost": "0.000005", + "max": 272001 + }, + { + "cost": "0.00001", + "min": 272001 + } + ], + "output": "0.000025", + "output_tiers": [ + { + "cost": "0.000025", + "max": 272001 + }, + { + "cost": "0.0000375", + "min": 272001 + } + ], + "input_cache_read": "0.0000005", + "input_cache_read_tiers": [ + { + "cost": "0.0000005", + "max": 272001 + }, + { + "cost": "0.000001", + "min": 272001 + } + ], + "input_cache_write": "0.00000625", + "input_cache_write_tiers": [ + { + "cost": "0.00000625", + "max": 272001 + }, + { + "cost": "0.0000125", + "min": 272001 + } + ] } }, { @@ -17512,6 +20871,106 @@ } } }, + { + "id": "openai/gpt-6-luna-batch", + "object": "model", + "created": 1755815280, + "released": 1790035200, + "owned_by": "openai", + "name": "GPT-6 Luna (Batch)", + "description": "GPT-6 Luna is OpenAI's efficient reasoning model for focused, high-volume tasks. It accepts text and images, generates text, and supports a 1,050,000-token context window with up to 128,000 output tokens. Configurable reasoning effort, structured outputs, prompt caching, and Responses API tools support cost-sensitive applications, coding tasks, and automated workflows.", + "context_window": 1050000, + "max_tokens": 128000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "explicit-caching", + "file-input", + "implicit-caching", + "reasoning", + "structured-output", + "tool-use", + "vision" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high", "xhigh", "max"] + } + ], + "knowledge": "2026-05-18", + "pricing": { + "input": "0.00000005", + "input_tiers": [ + { + "cost": "0.00000005", + "min": 0, + "max": 272001 + }, + { + "cost": "0.0000001", + "min": 272001 + } + ], + "output": "0.00000025", + "output_tiers": [ + { + "cost": "0.00000025", + "min": 0, + "max": 272001 + }, + { + "cost": "0.000000375", + "min": 272001 + } + ], + "input_cache_read": "0.000000005", + "input_cache_read_tiers": [ + { + "cost": "0.000000005", + "min": 0, + "max": 272001 + }, + { + "cost": "0.00000001", + "min": 272001 + } + ], + "input_cache_write": "0.0000000625", + "input_cache_write_tiers": [ + { + "cost": "0.0000000625", + "min": 0, + "max": 272001 + }, + { + "cost": "0.000000125", + "min": 272001 + } + ] + } + }, { "id": "openai/gpt-6-luna-decisions", "object": "model", @@ -18079,6 +21538,106 @@ } } }, + { + "id": "openai/gpt-6-sol-batch", + "object": "model", + "created": 1755815280, + "released": 1790035200, + "owned_by": "openai", + "name": "GPT-6 Sol (Batch)", + "description": "GPT-6 Sol is OpenAI's reasoning model for complex coding and agentic workflows. It accepts text and images, generates text, and supports a 1,050,000-token context window with up to 128,000 output tokens. Configurable reasoning effort, structured outputs, prompt caching, and Responses API tools make it suited to software development and multi-step automation.", + "context_window": 1050000, + "max_tokens": 128000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "explicit-caching", + "file-input", + "implicit-caching", + "reasoning", + "structured-output", + "tool-use", + "vision" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high", "xhigh", "max"] + } + ], + "knowledge": "2026-04-20", + "pricing": { + "input": "0.000001", + "input_tiers": [ + { + "cost": "0.000001", + "min": 0, + "max": 272001 + }, + { + "cost": "0.000002", + "min": 272001 + } + ], + "output": "0.000005", + "output_tiers": [ + { + "cost": "0.000005", + "min": 0, + "max": 272001 + }, + { + "cost": "0.0000075", + "min": 272001 + } + ], + "input_cache_read": "0.0000001", + "input_cache_read_tiers": [ + { + "cost": "0.0000001", + "min": 0, + "max": 272001 + }, + { + "cost": "0.0000002", + "min": 272001 + } + ], + "input_cache_write": "0.00000125", + "input_cache_write_tiers": [ + { + "cost": "0.00000125", + "min": 0, + "max": 272001 + }, + { + "cost": "0.0000025", + "min": 272001 + } + ] + } + }, { "id": "openai/gpt-6-sol-fast", "object": "model", @@ -18405,6 +21964,17 @@ "output": "0.00003", "input_cache_read": "0.0000004" } + }, + "ultrafast": { + "input": "0.000012", + "output": "0.00006", + "input_cache_read": "0.0000006", + "long_context": { + "threshold": 272001, + "input": "0.000024", + "output": "0.00009", + "input_cache_read": "0.0000012" + } } }, "fast": { @@ -18611,6 +22181,102 @@ } } }, + { + "id": "openai/gpt-6.1-sol-batch", + "object": "model", + "created": 1755815280, + "released": 1790640000, + "owned_by": "openai", + "name": "GPT-6.1 Sol (Batch)", + "description": "GPT-6.1 Sol is OpenAI's reasoning model for complex coding, computer use, and professional work. It accepts text and images, generates text, and supports a 1,050,000-token context window with up to 128,000 output tokens. Configurable reasoning effort, structured outputs, prompt caching, and Responses API tools support multi-step workflows.", + "context_window": 1050000, + "max_tokens": 128000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "explicit-caching", + "file-input", + "implicit-caching", + "reasoning", + "structured-output", + "tool-use", + "vision" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "effort", + "values": ["low", "medium", "high", "xhigh", "max"] + } + ], + "pricing": { + "input": "0.000001", + "input_tiers": [ + { + "cost": "0.000001", + "min": 0, + "max": 272001 + }, + { + "cost": "0.000002", + "min": 272001 + } + ], + "output": "0.000005", + "output_tiers": [ + { + "cost": "0.000005", + "min": 0, + "max": 272001 + }, + { + "cost": "0.0000075", + "min": 272001 + } + ], + "input_cache_read": "0.00000005", + "input_cache_read_tiers": [ + { + "cost": "0.00000005", + "min": 0, + "max": 272001 + }, + { + "cost": "0.0000001", + "min": 272001 + } + ], + "input_cache_write": "0.00000125", + "input_cache_write_tiers": [ + { + "cost": "0.00000125", + "min": 0, + "max": 272001 + }, + { + "cost": "0.0000025", + "min": 272001 + } + ] + } + }, { "id": "openai/gpt-6.1-sol-fast", "object": "model", @@ -19003,7 +22669,13 @@ "type": "language", "zdr": "some", "no_training": "all", - "tags": ["reasoning", "tool-use", "structured-output", "implicit-caching"], + "tags": [ + "reasoning", + "tool-use", + "structured-output", + "open-weights", + "implicit-caching" + ], "regions": ["us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { @@ -19054,9 +22726,15 @@ "context_window": 131072, "max_tokens": 8192, "type": "language", - "zdr": "some", - "no_training": "some", - "tags": ["reasoning", "tool-use", "structured-output", "implicit-caching"], + "zdr": "all", + "no_training": "all", + "tags": [ + "reasoning", + "tool-use", + "structured-output", + "open-weights", + "implicit-caching" + ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -19100,7 +22778,7 @@ "type": "language", "zdr": "all", "no_training": "all", - "tags": ["reasoning", "tool-use", "structured-output"], + "tags": ["reasoning", "tool-use", "structured-output", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -19142,7 +22820,13 @@ "type": "language", "zdr": "all", "no_training": "all", - "tags": ["reasoning", "tool-use", "structured-output", "implicit-caching"], + "tags": [ + "reasoning", + "tool-use", + "structured-output", + "open-weights", + "implicit-caching" + ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -19859,6 +23543,7 @@ "type": "transcription", "zdr": "none", "no_training": "all", + "tags": ["open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["audio"], @@ -19870,6 +23555,54 @@ "transcription_duration_cost_per_second": "0.0001" } }, + { + "id": "perplexity/pplx-decider-flash-v1.2", + "object": "model", + "created": 1755815280, + "released": 1792108800, + "owned_by": "perplexity", + "name": "Decider Flash V1.2 4B", + "description": "Perplexity Decider Flash V1.2 is a 4B multimodal decision model for high-volume classification, routing, labeling, and filtering. It evaluates text, structured JSON, and images against yes/no questions, custom choices, and ordered rubrics, returning typed answers with probabilities. It supports a 256K context window.", + "context_window": 262144, + "max_tokens": 0, + "type": "evaluation", + "zdr": "none", + "no_training": "all", + "tags": ["vision"], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image"], + "output": ["text"] + }, + "pricing": { + "input": "0.00000001", + "output": "0" + } + }, + { + "id": "perplexity/pplx-decider-v1.2", + "object": "model", + "created": 1755815280, + "released": 1792108800, + "owned_by": "perplexity", + "name": "Decider V1.2 27B", + "description": "Perplexity Decider V1.2 is a 27B multimodal decision model for classification, routing, and scoring. It evaluates text, structured JSON, and images against yes/no questions, custom choices, and ordered rubrics, returning typed answers with probabilities. It supports multiple questions over shared content and a 256K context window.", + "context_window": 262144, + "max_tokens": 0, + "type": "evaluation", + "zdr": "none", + "no_training": "all", + "tags": ["vision"], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image"], + "output": ["text"] + }, + "pricing": { + "input": "0.00000002", + "output": "0" + } + }, { "id": "perplexity/pplx-embed-v1-0.6b", "object": "model", @@ -19883,6 +23616,7 @@ "type": "embedding", "zdr": "none", "no_training": "all", + "tags": ["open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -19905,6 +23639,7 @@ "type": "embedding", "zdr": "none", "no_training": "all", + "tags": ["open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -19970,7 +23705,7 @@ "type": "language", "zdr": "none", "no_training": "none", - "tags": ["reasoning", "tool-use"], + "tags": ["reasoning", "tool-use", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -20011,7 +23746,7 @@ "type": "language", "zdr": "none", "no_training": "none", - "tags": ["reasoning", "tool-use", "free"], + "tags": ["reasoning", "tool-use", "free", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -20051,7 +23786,7 @@ "type": "image", "zdr": "none", "no_training": "all", - "tags": ["image-generation"], + "tags": ["image-generation", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -20059,39 +23794,6 @@ }, "pricing": {} }, - { - "id": "quiverai/arrow-1.1", - "object": "model", - "created": 1755815280, - "released": 1776297600, - "owned_by": "quiverai", - "name": "Arrow 1.1", - "description": "Best default for speed and quality, with stronger prompt following and more precise SVG structure.", - "context_window": 131072, - "max_tokens": 131072, - "type": "image", - "zdr": "none", - "no_training": "none", - "tags": ["image-generation"], - "supported_specifications": ["v3", "v4"], - "modalities": { - "input": ["text"], - "output": ["image"] - }, - "deprecated_at": 1792137600000, - "pricing": { - "image_dimension_quality_pricing": [ - { - "operation": "generate", - "cost": "0.2" - }, - { - "operation": "vectorize", - "cost": "0.15" - } - ] - } - }, { "id": "quiverai/arrow-2", "object": "model", @@ -20434,13 +24136,118 @@ "output": ["image"] }, "pricing": { - "image": "0.21", - "image_dimension_quality_pricing": [ - { - "style": "vector_illustration", - "cost": "0.3" - } - ] + "image": "0.21", + "image_dimension_quality_pricing": [ + { + "style": "vector_illustration", + "cost": "0.3" + } + ] + } + }, + { + "id": "reflection/beam", + "object": "model", + "created": 1755815280, + "released": 1792108800, + "owned_by": "reflection", + "name": "Beam 1.0", + "description": "Beam is Reflection’s reasoning model for coding and agentic workflows, combining strong coding capabilities with fast, low-latency inference.", + "context_window": 1048576, + "max_tokens": 131072, + "type": "language", + "zdr": "some", + "no_training": "some", + "tags": [ + "implicit-caching", + "reasoning", + "structured-output", + "tool-use", + "open-weights", + "free" + ], + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["text"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "effort", + "values": ["low", "medium", "high", "xhigh", "max"] + } + ], + "interleaved": { + "field": "reasoning_content" + }, + "pricing": { + "input": "0", + "output": "0", + "varies_by_provider": true + } + }, + { + "id": "reflection/beam-free", + "object": "model", + "created": 1755815280, + "released": 1792108800, + "owned_by": "reflection", + "name": "Beam 1.0 (Free)", + "description": "Beam is Reflection’s reasoning model for coding and agentic workflows, combining strong coding capabilities with fast, low-latency inference.", + "context_window": 1048576, + "max_tokens": 131072, + "type": "language", + "zdr": "none", + "no_training": "none", + "tags": [ + "implicit-caching", + "reasoning", + "structured-output", + "tool-use", + "free", + "open-weights" + ], + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["text"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "effort", + "values": ["low", "medium", "high", "xhigh", "max"] + } + ], + "interleaved": { + "field": "reasoning_content" + }, + "pricing": { + "input": "0", + "output": "0" } }, { @@ -20483,7 +24290,7 @@ "reasoning_options": [ { "type": "effort", - "values": ["high", "xhigh"] + "values": ["high", "xhigh", "max"] } ], "pricing": { @@ -20526,7 +24333,7 @@ "reasoning_options": [ { "type": "effort", - "values": ["high", "xhigh"] + "values": ["high", "xhigh", "max"] } ], "pricing": { @@ -20608,7 +24415,7 @@ "reasoning_options": [ { "type": "effort", - "values": ["high", "xhigh"] + "values": ["high", "xhigh", "max"] } ], "pricing": { @@ -20695,7 +24502,7 @@ }, { "type": "effort", - "values": ["none", "low", "medium", "high"] + "values": ["none", "minimal", "low", "medium", "high", "xhigh", "max"] } ], "pricing": { @@ -20704,6 +24511,86 @@ "input_cache_read": "0.00000015" } }, + { + "id": "scaledown/scaledown-classify-1", + "object": "model", + "created": 1755815280, + "released": 1791849600, + "owned_by": "scaledown", + "name": "Classify-1", + "description": "ScaleDown Classify-1 is a task-specific small language model for text classification. It assigns text to custom labels and returns probability scores, supporting intent detection, content categorization, and routing workflows. Its deterministic, encoder-only approach produces consistent classification results without sampling variability.", + "context_window": 0, + "max_tokens": 0, + "type": "evaluation", + "zdr": "none", + "no_training": "none", + "supported_specifications": ["v4"], + "modalities": { + "input": ["text"], + "output": ["text"] + }, + "pricing": { + "input": "0.00000005", + "output": "0" + } + }, + { + "id": "scaledown/scaledown-extract-1", + "object": "model", + "created": 1755815280, + "released": 1792454400, + "owned_by": "scaledown", + "name": "Extract-1", + "description": "ScaleDown Extract-1 is a task-specific language model for extracting structured data from unstructured text using a custom JSON schema. It identifies domain-specific entities with confidence scores, character offsets, and surrounding context, and supports nested objects and arrays for workflows such as invoice processing, contract analysis, and record parsing.", + "context_window": 1000000, + "max_tokens": 1000000, + "type": "language", + "zdr": "none", + "no_training": "none", + "tags": ["structured-output"], + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["text"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "response_format", + "structured_outputs" + ], + "temperature": true, + "pricing": { + "input": "0.00000005", + "output": "0" + } + }, + { + "id": "scaledown/scaledown-summarize-1", + "object": "model", + "created": 1755815280, + "released": 1792454400, + "owned_by": "scaledown", + "name": "Summarize-1", + "description": "ScaleDown Summarize-1 is a task-specific language model for abstractive summarization of long documents, transcripts, and conversations. It rewrites source text into concise summaries and accepts instructions for format, language, length, and focus, making it useful for document processing, meeting summaries, and support workflows.", + "context_window": 1000000, + "max_tokens": 1000, + "type": "language", + "zdr": "none", + "no_training": "none", + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["text"], + "output": ["text"] + }, + "supported_parameters": ["max_tokens", "temperature", "stop"], + "temperature": true, + "pricing": { + "input": "0.00000005", + "output": "0" + } + }, { "id": "spacexai/grok-4.1-fast-non-reasoning", "object": "model", @@ -20810,12 +24697,199 @@ } }, { - "id": "spacexai/grok-4.20-multi-agent", + "id": "spacexai/grok-4.20-multi-agent", + "object": "model", + "created": 1755815280, + "released": 1773100800, + "owned_by": "spacexai", + "name": "Grok 4.20 Multi-Agent", + "description": "Multiple agents collaborate in parallel to perform deep research tasks.", + "context_window": 2000000, + "max_tokens": 2000000, + "type": "language", + "zdr": "all", + "no_training": "all", + "tags": [ + "reasoning", + "tool-use", + "implicit-caching", + "vision", + "file-input", + "web-search", + "structured-output" + ], + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high"] + } + ], + "pricing": { + "input": "0.00000125", + "input_tiers": [ + { + "cost": "0.00000125", + "min": 0, + "max": 200001 + }, + { + "cost": "0.0000025", + "min": 200001 + } + ], + "output": "0.0000025", + "output_tiers": [ + { + "cost": "0.0000025", + "min": 0, + "max": 200001 + }, + { + "cost": "0.000005", + "min": 200001 + } + ], + "input_cache_read": "0.0000002", + "input_cache_read_tiers": [ + { + "cost": "0.0000002", + "min": 0, + "max": 200001 + }, + { + "cost": "0.0000004", + "min": 200001 + } + ], + "web_search": "5", + "service_tiers": { + "priority": { + "input": "0.0000025", + "output": "0.000005", + "input_cache_read": "0.0000004", + "long_context": { + "threshold": 200001, + "input": "0.000005", + "output": "0.00001", + "input_cache_read": "0.0000008" + } + } + } + } + }, + { + "id": "spacexai/grok-4.20-multi-agent-batch", + "object": "model", + "created": 1755815280, + "released": 1773100800, + "owned_by": "spacexai", + "name": "Grok 4.20 Multi-Agent (Batch)", + "description": "Multiple agents collaborate in parallel to perform deep research tasks.", + "context_window": 2000000, + "max_tokens": 2000000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "reasoning", + "tool-use", + "implicit-caching", + "vision", + "file-input", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high"] + } + ], + "pricing": { + "input": "0.000001", + "input_tiers": [ + { + "cost": "0.000001", + "min": 0, + "max": 200001 + }, + { + "cost": "0.000002", + "min": 200001 + } + ], + "output": "0.000002", + "output_tiers": [ + { + "cost": "0.000002", + "min": 0, + "max": 200001 + }, + { + "cost": "0.000004", + "min": 200001 + } + ], + "input_cache_read": "0.00000016", + "input_cache_read_tiers": [ + { + "cost": "0.00000016", + "min": 0, + "max": 200001 + }, + { + "cost": "0.00000032", + "min": 200001 + } + ] + } + }, + { + "id": "spacexai/grok-4.20-multi-agent-beta", "object": "model", "created": 1755815280, - "released": 1773100800, + "released": 1773187200, "owned_by": "spacexai", - "name": "Grok 4.20 Multi-Agent", + "name": "Grok 4.20 Multi Agent Beta", "description": "Multiple agents collaborate in parallel to perform deep research tasks.", "context_window": 2000000, "max_tokens": 2000000, @@ -20894,43 +24968,29 @@ "min": 200001 } ], - "web_search": "5", - "service_tiers": { - "priority": { - "input": "0.0000025", - "output": "0.000005", - "input_cache_read": "0.0000004", - "long_context": { - "threshold": 200001, - "input": "0.000005", - "output": "0.00001", - "input_cache_read": "0.0000008" - } - } - } + "web_search": "5" } }, { - "id": "spacexai/grok-4.20-multi-agent-beta", + "id": "spacexai/grok-4.20-non-reasoning", "object": "model", "created": 1755815280, - "released": 1773187200, + "released": 1773100800, "owned_by": "spacexai", - "name": "Grok 4.20 Multi Agent Beta", - "description": "Multiple agents collaborate in parallel to perform deep research tasks.", + "name": "Grok 4.20 Non-Reasoning", + "description": "Grok 4.20 Beta is the newest flagship model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherence, delivering consistently precise and truthful responses.", "context_window": 2000000, "max_tokens": 2000000, "type": "language", "zdr": "all", "no_training": "all", "tags": [ - "reasoning", "tool-use", "implicit-caching", - "vision", "file-input", - "web-search", - "structured-output" + "vision", + "structured-output", + "web-search" ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { @@ -20995,31 +25055,44 @@ "min": 200001 } ], - "web_search": "5" + "web_search": "5", + "service_tiers": { + "priority": { + "input": "0.0000025", + "output": "0.000005", + "input_cache_read": "0.0000004", + "long_context": { + "threshold": 200001, + "input": "0.000005", + "output": "0.00001", + "input_cache_read": "0.0000008" + } + } + }, + "varies_by_provider": true } }, { - "id": "spacexai/grok-4.20-non-reasoning", + "id": "spacexai/grok-4.20-non-reasoning-batch", "object": "model", "created": 1755815280, "released": 1773100800, "owned_by": "spacexai", - "name": "Grok 4.20 Non-Reasoning", + "name": "Grok 4.20 Non-Reasoning (Batch)", "description": "Grok 4.20 Beta is the newest flagship model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherence, delivering consistently precise and truthful responses.", "context_window": 2000000, "max_tokens": 2000000, "type": "language", - "zdr": "all", + "zdr": "none", "no_training": "all", "tags": [ "tool-use", "implicit-caching", "file-input", "vision", - "structured-output", - "web-search" + "structured-output" ], - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v4"], "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] @@ -21046,57 +25119,42 @@ } ], "pricing": { - "input": "0.00000125", + "input": "0.000001", "input_tiers": [ { - "cost": "0.00000125", + "cost": "0.000001", "min": 0, "max": 200001 }, { - "cost": "0.0000025", + "cost": "0.000002", "min": 200001 } ], - "output": "0.0000025", + "output": "0.000002", "output_tiers": [ { - "cost": "0.0000025", + "cost": "0.000002", "min": 0, "max": 200001 }, { - "cost": "0.000005", + "cost": "0.000004", "min": 200001 } ], - "input_cache_read": "0.0000002", + "input_cache_read": "0.00000016", "input_cache_read_tiers": [ { - "cost": "0.0000002", + "cost": "0.00000016", "min": 0, "max": 200001 }, { - "cost": "0.0000004", + "cost": "0.00000032", "min": 200001 } - ], - "web_search": "5", - "service_tiers": { - "priority": { - "input": "0.0000025", - "output": "0.000005", - "input_cache_read": "0.0000004", - "long_context": { - "threshold": 200001, - "input": "0.000005", - "output": "0.00001", - "input_cache_read": "0.0000008" - } - } - }, - "varies_by_provider": true + ] } }, { @@ -21283,6 +25341,92 @@ "varies_by_provider": true } }, + { + "id": "spacexai/grok-4.20-reasoning-batch", + "object": "model", + "created": 1755815280, + "released": 1773100800, + "owned_by": "spacexai", + "name": "Grok 4.20 Reasoning (Batch)", + "description": "Grok 4.20 Beta is the newest flagship model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherence, delivering consistently precise and truthful responses.", + "context_window": 2000000, + "max_tokens": 2000000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "reasoning", + "tool-use", + "implicit-caching", + "vision", + "file-input", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high"] + } + ], + "pricing": { + "input": "0.000001", + "input_tiers": [ + { + "cost": "0.000001", + "min": 0, + "max": 200001 + }, + { + "cost": "0.000002", + "min": 200001 + } + ], + "output": "0.000002", + "output_tiers": [ + { + "cost": "0.000002", + "min": 0, + "max": 200001 + }, + { + "cost": "0.000004", + "min": 200001 + } + ], + "input_cache_read": "0.00000016", + "input_cache_read_tiers": [ + { + "cost": "0.00000016", + "min": 0, + "max": 200001 + }, + { + "cost": "0.00000032", + "min": 200001 + } + ] + } + }, { "id": "spacexai/grok-4.20-reasoning-beta", "object": "model", @@ -21466,7 +25610,90 @@ "input_cache_read": "0.0000008" } } - } + } + } + }, + { + "id": "spacexai/grok-4.3-batch", + "object": "model", + "created": 1755815280, + "released": 1777507200, + "owned_by": "spacexai", + "name": "Grok 4.3 (Batch)", + "description": "Grok 4.3 is a new model matching the scale of Grok 4.20 with an improved architecture and a December 2025 knowledge cutoff.", + "context_window": 1000000, + "max_tokens": 1000000, + "type": "language", + "zdr": "none", + "no_training": "all", + "tags": [ + "reasoning", + "tool-use", + "implicit-caching", + "file-input", + "vision", + "structured-output" + ], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image", "pdf"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning", + "response_format", + "structured_outputs" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "effort", + "values": ["low", "medium", "high"] + } + ], + "pricing": { + "input": "0.000001", + "input_tiers": [ + { + "cost": "0.000001", + "min": 0, + "max": 200001 + }, + { + "cost": "0.000002", + "min": 200001 + } + ], + "output": "0.000002", + "output_tiers": [ + { + "cost": "0.000002", + "min": 0, + "max": 200001 + }, + { + "cost": "0.000004", + "min": 200001 + } + ], + "input_cache_read": "0.00000016", + "input_cache_read_tiers": [ + { + "cost": "0.00000016", + "min": 0, + "max": 200001 + }, + { + "cost": "0.00000032", + "min": 200001 + } + ] } }, { @@ -21953,7 +26180,7 @@ "type": "video", "zdr": "none", "no_training": "all", - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v3", "v4"], "modalities": { "input": ["text"], "output": ["video"] @@ -22030,7 +26257,7 @@ "type": "video", "zdr": "none", "no_training": "all", - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v3", "v4"], "modalities": { "input": ["text"], "output": ["video"] @@ -22105,7 +26332,7 @@ "type": "video", "zdr": "none", "no_training": "all", - "supported_specifications": ["v2", "v3", "v4"], + "supported_specifications": ["v3", "v4"], "modalities": { "input": ["text"], "output": ["video"] @@ -22225,18 +26452,19 @@ } }, { - "id": "spacexai/grok-voice-think-fast-1.0", + "id": "spacexai/grok-voice-3.0", "object": "model", "created": 1755815280, - "released": 1776902400, + "released": 1791936000, "owned_by": "spacexai", - "name": "Grok Voice Think Fast 1.0", - "description": "Build real-time voice applications powered by Grok. Stream audio and text bidirectionally via WebSocket for voice assistants, phone agents, and interactive voice systems.", + "name": "Grok Voice 3.0", + "description": "Grok Voice 3.0 is xAI’s realtime speech-to-speech model for interactive voice agents. It streams audio and text bidirectionally, supports multilingual conversations and function calling, and includes reasoning enabled by default for complex instructions and nuanced dialogue.", "context_window": 0, "max_tokens": 0, "type": "realtime", "zdr": "all", "no_training": "all", + "tags": ["audio-input", "reasoning", "tool-use", "websocket-realtime"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text", "audio"], @@ -22246,6 +26474,8 @@ "max_tokens", "temperature", "stop", + "tools", + "tool_choice", "reasoning", "include_reasoning" ], @@ -22261,7 +26491,7 @@ ], "pricing": { "realtime_client_message_cost": "0.004", - "realtime_session_duration_cost_per_second": "0.000834" + "realtime_session_duration_cost_per_second": "0.001334" } }, { @@ -22299,28 +26529,29 @@ "values": ["none", "low", "medium", "high"] } ], + "deprecated_at": 1793836800000, "pricing": { "realtime_client_message_cost": "0.004", "realtime_session_duration_cost_per_second": "0.001334" } }, { - "id": "stepfun/step-3.5-flash", + "id": "stealth/glyph-cluster", "object": "model", "created": 1755815280, - "released": 1769644800, - "owned_by": "stepfun", - "name": "StepFun 3.5 Flash", - "description": "Step 3.5 Flash is an open-source reasoning model by StepFun with 196B total parameters (11B active) using Mixture of Experts. It features a 256K context window, deep reasoning, tool calling, and agentic capabilities, achieving 97.3 on AIME 2025 and 74.4% on SWE-bench Verified.", - "context_window": 262114, - "max_tokens": 262114, + "released": 1791331200, + "owned_by": "stealth", + "name": "Glyph Cluster", + "description": "Glyph Cluster is an anonymous reasoning model in early access. Prompts and outputs will be retained by the provider.", + "context_window": 256000, + "max_tokens": 256000, "type": "language", - "zdr": "all", - "no_training": "all", - "tags": ["reasoning", "tool-use", "implicit-caching", "vision"], + "zdr": "none", + "no_training": "none", + "tags": ["reasoning", "tool-use", "implicit-caching"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { - "input": ["text", "image"], + "input": ["text"], "output": ["text"] }, "supported_parameters": [ @@ -22336,14 +26567,12 @@ "reasoning_options": [ { "type": "effort", - "values": ["low", "medium", "high"] + "values": ["low", "medium", "high", "xhigh"] } ], - "knowledge": "2025-01", "pricing": { - "input": "0.00000009", - "output": "0.0000003", - "input_cache_read": "0.00000002" + "input": "0", + "output": "0" } }, { @@ -22364,7 +26593,8 @@ "reasoning", "tool-use", "vision", - "structured-output" + "structured-output", + "open-weights" ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { @@ -22404,21 +26634,31 @@ "owned_by": "stepfun", "name": "Step 5 Preview", "description": "Step 5 Preview is StepFun’s flagship AI model for agentic coding, professional knowledge work, and financial analysis. Built on a sparse Mixture-of-Experts architecture with 600B total parameters and 27B active per token, it combines a 1M-token context window with vision input. From building interactive applications and debugging code to conducting research and producing analytical reports, it supports complex workflows that require sustained reasoning, tool use, and iterative refinement.", - "context_window": 1000000, - "max_tokens": 1000000, + "context_window": 1048576, + "max_tokens": 1048576, "type": "language", - "zdr": "none", - "no_training": "none", - "tags": ["implicit-caching", "vision", "structured-output"], + "zdr": "some", + "no_training": "some", + "tags": [ + "implicit-caching", + "reasoning", + "structured-output", + "tool-use", + "video-input", + "vision", + "open-weights" + ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { - "input": ["text", "image"], + "input": ["text", "image", "video"], "output": ["text"] }, "supported_parameters": [ "max_tokens", "temperature", "stop", + "tools", + "tool_choice", "reasoning", "include_reasoning", "response_format", @@ -22434,7 +26674,8 @@ "pricing": { "input": "0.000001", "output": "0.0000027", - "input_cache_read": "0.00000005" + "input_cache_read": "0.0000001", + "varies_by_provider": true } }, { @@ -22450,6 +26691,7 @@ "type": "language", "zdr": "none", "no_training": "none", + "tags": ["open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -22475,7 +26717,7 @@ "type": "language", "zdr": "none", "no_training": "none", - "tags": ["structured-output"], + "tags": ["structured-output", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -22507,7 +26749,7 @@ "type": "language", "zdr": "none", "no_training": "none", - "tags": ["structured-output"], + "tags": ["structured-output", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -22539,7 +26781,13 @@ "type": "language", "zdr": "some", "no_training": "some", - "tags": ["implicit-caching", "reasoning", "tool-use", "structured-output"], + "tags": [ + "implicit-caching", + "reasoning", + "tool-use", + "structured-output", + "open-weights" + ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -22583,7 +26831,7 @@ "type": "language", "zdr": "none", "no_training": "none", - "tags": ["reasoning", "tool-use", "implicit-caching"], + "tags": ["reasoning", "tool-use", "implicit-caching", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -22630,6 +26878,7 @@ "structured-output", "tool-use", "vision", + "open-weights", "file-input" ], "supported_specifications": ["v2", "v3", "v4"], @@ -22681,7 +26930,8 @@ "vision", "file-input", "implicit-caching", - "structured-output" + "structured-output", + "open-weights" ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { @@ -22796,6 +27046,54 @@ "output": "0" } }, + { + "id": "typesafe-ai/jev-1.13.0", + "object": "model", + "created": 1755815280, + "released": 1789430400, + "owned_by": "typesafe-ai", + "name": "Jev 1.13.0", + "description": "Jev 1.13.0 is TypeSafe AI’s System One evaluation model for fast, structured decisions in software. It evaluates shared state against typed questions and returns choices, scores, and boolean probabilities, supporting classification, routing, rubric-based assessment, and automated verification. Multiple questions can be evaluated in parallel within a single request.", + "context_window": 32000, + "max_tokens": 0, + "type": "evaluation", + "zdr": "all", + "no_training": "all", + "tags": ["vision"], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image"], + "output": ["text"] + }, + "pricing": { + "input": "0.000000042", + "output": "0" + } + }, + { + "id": "typesafe-ai/jev-1.14.0", + "object": "model", + "created": 1755815280, + "released": 1792022400, + "owned_by": "typesafe-ai", + "name": "Jev 1.14.0", + "description": "Jev 1.14.0 is TypeSafe AI’s System One evaluation model for fast, structured decisions in software. It evaluates shared state against typed questions and returns choices, scores, and boolean probabilities, supporting classification, routing, rubric-based assessment, and automated verification. Multiple questions can be evaluated in parallel within a single request.", + "context_window": 32000, + "max_tokens": 0, + "type": "evaluation", + "zdr": "all", + "no_training": "all", + "tags": ["vision"], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text", "image"], + "output": ["text"] + }, + "pricing": { + "input": "0.000000042", + "output": "0" + } + }, { "id": "voyage/rerank-2.5", "object": "model", @@ -23115,14 +27413,15 @@ "context_window": 1050000, "max_tokens": 131100, "type": "language", - "zdr": "some", - "no_training": "some", + "zdr": "none", + "no_training": "none", "tags": [ "reasoning", "tool-use", "implicit-caching", "vision", - "structured-output" + "structured-output", + "open-weights" ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { @@ -23148,10 +27447,9 @@ ], "knowledge": "2024-12", "pricing": { - "input": "0.00000014", - "output": "0.00000028", - "input_cache_read": "0.0000000028", - "varies_by_provider": true + "input": "0.000000119", + "output": "0.000000238", + "input_cache_read": "0.0000000025" } }, { @@ -23165,9 +27463,15 @@ "context_window": 1050000, "max_tokens": 131000, "type": "language", - "zdr": "some", - "no_training": "some", - "tags": ["reasoning", "tool-use", "implicit-caching", "structured-output"], + "zdr": "none", + "no_training": "none", + "tags": [ + "reasoning", + "tool-use", + "implicit-caching", + "structured-output", + "open-weights" + ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -23192,10 +27496,9 @@ ], "knowledge": "2024-12", "pricing": { - "input": "0.000000435", - "output": "0.00000087", - "input_cache_read": "0.0000000036", - "varies_by_provider": true + "input": "0.0000003045", + "output": "0.000000609", + "input_cache_read": "0.0000000028" } }, { @@ -23205,7 +27508,7 @@ "released": 1789948800, "owned_by": "xiaomi", "name": "MiMo V2.6 Flash", - "description": "MiMo-V2.6-Flash is an open-source Mixture-of-Experts model from Xiaomi with 309B total parameters and 15B activated per token. Its hybrid attention (sliding-window layers interleaved with global attention) keeps long-context serving efficient across a 1M-token context window. It accepts text and image input and is suited for coding, agent workflows and high-volume tool use.\n\nReasoning is supported and enabled by default.", + "description": "MiMo V2.6 Flash is Xiaomi's efficient multimodal reasoning model for coding, automation, and everyday agent workflows. It accepts text, images, audio, and video within a 1M-token context window, with up to 128K tokens of output. Deep thinking, tool calling, JSON mode, and prompt caching make it suitable for applications that need multimodal understanding at a lower token cost.", "context_window": 1048576, "max_tokens": 131072, "type": "language", @@ -23218,7 +27521,8 @@ "structured-output", "tool-use", "video-input", - "vision" + "vision", + "open-weights" ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { @@ -23247,9 +27551,9 @@ } ], "pricing": { - "input": "0.00000004", - "output": "0.00000128", - "input_cache_read": "0.00000004", + "input": "0.00000014", + "output": "0.00000028", + "input_cache_read": "0.0000000028", "varies_by_provider": true } }, @@ -23273,7 +27577,8 @@ "structured-output", "tool-use", "video-input", - "vision" + "vision", + "open-weights" ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { @@ -23328,7 +27633,8 @@ "structured-output", "tool-use", "video-input", - "vision" + "vision", + "open-weights" ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { @@ -23375,7 +27681,13 @@ "type": "language", "zdr": "none", "no_training": "none", - "tags": ["reasoning", "tool-use", "implicit-caching", "structured-output"], + "tags": [ + "reasoning", + "tool-use", + "implicit-caching", + "structured-output", + "open-weights" + ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -23419,7 +27731,13 @@ "type": "language", "zdr": "none", "no_training": "none", - "tags": ["reasoning", "tool-use", "implicit-caching", "structured-output"], + "tags": [ + "reasoning", + "tool-use", + "implicit-caching", + "structured-output", + "open-weights" + ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -23467,7 +27785,8 @@ "reasoning", "tool-use", "vision", - "structured-output" + "structured-output", + "open-weights" ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { @@ -23511,7 +27830,13 @@ "type": "language", "zdr": "some", "no_training": "some", - "tags": ["implicit-caching", "reasoning", "tool-use", "structured-output"], + "tags": [ + "implicit-caching", + "reasoning", + "tool-use", + "structured-output", + "open-weights" + ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -23556,7 +27881,13 @@ "type": "language", "zdr": "some", "no_training": "some", - "tags": ["reasoning", "tool-use", "structured-output", "implicit-caching"], + "tags": [ + "reasoning", + "tool-use", + "structured-output", + "open-weights", + "implicit-caching" + ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -23577,6 +27908,10 @@ "reasoning_options": [ { "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high"] } ], "knowledge": "2025-04", @@ -23600,7 +27935,13 @@ "type": "language", "zdr": "some", "no_training": "some", - "tags": ["reasoning", "tool-use", "structured-output", "implicit-caching"], + "tags": [ + "reasoning", + "tool-use", + "structured-output", + "open-weights", + "implicit-caching" + ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -23621,6 +27962,10 @@ "reasoning_options": [ { "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high"] } ], "knowledge": "2025-04", @@ -23642,7 +27987,7 @@ "type": "language", "zdr": "none", "no_training": "none", - "tags": ["reasoning", "tool-use", "implicit-caching"], + "tags": ["reasoning", "tool-use", "implicit-caching", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -23661,6 +28006,10 @@ "reasoning_options": [ { "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high"] } ], "knowledge": "2025-01", @@ -23684,7 +28033,13 @@ "type": "language", "zdr": "some", "no_training": "some", - "tags": ["reasoning", "tool-use", "structured-output", "implicit-caching"], + "tags": [ + "reasoning", + "tool-use", + "structured-output", + "open-weights", + "implicit-caching" + ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -23705,6 +28060,10 @@ "reasoning_options": [ { "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high"] } ], "pricing": { @@ -23744,6 +28103,10 @@ "reasoning_options": [ { "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high"] } ], "pricing": { @@ -23763,9 +28126,15 @@ "context_window": 202800, "max_tokens": 64000, "type": "language", - "zdr": "some", - "no_training": "some", - "tags": ["implicit-caching", "reasoning", "tool-use", "structured-output"], + "zdr": "none", + "no_training": "none", + "tags": [ + "implicit-caching", + "reasoning", + "tool-use", + "structured-output", + "open-weights" + ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -23786,6 +28155,10 @@ "reasoning_options": [ { "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high"] } ], "pricing": { @@ -23808,7 +28181,13 @@ "type": "language", "zdr": "some", "no_training": "some", - "tags": ["reasoning", "tool-use", "implicit-caching", "structured-output"], + "tags": [ + "reasoning", + "tool-use", + "implicit-caching", + "structured-output", + "open-weights" + ], "regions": ["us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { @@ -23873,7 +28252,13 @@ "type": "language", "zdr": "all", "no_training": "all", - "tags": ["reasoning", "tool-use", "implicit-caching", "structured-output"], + "tags": [ + "reasoning", + "tool-use", + "implicit-caching", + "structured-output", + "open-weights" + ], "regions": ["us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { @@ -23928,7 +28313,14 @@ "type": "language", "zdr": "some", "no_training": "some", - "tags": ["implicit-caching", "reasoning", "tool-use", "structured-output"], + "tags": [ + "implicit-caching", + "reasoning", + "tool-use", + "structured-output", + "open-weights", + "explicit-caching" + ], "regions": ["us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { @@ -23985,7 +28377,13 @@ "type": "language", "zdr": "all", "no_training": "all", - "tags": ["reasoning", "tool-use", "implicit-caching", "structured-output"], + "tags": [ + "reasoning", + "tool-use", + "implicit-caching", + "open-weights", + "structured-output" + ], "regions": ["us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { @@ -24045,12 +28443,14 @@ "tool-use", "implicit-caching", "vision", - "structured-output" + "structured-output", + "open-weights", + "video-input" ], "regions": ["us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { - "input": ["text", "image"], + "input": ["text", "image", "video"], "output": ["text"] }, "supported_parameters": [ @@ -24103,7 +28503,8 @@ "tool-use", "implicit-caching", "vision", - "structured-output" + "structured-output", + "open-weights" ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { @@ -24175,6 +28576,10 @@ "reasoning_options": [ { "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high"] } ], "pricing": {